| { | |
| "best_metric": 1.8324859142303467, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-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": 9.001953973078595e-06, | |
| "loss": 3.0619, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.193356990814209, | |
| "eval_runtime": 202.8391, | |
| "eval_samples_per_second": 8.78, | |
| "eval_steps_per_second": 1.099, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002388189318281e-06, | |
| "loss": 2.6954, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.0489742755889893, | |
| "eval_runtime": 202.1581, | |
| "eval_samples_per_second": 8.81, | |
| "eval_steps_per_second": 1.103, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.002605297438124e-06, | |
| "loss": 2.5695, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.984281063079834, | |
| "eval_runtime": 202.0926, | |
| "eval_samples_per_second": 8.813, | |
| "eval_steps_per_second": 1.103, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003039513677812e-06, | |
| "loss": 2.518, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.9648078680038452, | |
| "eval_runtime": 201.8792, | |
| "eval_samples_per_second": 8.822, | |
| "eval_steps_per_second": 1.105, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.0034737299175e-06, | |
| "loss": 2.4652, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.935389757156372, | |
| "eval_runtime": 199.4005, | |
| "eval_samples_per_second": 8.932, | |
| "eval_steps_per_second": 1.118, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.003907946157187e-06, | |
| "loss": 2.4235, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.9127476215362549, | |
| "eval_runtime": 199.1339, | |
| "eval_samples_per_second": 8.944, | |
| "eval_steps_per_second": 1.12, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.00412505427703e-06, | |
| "loss": 2.3947, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.871512532234192, | |
| "eval_runtime": 201.6282, | |
| "eval_samples_per_second": 8.833, | |
| "eval_steps_per_second": 1.106, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0045592705167173e-06, | |
| "loss": 2.369, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.856353998184204, | |
| "eval_runtime": 196.2259, | |
| "eval_samples_per_second": 9.076, | |
| "eval_steps_per_second": 1.136, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0049934867564047e-06, | |
| "loss": 2.3542, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.8511120080947876, | |
| "eval_runtime": 203.2322, | |
| "eval_samples_per_second": 8.763, | |
| "eval_steps_per_second": 1.097, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.427702996092055e-09, | |
| "loss": 2.3407, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.8324859142303467, | |
| "eval_runtime": 201.5085, | |
| "eval_samples_per_second": 8.838, | |
| "eval_steps_per_second": 1.107, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 7.575060159014402e+19, | |
| "train_loss": 1.4347297936794399, | |
| "train_runtime": 16954.3153, | |
| "train_samples_per_second": 10.865, | |
| "train_steps_per_second": 2.717 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 7.575060159014402e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |