| { | |
| "best_metric": 1.8343534469604492, | |
| "best_model_checkpoint": "cdetr-r50-cd45rb-all-4ah\\checkpoint-23030", | |
| "epoch": 10.0, | |
| "global_step": 23030, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.003039513677813e-06, | |
| "loss": 2.165, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.0256807804107666, | |
| "eval_runtime": 417.1917, | |
| "eval_samples_per_second": 4.269, | |
| "eval_steps_per_second": 0.535, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.003907946157187e-06, | |
| "loss": 1.9843, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9741652011871338, | |
| "eval_runtime": 403.5768, | |
| "eval_samples_per_second": 4.413, | |
| "eval_steps_per_second": 0.553, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003907946157187e-06, | |
| "loss": 1.9296, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.9122804403305054, | |
| "eval_runtime": 401.3575, | |
| "eval_samples_per_second": 4.437, | |
| "eval_steps_per_second": 0.556, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.0043421623968744e-06, | |
| "loss": 1.8949, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.8927873373031616, | |
| "eval_runtime": 408.1494, | |
| "eval_samples_per_second": 4.364, | |
| "eval_steps_per_second": 0.546, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.005210594876249e-06, | |
| "loss": 1.8751, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.9116449356079102, | |
| "eval_runtime": 406.0082, | |
| "eval_samples_per_second": 4.387, | |
| "eval_steps_per_second": 0.549, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.005210594876249e-06, | |
| "loss": 1.854, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.8909248113632202, | |
| "eval_runtime": 396.4567, | |
| "eval_samples_per_second": 4.492, | |
| "eval_steps_per_second": 0.562, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.005644811115936e-06, | |
| "loss": 1.8354, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.8532779216766357, | |
| "eval_runtime": 390.3322, | |
| "eval_samples_per_second": 4.563, | |
| "eval_steps_per_second": 0.571, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0060790273556234e-06, | |
| "loss": 1.8257, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.8406795263290405, | |
| "eval_runtime": 388.3033, | |
| "eval_samples_per_second": 4.587, | |
| "eval_steps_per_second": 0.574, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0060790273556232e-06, | |
| "loss": 1.8101, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.8452762365341187, | |
| "eval_runtime": 395.2037, | |
| "eval_samples_per_second": 4.507, | |
| "eval_steps_per_second": 0.564, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.947459834997829e-09, | |
| "loss": 1.8025, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.8343534469604492, | |
| "eval_runtime": 390.5312, | |
| "eval_samples_per_second": 4.56, | |
| "eval_steps_per_second": 0.571, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 23030, | |
| "total_flos": 9.19423903761792e+19, | |
| "train_loss": 1.8976711761832392, | |
| "train_runtime": 56257.2381, | |
| "train_samples_per_second": 3.274, | |
| "train_steps_per_second": 0.409 | |
| } | |
| ], | |
| "max_steps": 23030, | |
| "num_train_epochs": 10, | |
| "total_flos": 9.19423903761792e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |