| { | |
| "best_metric": 1.517209529876709, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-dilation-corrected\\checkpoint-110544", | |
| "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": 9.600781589231439e-06, | |
| "loss": 2.4024, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.761290192604065, | |
| "eval_runtime": 236.9885, | |
| "eval_samples_per_second": 7.515, | |
| "eval_steps_per_second": 0.941, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.200955275727314e-06, | |
| "loss": 2.1798, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.7138808965682983, | |
| "eval_runtime": 239.8342, | |
| "eval_samples_per_second": 7.426, | |
| "eval_steps_per_second": 0.93, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.80104211897525e-06, | |
| "loss": 2.1158, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.6784090995788574, | |
| "eval_runtime": 240.3185, | |
| "eval_samples_per_second": 7.411, | |
| "eval_steps_per_second": 0.928, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.401128962223187e-06, | |
| "loss": 2.0907, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.651432752609253, | |
| "eval_runtime": 240.8773, | |
| "eval_samples_per_second": 7.394, | |
| "eval_steps_per_second": 0.926, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.001389491967e-06, | |
| "loss": 2.0665, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.6573233604431152, | |
| "eval_runtime": 241.2613, | |
| "eval_samples_per_second": 7.382, | |
| "eval_steps_per_second": 0.924, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.601476335214938e-06, | |
| "loss": 2.0511, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.6507837772369385, | |
| "eval_runtime": 240.9902, | |
| "eval_samples_per_second": 7.39, | |
| "eval_steps_per_second": 0.925, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.201650021710812e-06, | |
| "loss": 2.0401, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.6144988536834717, | |
| "eval_runtime": 241.2052, | |
| "eval_samples_per_second": 7.384, | |
| "eval_steps_per_second": 0.925, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.801823708206688e-06, | |
| "loss": 2.0217, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6352990865707397, | |
| "eval_runtime": 241.2577, | |
| "eval_samples_per_second": 7.382, | |
| "eval_steps_per_second": 0.924, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.4020842379505e-06, | |
| "loss": 2.0119, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6176352500915527, | |
| "eval_runtime": 241.7767, | |
| "eval_samples_per_second": 7.366, | |
| "eval_steps_per_second": 0.922, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.0021710811984364e-06, | |
| "loss": 1.9921, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6012073755264282, | |
| "eval_runtime": 247.8336, | |
| "eval_samples_per_second": 7.186, | |
| "eval_steps_per_second": 0.9, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5.602344767694312e-06, | |
| "loss": 1.9841, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.5831871032714844, | |
| "eval_runtime": 241.576, | |
| "eval_samples_per_second": 7.372, | |
| "eval_steps_per_second": 0.923, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.20243161094225e-06, | |
| "loss": 1.9774, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.6204363107681274, | |
| "eval_runtime": 241.4129, | |
| "eval_samples_per_second": 7.377, | |
| "eval_steps_per_second": 0.924, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.802605297438124e-06, | |
| "loss": 1.9567, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.5836392641067505, | |
| "eval_runtime": 241.5967, | |
| "eval_samples_per_second": 7.372, | |
| "eval_steps_per_second": 0.923, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.402778983934e-06, | |
| "loss": 1.9542, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.5788718461990356, | |
| "eval_runtime": 241.4156, | |
| "eval_samples_per_second": 7.377, | |
| "eval_steps_per_second": 0.924, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.002865827181937e-06, | |
| "loss": 1.9347, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.5565046072006226, | |
| "eval_runtime": 240.9493, | |
| "eval_samples_per_second": 7.392, | |
| "eval_steps_per_second": 0.926, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.6029526704298744e-06, | |
| "loss": 1.9348, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.5833003520965576, | |
| "eval_runtime": 241.3442, | |
| "eval_samples_per_second": 7.38, | |
| "eval_steps_per_second": 0.924, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.203039513677812e-06, | |
| "loss": 1.9188, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.5547460317611694, | |
| "eval_runtime": 240.9652, | |
| "eval_samples_per_second": 7.391, | |
| "eval_steps_per_second": 0.925, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.8031263569257496e-06, | |
| "loss": 1.9085, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.5456182956695557, | |
| "eval_runtime": 241.1028, | |
| "eval_samples_per_second": 7.387, | |
| "eval_steps_per_second": 0.925, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.403473729917499e-06, | |
| "loss": 1.8956, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.5432853698730469, | |
| "eval_runtime": 242.3443, | |
| "eval_samples_per_second": 7.349, | |
| "eval_steps_per_second": 0.92, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.003647416413374e-06, | |
| "loss": 1.8891, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.5555381774902344, | |
| "eval_runtime": 241.9085, | |
| "eval_samples_per_second": 7.362, | |
| "eval_steps_per_second": 0.922, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.6037342596613115e-06, | |
| "loss": 1.8899, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.5277676582336426, | |
| "eval_runtime": 241.2143, | |
| "eval_samples_per_second": 7.383, | |
| "eval_steps_per_second": 0.924, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.203821102909249e-06, | |
| "loss": 1.8782, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.5234768390655518, | |
| "eval_runtime": 240.7814, | |
| "eval_samples_per_second": 7.397, | |
| "eval_steps_per_second": 0.926, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.040816326530614e-07, | |
| "loss": 1.8676, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.531404733657837, | |
| "eval_runtime": 240.8805, | |
| "eval_samples_per_second": 7.394, | |
| "eval_steps_per_second": 0.926, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.0425531914893625e-07, | |
| "loss": 1.8699, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.517209529876709, | |
| "eval_runtime": 241.0222, | |
| "eval_samples_per_second": 7.389, | |
| "eval_steps_per_second": 0.925, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.429005644811116e-09, | |
| "loss": 1.8627, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.5202314853668213, | |
| "eval_runtime": 240.9969, | |
| "eval_samples_per_second": 7.39, | |
| "eval_steps_per_second": 0.925, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 115150, | |
| "total_flos": 2.2008141195206407e+20, | |
| "train_loss": 1.9877705201096396, | |
| "train_runtime": 99033.2526, | |
| "train_samples_per_second": 4.65, | |
| "train_steps_per_second": 1.163 | |
| } | |
| ], | |
| "max_steps": 115150, | |
| "num_train_epochs": 25, | |
| "total_flos": 2.2008141195206407e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |