| { | |
| "best_metric": 2.356618642807007, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-512d\\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": 9.001302648719063e-06, | |
| "loss": 3.7973, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.6332945823669434, | |
| "eval_runtime": 210.8129, | |
| "eval_samples_per_second": 8.448, | |
| "eval_steps_per_second": 1.058, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.001953973078594e-06, | |
| "loss": 3.3709, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.9579620361328125, | |
| "eval_runtime": 210.4075, | |
| "eval_samples_per_second": 8.465, | |
| "eval_steps_per_second": 1.06, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.002171081198438e-06, | |
| "loss": 3.3095, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.6953182220458984, | |
| "eval_runtime": 210.2643, | |
| "eval_samples_per_second": 8.47, | |
| "eval_steps_per_second": 1.061, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.002388189318281e-06, | |
| "loss": 3.2586, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.5300939083099365, | |
| "eval_runtime": 210.0522, | |
| "eval_samples_per_second": 8.479, | |
| "eval_steps_per_second": 1.062, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.002605297438125e-06, | |
| "loss": 3.1816, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.4802017211914062, | |
| "eval_runtime": 209.6764, | |
| "eval_samples_per_second": 8.494, | |
| "eval_steps_per_second": 1.064, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.003039513677812e-06, | |
| "loss": 3.1054, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.438953161239624, | |
| "eval_runtime": 209.669, | |
| "eval_samples_per_second": 8.494, | |
| "eval_steps_per_second": 1.064, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.003690838037343e-06, | |
| "loss": 3.0564, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.396704912185669, | |
| "eval_runtime": 209.0835, | |
| "eval_samples_per_second": 8.518, | |
| "eval_steps_per_second": 1.067, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0039079461571862e-06, | |
| "loss": 3.02, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.389368772506714, | |
| "eval_runtime": 208.3895, | |
| "eval_samples_per_second": 8.546, | |
| "eval_steps_per_second": 1.07, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0043421623968736e-06, | |
| "loss": 2.9957, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.367252826690674, | |
| "eval_runtime": 208.4267, | |
| "eval_samples_per_second": 8.545, | |
| "eval_steps_per_second": 1.07, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.559270516717325e-09, | |
| "loss": 2.9709, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.356618642807007, | |
| "eval_runtime": 208.5158, | |
| "eval_samples_per_second": 8.541, | |
| "eval_steps_per_second": 1.069, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 1.4680704123221757e+20, | |
| "train_loss": 3.2066407734137536, | |
| "train_runtime": 30464.6591, | |
| "train_samples_per_second": 6.047, | |
| "train_steps_per_second": 1.512 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.4680704123221757e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |