| { | |
| "best_metric": 2.3912506103515625, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-attdrop02\\checkpoint-41454", | |
| "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-07, | |
| "loss": 3.6528, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.7771737575531006, | |
| "eval_runtime": 203.0212, | |
| "eval_samples_per_second": 8.772, | |
| "eval_steps_per_second": 1.098, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002605297438124e-07, | |
| "loss": 3.3969, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.6611618995666504, | |
| "eval_runtime": 200.75, | |
| "eval_samples_per_second": 8.872, | |
| "eval_steps_per_second": 1.111, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003039513677811e-07, | |
| "loss": 3.2937, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.569552183151245, | |
| "eval_runtime": 200.8087, | |
| "eval_samples_per_second": 8.869, | |
| "eval_steps_per_second": 1.111, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003473729917499e-07, | |
| "loss": 3.2385, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.5185132026672363, | |
| "eval_runtime": 200.7723, | |
| "eval_samples_per_second": 8.871, | |
| "eval_steps_per_second": 1.111, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003690838037342e-07, | |
| "loss": 3.1884, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.4788544178009033, | |
| "eval_runtime": 200.6463, | |
| "eval_samples_per_second": 8.876, | |
| "eval_steps_per_second": 1.111, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.00412505427703e-07, | |
| "loss": 3.1504, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.4482903480529785, | |
| "eval_runtime": 200.9385, | |
| "eval_samples_per_second": 8.863, | |
| "eval_steps_per_second": 1.11, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0045592705167174e-07, | |
| "loss": 3.1188, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.424715757369995, | |
| "eval_runtime": 200.4709, | |
| "eval_samples_per_second": 8.884, | |
| "eval_steps_per_second": 1.112, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0047763786365608e-07, | |
| "loss": 3.0975, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.4002413749694824, | |
| "eval_runtime": 200.3404, | |
| "eval_samples_per_second": 8.89, | |
| "eval_steps_per_second": 1.113, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0052105948762483e-07, | |
| "loss": 3.0858, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.3912506103515625, | |
| "eval_runtime": 200.7723, | |
| "eval_samples_per_second": 8.871, | |
| "eval_steps_per_second": 1.111, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.644811115935736e-10, | |
| "loss": 3.0788, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.3955395221710205, | |
| "eval_runtime": 200.6016, | |
| "eval_samples_per_second": 8.878, | |
| "eval_steps_per_second": 1.112, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 7.575060159014402e+19, | |
| "train_loss": 3.230159858574414, | |
| "train_runtime": 28503.0086, | |
| "train_samples_per_second": 6.463, | |
| "train_steps_per_second": 1.616 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 7.575060159014402e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |