| { | |
| "best_metric": 1.7369647026062012, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-500q-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": 9.600868432479375e-06, | |
| "loss": 1.9439, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.0401558876037598, | |
| "eval_runtime": 1382.6016, | |
| "eval_samples_per_second": 1.288, | |
| "eval_steps_per_second": 0.161, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.201042118975251e-06, | |
| "loss": 1.91, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9975517988204956, | |
| "eval_runtime": 1419.7704, | |
| "eval_samples_per_second": 1.254, | |
| "eval_steps_per_second": 0.157, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.801302648719062e-06, | |
| "loss": 1.8797, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.9800050258636475, | |
| "eval_runtime": 1300.0427, | |
| "eval_samples_per_second": 1.37, | |
| "eval_steps_per_second": 0.172, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.401476335214937e-06, | |
| "loss": 1.8557, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.9186592102050781, | |
| "eval_runtime": 1396.4555, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.16, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.001563178462876e-06, | |
| "loss": 1.8409, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.9056885242462158, | |
| "eval_runtime": 707.528, | |
| "eval_samples_per_second": 2.517, | |
| "eval_steps_per_second": 0.315, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.60173686495875e-06, | |
| "loss": 1.8149, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.9150078296661377, | |
| "eval_runtime": 732.1035, | |
| "eval_samples_per_second": 2.433, | |
| "eval_steps_per_second": 0.305, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.2017368649587506e-06, | |
| "loss": 1.8095, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.8740921020507812, | |
| "eval_runtime": 740.742, | |
| "eval_samples_per_second": 2.404, | |
| "eval_steps_per_second": 0.301, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.8019105514546245e-06, | |
| "loss": 1.7931, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.8915313482284546, | |
| "eval_runtime": 393.6231, | |
| "eval_samples_per_second": 4.525, | |
| "eval_steps_per_second": 0.567, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.4019973947025625e-06, | |
| "loss": 1.7758, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.8704705238342285, | |
| "eval_runtime": 398.0752, | |
| "eval_samples_per_second": 4.474, | |
| "eval_steps_per_second": 0.56, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.0020842379505e-06, | |
| "loss": 1.7674, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.850295066833496, | |
| "eval_runtime": 534.0967, | |
| "eval_samples_per_second": 3.335, | |
| "eval_steps_per_second": 0.418, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5.602344767694312e-06, | |
| "loss": 1.7459, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.818764328956604, | |
| "eval_runtime": 696.4058, | |
| "eval_samples_per_second": 2.557, | |
| "eval_steps_per_second": 0.32, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.202518454190188e-06, | |
| "loss": 1.7322, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.8162474632263184, | |
| "eval_runtime": 720.9778, | |
| "eval_samples_per_second": 2.47, | |
| "eval_steps_per_second": 0.309, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.8026921406860624e-06, | |
| "loss": 1.721, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.800376057624817, | |
| "eval_runtime": 677.5807, | |
| "eval_samples_per_second": 2.628, | |
| "eval_steps_per_second": 0.329, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.402778983934e-06, | |
| "loss": 1.7109, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.7954081296920776, | |
| "eval_runtime": 630.3996, | |
| "eval_samples_per_second": 2.825, | |
| "eval_steps_per_second": 0.354, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.002952670429874e-06, | |
| "loss": 1.7027, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.7816314697265625, | |
| "eval_runtime": 631.78, | |
| "eval_samples_per_second": 2.819, | |
| "eval_steps_per_second": 0.353, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.603039513677812e-06, | |
| "loss": 1.6971, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.7844570875167847, | |
| "eval_runtime": 632.2022, | |
| "eval_samples_per_second": 2.817, | |
| "eval_steps_per_second": 0.353, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.2033000434216244e-06, | |
| "loss": 1.6812, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.7753602266311646, | |
| "eval_runtime": 625.6408, | |
| "eval_samples_per_second": 2.847, | |
| "eval_steps_per_second": 0.356, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.803300043421624e-06, | |
| "loss": 1.6735, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.7677279710769653, | |
| "eval_runtime": 577.7402, | |
| "eval_samples_per_second": 3.083, | |
| "eval_steps_per_second": 0.386, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.403473729917499e-06, | |
| "loss": 1.6696, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.770689606666565, | |
| "eval_runtime": 240.6916, | |
| "eval_samples_per_second": 7.4, | |
| "eval_steps_per_second": 0.926, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.003647416413374e-06, | |
| "loss": 1.6622, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.7661957740783691, | |
| "eval_runtime": 241.9531, | |
| "eval_samples_per_second": 7.361, | |
| "eval_steps_per_second": 0.922, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.603821102909249e-06, | |
| "loss": 1.6554, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.7594928741455078, | |
| "eval_runtime": 241.3426, | |
| "eval_samples_per_second": 7.38, | |
| "eval_steps_per_second": 0.924, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.2039079461571863e-06, | |
| "loss": 1.6529, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.7429261207580566, | |
| "eval_runtime": 240.7407, | |
| "eval_samples_per_second": 7.398, | |
| "eval_steps_per_second": 0.926, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.039947894051238e-07, | |
| "loss": 1.6441, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.739193081855774, | |
| "eval_runtime": 239.2341, | |
| "eval_samples_per_second": 7.445, | |
| "eval_steps_per_second": 0.932, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.041684759009987e-07, | |
| "loss": 1.6395, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.7394294738769531, | |
| "eval_runtime": 238.4537, | |
| "eval_samples_per_second": 7.469, | |
| "eval_steps_per_second": 0.935, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.25531914893617e-09, | |
| "loss": 1.6329, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.7369647026062012, | |
| "eval_runtime": 240.7806, | |
| "eval_samples_per_second": 7.397, | |
| "eval_steps_per_second": 0.926, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 115150, | |
| "total_flos": 2.2008141195206407e+20, | |
| "train_loss": 1.7444752132069583, | |
| "train_runtime": 191692.4998, | |
| "train_samples_per_second": 2.402, | |
| "train_steps_per_second": 0.601 | |
| } | |
| ], | |
| "max_steps": 115150, | |
| "num_train_epochs": 25, | |
| "total_flos": 2.2008141195206407e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |