| { | |
| "best_metric": 1.5793741941452026, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l\\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": 8.003907946157187e-06, | |
| "loss": 2.4794, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8245322704315186, | |
| "eval_runtime": 201.5413, | |
| "eval_samples_per_second": 8.837, | |
| "eval_steps_per_second": 1.106, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.004776378636562e-06, | |
| "loss": 2.2469, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.7593357563018799, | |
| "eval_runtime": 206.2392, | |
| "eval_samples_per_second": 8.636, | |
| "eval_steps_per_second": 1.081, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.005644811115936e-06, | |
| "loss": 2.1817, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.7108566761016846, | |
| "eval_runtime": 206.9329, | |
| "eval_samples_per_second": 8.607, | |
| "eval_steps_per_second": 1.078, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.0065132435953105e-06, | |
| "loss": 2.1418, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.6976348161697388, | |
| "eval_runtime": 206.348, | |
| "eval_samples_per_second": 8.631, | |
| "eval_steps_per_second": 1.081, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.947459834997829e-09, | |
| "loss": 2.118, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.6694599390029907, | |
| "eval_runtime": 206.6437, | |
| "eval_samples_per_second": 8.619, | |
| "eval_steps_per_second": 1.079, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.003907946157187e-06, | |
| "loss": 2.1237, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.6780959367752075, | |
| "eval_runtime": 207.7036, | |
| "eval_samples_per_second": 8.575, | |
| "eval_steps_per_second": 1.074, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.004342162396874e-06, | |
| "loss": 2.1025, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.6574461460113525, | |
| "eval_runtime": 206.2072, | |
| "eval_samples_per_second": 8.637, | |
| "eval_steps_per_second": 1.081, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0043421623968738e-06, | |
| "loss": 2.0796, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6417841911315918, | |
| "eval_runtime": 206.3439, | |
| "eval_samples_per_second": 8.631, | |
| "eval_steps_per_second": 1.081, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0049934867564047e-06, | |
| "loss": 2.0672, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6333234310150146, | |
| "eval_runtime": 205.3701, | |
| "eval_samples_per_second": 8.672, | |
| "eval_steps_per_second": 1.086, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.210594876248372e-09, | |
| "loss": 2.0597, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.631255865097046, | |
| "eval_runtime": 206.8618, | |
| "eval_samples_per_second": 8.61, | |
| "eval_steps_per_second": 1.078, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5.6022579244463745e-06, | |
| "loss": 2.0948, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.65455162525177, | |
| "eval_runtime": 203.3509, | |
| "eval_samples_per_second": 8.758, | |
| "eval_steps_per_second": 1.097, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.202518454190188e-06, | |
| "loss": 2.0943, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.6905332803726196, | |
| "eval_runtime": 203.6074, | |
| "eval_samples_per_second": 8.747, | |
| "eval_steps_per_second": 1.095, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.8026921406860624e-06, | |
| "loss": 2.0819, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6430035829544067, | |
| "eval_runtime": 203.499, | |
| "eval_samples_per_second": 8.752, | |
| "eval_steps_per_second": 1.096, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.402865827181937e-06, | |
| "loss": 2.0795, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.6439093351364136, | |
| "eval_runtime": 203.71, | |
| "eval_samples_per_second": 8.743, | |
| "eval_steps_per_second": 1.095, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.002952670429874e-06, | |
| "loss": 2.0566, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.6448781490325928, | |
| "eval_runtime": 203.5479, | |
| "eval_samples_per_second": 8.75, | |
| "eval_steps_per_second": 1.096, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.603126356925749e-06, | |
| "loss": 2.0435, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6203994750976562, | |
| "eval_runtime": 203.4545, | |
| "eval_samples_per_second": 8.754, | |
| "eval_steps_per_second": 1.096, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.2033000434216244e-06, | |
| "loss": 2.0375, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.6195158958435059, | |
| "eval_runtime": 202.3983, | |
| "eval_samples_per_second": 8.799, | |
| "eval_steps_per_second": 1.102, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.803473729917499e-06, | |
| "loss": 2.032, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.6127674579620361, | |
| "eval_runtime": 206.9631, | |
| "eval_samples_per_second": 8.605, | |
| "eval_steps_per_second": 1.077, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.4035605731654367e-06, | |
| "loss": 2.0079, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.608217716217041, | |
| "eval_runtime": 202.2977, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 1.102, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.0037342596613115e-06, | |
| "loss": 1.9985, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.6037356853485107, | |
| "eval_runtime": 202.9099, | |
| "eval_samples_per_second": 8.777, | |
| "eval_steps_per_second": 1.099, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.6039947894051239e-06, | |
| "loss": 1.9976, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.6005302667617798, | |
| "eval_runtime": 202.3563, | |
| "eval_samples_per_second": 8.801, | |
| "eval_steps_per_second": 1.102, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.2040816326530612e-06, | |
| "loss": 1.9887, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.5969282388687134, | |
| "eval_runtime": 202.3053, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 1.102, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.042553191489362e-07, | |
| "loss": 1.9841, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.5841056108474731, | |
| "eval_runtime": 204.4797, | |
| "eval_samples_per_second": 8.71, | |
| "eval_steps_per_second": 1.091, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.043421623968737e-07, | |
| "loss": 1.9763, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.582602620124817, | |
| "eval_runtime": 204.7835, | |
| "eval_samples_per_second": 8.697, | |
| "eval_steps_per_second": 1.089, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.515848892748589e-09, | |
| "loss": 1.9686, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.5793741941452026, | |
| "eval_runtime": 204.7422, | |
| "eval_samples_per_second": 8.699, | |
| "eval_steps_per_second": 1.089, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 115150, | |
| "total_flos": 2.2008277540080006e+20, | |
| "train_loss": 1.217662907416956, | |
| "train_runtime": 44441.0276, | |
| "train_samples_per_second": 10.363, | |
| "train_steps_per_second": 2.591 | |
| } | |
| ], | |
| "max_steps": 115150, | |
| "num_train_epochs": 25, | |
| "total_flos": 2.2008277540080006e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |