| { | |
| "best_metric": 1.9994829893112183, | |
| "best_model_checkpoint": "detr-r101-cd45rb-4ah-4l-256d\\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": 9.002171081198437e-06, | |
| "loss": 3.7019, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.7623746395111084, | |
| "eval_runtime": 218.54, | |
| "eval_samples_per_second": 8.15, | |
| "eval_steps_per_second": 1.02, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002822405557968e-06, | |
| "loss": 3.242, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.4796128273010254, | |
| "eval_runtime": 218.2149, | |
| "eval_samples_per_second": 8.162, | |
| "eval_steps_per_second": 1.022, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003039513677812e-06, | |
| "loss": 3.0192, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.281315565109253, | |
| "eval_runtime": 218.7447, | |
| "eval_samples_per_second": 8.142, | |
| "eval_steps_per_second": 1.019, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003473729917499e-06, | |
| "loss": 2.863, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.188972234725952, | |
| "eval_runtime": 214.0495, | |
| "eval_samples_per_second": 8.321, | |
| "eval_steps_per_second": 1.042, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003907946157187e-06, | |
| "loss": 2.7702, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.124577283859253, | |
| "eval_runtime": 213.5259, | |
| "eval_samples_per_second": 8.341, | |
| "eval_steps_per_second": 1.044, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.0041250542770305e-06, | |
| "loss": 2.7018, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.112076759338379, | |
| "eval_runtime": 213.6474, | |
| "eval_samples_per_second": 8.336, | |
| "eval_steps_per_second": 1.044, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0045592705167175e-06, | |
| "loss": 2.6499, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.0616090297698975, | |
| "eval_runtime": 216.9309, | |
| "eval_samples_per_second": 8.21, | |
| "eval_steps_per_second": 1.028, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0047763786365613e-06, | |
| "loss": 2.6082, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.032071352005005, | |
| "eval_runtime": 210.629, | |
| "eval_samples_per_second": 8.456, | |
| "eval_steps_per_second": 1.059, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0052105948762484e-06, | |
| "loss": 2.5774, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.009509563446045, | |
| "eval_runtime": 212.984, | |
| "eval_samples_per_second": 8.362, | |
| "eval_steps_per_second": 1.047, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.427702996092055e-09, | |
| "loss": 2.5589, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.9994829893112183, | |
| "eval_runtime": 212.8648, | |
| "eval_samples_per_second": 8.367, | |
| "eval_steps_per_second": 1.048, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 1.1594350209611519e+20, | |
| "train_loss": 2.869251129640686, | |
| "train_runtime": 32768.7078, | |
| "train_samples_per_second": 5.622, | |
| "train_steps_per_second": 1.406 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.1594350209611519e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |