| { | |
| "best_metric": 1.9501873254776, | |
| "best_model_checkpoint": "detr-r50-cd45rb-2ah-6l\\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": 8.0034737299175e-06, | |
| "loss": 3.4851, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.4806125164031982, | |
| "eval_runtime": 237.1291, | |
| "eval_samples_per_second": 7.511, | |
| "eval_steps_per_second": 0.94, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.004776378636562e-06, | |
| "loss": 2.995, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.2760725021362305, | |
| "eval_runtime": 207.1825, | |
| "eval_samples_per_second": 8.596, | |
| "eval_steps_per_second": 1.076, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.005644811115936e-06, | |
| "loss": 2.7717, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.160128355026245, | |
| "eval_runtime": 205.8051, | |
| "eval_samples_per_second": 8.654, | |
| "eval_steps_per_second": 1.084, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.0060790273556234e-06, | |
| "loss": 2.674, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.0849480628967285, | |
| "eval_runtime": 198.2919, | |
| "eval_samples_per_second": 8.982, | |
| "eval_steps_per_second": 1.125, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.513243595310465e-09, | |
| "loss": 2.6185, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.070624589920044, | |
| "eval_runtime": 204.5209, | |
| "eval_samples_per_second": 8.708, | |
| "eval_steps_per_second": 1.09, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.0041250542770305e-06, | |
| "loss": 2.5992, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.0398733615875244, | |
| "eval_runtime": 206.6619, | |
| "eval_samples_per_second": 8.618, | |
| "eval_steps_per_second": 1.079, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.00412505427703e-06, | |
| "loss": 2.5376, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.999878168106079, | |
| "eval_runtime": 202.5511, | |
| "eval_samples_per_second": 8.793, | |
| "eval_steps_per_second": 1.101, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0045592705167173e-06, | |
| "loss": 2.4979, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.996376872062683, | |
| "eval_runtime": 206.6396, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 1.079, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0049934867564047e-06, | |
| "loss": 2.4669, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.9711166620254517, | |
| "eval_runtime": 201.9711, | |
| "eval_samples_per_second": 8.818, | |
| "eval_steps_per_second": 1.104, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.210594876248372e-09, | |
| "loss": 2.447, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.9501873254776, | |
| "eval_runtime": 205.7415, | |
| "eval_samples_per_second": 8.656, | |
| "eval_steps_per_second": 1.084, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 8.803311016032e+19, | |
| "train_loss": 1.2548531721531697, | |
| "train_runtime": 14767.0616, | |
| "train_samples_per_second": 12.474, | |
| "train_steps_per_second": 3.119 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.803311016032e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |