| { | |
| "best_metric": 4.966714859008789, | |
| "best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-1024ffn\\checkpoint-4606", | |
| "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": 9.002822405557969e-06, | |
| "loss": 4.7717, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 4.966714859008789, | |
| "eval_runtime": 221.1972, | |
| "eval_samples_per_second": 8.052, | |
| "eval_steps_per_second": 1.008, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.003256621797655e-06, | |
| "loss": 3.7186, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 5.014622211456299, | |
| "eval_runtime": 220.3269, | |
| "eval_samples_per_second": 8.083, | |
| "eval_steps_per_second": 1.012, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003473729917499e-06, | |
| "loss": 3.6825, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 5.00844144821167, | |
| "eval_runtime": 221.4773, | |
| "eval_samples_per_second": 8.041, | |
| "eval_steps_per_second": 1.007, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003907946157187e-06, | |
| "loss": 3.6793, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 5.032161235809326, | |
| "eval_runtime": 222.1159, | |
| "eval_samples_per_second": 8.018, | |
| "eval_steps_per_second": 1.004, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.00412505427703e-06, | |
| "loss": 3.673, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 5.032976150512695, | |
| "eval_runtime": 220.9746, | |
| "eval_samples_per_second": 8.06, | |
| "eval_steps_per_second": 1.009, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.004342162396874e-06, | |
| "loss": 3.6605, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 5.019674301147461, | |
| "eval_runtime": 218.4761, | |
| "eval_samples_per_second": 8.152, | |
| "eval_steps_per_second": 1.021, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.004993486756405e-06, | |
| "loss": 3.657, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 5.012796401977539, | |
| "eval_runtime": 218.8433, | |
| "eval_samples_per_second": 8.138, | |
| "eval_steps_per_second": 1.019, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0052105948762484e-06, | |
| "loss": 3.6543, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 5.012375831604004, | |
| "eval_runtime": 218.5519, | |
| "eval_samples_per_second": 8.149, | |
| "eval_steps_per_second": 1.02, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.005644811115936e-06, | |
| "loss": 3.6505, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 5.009885311126709, | |
| "eval_runtime": 219.0824, | |
| "eval_samples_per_second": 8.129, | |
| "eval_steps_per_second": 1.018, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.079027355623101e-09, | |
| "loss": 3.6484, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 5.015266418457031, | |
| "eval_runtime": 219.2706, | |
| "eval_samples_per_second": 8.122, | |
| "eval_steps_per_second": 1.017, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 1.1484829518739199e+20, | |
| "train_loss": 3.7795834831605513, | |
| "train_runtime": 34309.947, | |
| "train_samples_per_second": 5.369, | |
| "train_steps_per_second": 1.342 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.1484829518739199e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |