| { | |
| "best_metric": 1.5861479043960571, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-gelu-corrected\\checkpoint-115150", | |
| "epoch": 25.0, | |
| "global_step": 115150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.00238818931828e-06, | |
| "loss": 3.0438, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9413050413131714, | |
| "eval_runtime": 201.9196, | |
| "eval_samples_per_second": 8.82, | |
| "eval_steps_per_second": 1.104, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002822405557968e-06, | |
| "loss": 2.3933, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8238338232040405, | |
| "eval_runtime": 202.1836, | |
| "eval_samples_per_second": 8.809, | |
| "eval_steps_per_second": 1.103, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003039513677812e-06, | |
| "loss": 2.2782, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.771848440170288, | |
| "eval_runtime": 202.1516, | |
| "eval_samples_per_second": 8.81, | |
| "eval_steps_per_second": 1.103, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003473729917499e-06, | |
| "loss": 2.2383, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.752848505973816, | |
| "eval_runtime": 202.2922, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 1.102, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003690838037343e-06, | |
| "loss": 2.2046, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7264593839645386, | |
| "eval_runtime": 201.788, | |
| "eval_samples_per_second": 8.826, | |
| "eval_steps_per_second": 1.105, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.0041250542770305e-06, | |
| "loss": 2.1659, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.7125098705291748, | |
| "eval_runtime": 202.0053, | |
| "eval_samples_per_second": 8.817, | |
| "eval_steps_per_second": 1.104, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0045592705167175e-06, | |
| "loss": 2.1457, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.6760411262512207, | |
| "eval_runtime": 201.2859, | |
| "eval_samples_per_second": 8.848, | |
| "eval_steps_per_second": 1.108, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0047763786365613e-06, | |
| "loss": 2.1111, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6621686220169067, | |
| "eval_runtime": 201.2613, | |
| "eval_samples_per_second": 8.849, | |
| "eval_steps_per_second": 1.108, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0052105948762484e-06, | |
| "loss": 2.0959, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6466784477233887, | |
| "eval_runtime": 201.3173, | |
| "eval_samples_per_second": 8.847, | |
| "eval_steps_per_second": 1.108, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.427702996092055e-09, | |
| "loss": 2.0826, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.639158010482788, | |
| "eval_runtime": 201.0423, | |
| "eval_samples_per_second": 8.859, | |
| "eval_steps_per_second": 1.109, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.50293095961789e-06, | |
| "loss": 2.1132, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.687514305114746, | |
| "eval_runtime": 203.299, | |
| "eval_samples_per_second": 8.76, | |
| "eval_steps_per_second": 1.097, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.003039513677812e-06, | |
| "loss": 2.1145, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.6863107681274414, | |
| "eval_runtime": 203.0628, | |
| "eval_samples_per_second": 8.771, | |
| "eval_steps_per_second": 1.098, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.5032566217976557e-06, | |
| "loss": 2.0947, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6527632474899292, | |
| "eval_runtime": 203.1785, | |
| "eval_samples_per_second": 8.766, | |
| "eval_steps_per_second": 1.098, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.003582283977421e-06, | |
| "loss": 2.0777, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.666866660118103, | |
| "eval_runtime": 202.7783, | |
| "eval_samples_per_second": 8.783, | |
| "eval_steps_per_second": 1.1, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.5036908380373426e-06, | |
| "loss": 2.0551, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.6240596771240234, | |
| "eval_runtime": 203.6325, | |
| "eval_samples_per_second": 8.746, | |
| "eval_steps_per_second": 1.095, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.0037993920972645e-06, | |
| "loss": 2.0567, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6240826845169067, | |
| "eval_runtime": 203.7113, | |
| "eval_samples_per_second": 8.743, | |
| "eval_steps_per_second": 1.095, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.504233608336952e-06, | |
| "loss": 2.042, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.6171499490737915, | |
| "eval_runtime": 203.6475, | |
| "eval_samples_per_second": 8.746, | |
| "eval_steps_per_second": 1.095, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.004233608336952e-06, | |
| "loss": 2.0306, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.6062376499176025, | |
| "eval_runtime": 203.3215, | |
| "eval_samples_per_second": 8.76, | |
| "eval_steps_per_second": 1.097, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.043421623968737e-07, | |
| "loss": 2.015, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.5988867282867432, | |
| "eval_runtime": 203.4303, | |
| "eval_samples_per_second": 8.755, | |
| "eval_steps_per_second": 1.096, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.0037342596613115e-06, | |
| "loss": 2.0206, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.6168476343154907, | |
| "eval_runtime": 207.1893, | |
| "eval_samples_per_second": 8.596, | |
| "eval_steps_per_second": 1.076, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.6039947894051239e-06, | |
| "loss": 2.026, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.6022319793701172, | |
| "eval_runtime": 206.9802, | |
| "eval_samples_per_second": 8.605, | |
| "eval_steps_per_second": 1.077, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.2041684759009988e-06, | |
| "loss": 2.0109, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.5995537042617798, | |
| "eval_runtime": 206.8836, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 1.078, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.042553191489362e-07, | |
| "loss": 2.0133, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.5983381271362305, | |
| "eval_runtime": 206.4758, | |
| "eval_samples_per_second": 8.626, | |
| "eval_steps_per_second": 1.08, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.043421623968737e-07, | |
| "loss": 2.0081, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.5887646675109863, | |
| "eval_runtime": 203.9191, | |
| "eval_samples_per_second": 8.734, | |
| "eval_steps_per_second": 1.094, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.515848892748589e-09, | |
| "loss": 1.9975, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.5861479043960571, | |
| "eval_runtime": 204.8681, | |
| "eval_samples_per_second": 8.693, | |
| "eval_steps_per_second": 1.089, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 115150, | |
| "total_flos": 2.2008141195206407e+20, | |
| "train_loss": 0.4830571452317629, | |
| "train_runtime": 17891.958, | |
| "train_samples_per_second": 25.739, | |
| "train_steps_per_second": 6.436 | |
| } | |
| ], | |
| "max_steps": 115150, | |
| "num_train_epochs": 25, | |
| "total_flos": 2.2008141195206407e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |