| { | |
| "best_metric": 1.6447107791900635, | |
| "best_model_checkpoint": "detr-r101-cd45rb-8ah-12l\\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": 3.0401, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.163705587387085, | |
| "eval_runtime": 222.5701, | |
| "eval_samples_per_second": 8.002, | |
| "eval_steps_per_second": 1.002, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002822405557968e-06, | |
| "loss": 2.7151, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.06657338142395, | |
| "eval_runtime": 222.3447, | |
| "eval_samples_per_second": 8.01, | |
| "eval_steps_per_second": 1.003, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003039513677812e-06, | |
| "loss": 2.6021, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.986824870109558, | |
| "eval_runtime": 226.29, | |
| "eval_samples_per_second": 7.87, | |
| "eval_steps_per_second": 0.985, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003473729917499e-06, | |
| "loss": 2.5221, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.8957558870315552, | |
| "eval_runtime": 219.599, | |
| "eval_samples_per_second": 8.11, | |
| "eval_steps_per_second": 1.015, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003907946157187e-06, | |
| "loss": 2.4541, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.8809998035430908, | |
| "eval_runtime": 222.9944, | |
| "eval_samples_per_second": 7.987, | |
| "eval_steps_per_second": 1.0, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.0041250542770305e-06, | |
| "loss": 2.4155, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.8369228839874268, | |
| "eval_runtime": 220.1885, | |
| "eval_samples_per_second": 8.089, | |
| "eval_steps_per_second": 1.013, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0047763786365614e-06, | |
| "loss": 2.3531, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.8039908409118652, | |
| "eval_runtime": 225.4193, | |
| "eval_samples_per_second": 7.901, | |
| "eval_steps_per_second": 0.989, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.004993486756405e-06, | |
| "loss": 2.31, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.797875165939331, | |
| "eval_runtime": 219.4975, | |
| "eval_samples_per_second": 8.114, | |
| "eval_steps_per_second": 1.016, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0054277029960922e-06, | |
| "loss": 2.2841, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.7520661354064941, | |
| "eval_runtime": 222.6235, | |
| "eval_samples_per_second": 8.0, | |
| "eval_steps_per_second": 1.002, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.644811115935737e-09, | |
| "loss": 2.2555, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.7242921590805054, | |
| "eval_runtime": 220.3572, | |
| "eval_samples_per_second": 8.082, | |
| "eval_steps_per_second": 1.012, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5.602518454190186e-06, | |
| "loss": 2.3388, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.8519611358642578, | |
| "eval_runtime": 224.9013, | |
| "eval_samples_per_second": 7.919, | |
| "eval_steps_per_second": 0.992, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.202605297438124e-06, | |
| "loss": 2.3523, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.8499144315719604, | |
| "eval_runtime": 224.2008, | |
| "eval_samples_per_second": 7.944, | |
| "eval_steps_per_second": 0.995, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.802778983933999e-06, | |
| "loss": 2.3515, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.7634978294372559, | |
| "eval_runtime": 225.8943, | |
| "eval_samples_per_second": 7.884, | |
| "eval_steps_per_second": 0.987, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.402865827181937e-06, | |
| "loss": 2.3236, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.7787134647369385, | |
| "eval_runtime": 223.7953, | |
| "eval_samples_per_second": 7.958, | |
| "eval_steps_per_second": 0.996, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.002952670429874e-06, | |
| "loss": 2.2676, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.7517672777175903, | |
| "eval_runtime": 226.211, | |
| "eval_samples_per_second": 7.873, | |
| "eval_steps_per_second": 0.986, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.6033000434216243e-06, | |
| "loss": 2.2787, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.7879087924957275, | |
| "eval_runtime": 223.8881, | |
| "eval_samples_per_second": 7.955, | |
| "eval_steps_per_second": 0.996, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.2033868866695615e-06, | |
| "loss": 2.2523, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.7303467988967896, | |
| "eval_runtime": 223.161, | |
| "eval_samples_per_second": 7.981, | |
| "eval_steps_per_second": 0.999, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.8035605731654363e-06, | |
| "loss": 2.2357, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.7361239194869995, | |
| "eval_runtime": 222.8596, | |
| "eval_samples_per_second": 7.992, | |
| "eval_steps_per_second": 1.001, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.4036474164133743e-06, | |
| "loss": 2.2068, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.691589117050171, | |
| "eval_runtime": 223.3285, | |
| "eval_samples_per_second": 7.975, | |
| "eval_steps_per_second": 0.999, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.0037342596613115e-06, | |
| "loss": 2.1972, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.6940640211105347, | |
| "eval_runtime": 222.4012, | |
| "eval_samples_per_second": 8.008, | |
| "eval_steps_per_second": 1.003, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.6039079461571863e-06, | |
| "loss": 2.1856, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.6824039220809937, | |
| "eval_runtime": 219.7189, | |
| "eval_samples_per_second": 8.106, | |
| "eval_steps_per_second": 1.015, | |
| "step": 96726 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.2039947894051239e-06, | |
| "loss": 2.1611, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.6710505485534668, | |
| "eval_runtime": 219.2608, | |
| "eval_samples_per_second": 8.123, | |
| "eval_steps_per_second": 1.017, | |
| "step": 101332 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.041684759009987e-07, | |
| "loss": 2.1419, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.6535351276397705, | |
| "eval_runtime": 220.9951, | |
| "eval_samples_per_second": 8.059, | |
| "eval_steps_per_second": 1.009, | |
| "step": 105938 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.0425531914893625e-07, | |
| "loss": 2.1412, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.6602009534835815, | |
| "eval_runtime": 477.2637, | |
| "eval_samples_per_second": 3.732, | |
| "eval_steps_per_second": 0.467, | |
| "step": 110544 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.515848892748589e-09, | |
| "loss": 2.1285, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.6447107791900635, | |
| "eval_runtime": 581.8045, | |
| "eval_samples_per_second": 3.061, | |
| "eval_steps_per_second": 0.383, | |
| "step": 115150 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 115150, | |
| "total_flos": 4.126770236983678e+20, | |
| "train_loss": 0.4303329726172384, | |
| "train_runtime": 23864.0904, | |
| "train_samples_per_second": 19.298, | |
| "train_steps_per_second": 4.825 | |
| } | |
| ], | |
| "max_steps": 115150, | |
| "num_train_epochs": 25, | |
| "total_flos": 4.126770236983678e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |