| { | |
| "best_metric": 0.19675925925925927, | |
| "best_model_checkpoint": "microsoft-resnet-50-cartoon-face-recognition/checkpoint-24", | |
| "epoch": 19.88888888888889, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.06712962962962964, | |
| "eval_f1": 0.04268330700511537, | |
| "eval_loss": 3.1718316078186035, | |
| "eval_precision": 0.07750900471648707, | |
| "eval_recall": 0.06712962962962964, | |
| "eval_runtime": 6.9896, | |
| "eval_samples_per_second": 61.806, | |
| "eval_steps_per_second": 1.001, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001, | |
| "loss": 3.409, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.09722222222222222, | |
| "eval_f1": 0.06941620132016908, | |
| "eval_loss": 3.1434757709503174, | |
| "eval_precision": 0.09483282105538404, | |
| "eval_recall": 0.09722222222222222, | |
| "eval_runtime": 6.3177, | |
| "eval_samples_per_second": 68.379, | |
| "eval_steps_per_second": 1.108, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.16666666666666666, | |
| "eval_f1": 0.1157640285514969, | |
| "eval_loss": 3.1100411415100098, | |
| "eval_precision": 0.12231976324858271, | |
| "eval_recall": 0.16666666666666666, | |
| "eval_runtime": 5.8995, | |
| "eval_samples_per_second": 73.226, | |
| "eval_steps_per_second": 1.187, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 3.597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.19675925925925927, | |
| "eval_f1": 0.11625378991501253, | |
| "eval_loss": 3.0767667293548584, | |
| "eval_precision": 0.13583887289090224, | |
| "eval_recall": 0.19675925925925927, | |
| "eval_runtime": 5.9054, | |
| "eval_samples_per_second": 73.153, | |
| "eval_steps_per_second": 1.185, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2968, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_accuracy": 0.17592592592592593, | |
| "eval_f1": 0.08794959812293887, | |
| "eval_loss": 3.051513195037842, | |
| "eval_precision": 0.08687890109673733, | |
| "eval_recall": 0.17592592592592593, | |
| "eval_runtime": 5.8218, | |
| "eval_samples_per_second": 74.204, | |
| "eval_steps_per_second": 1.202, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_accuracy": 0.1712962962962963, | |
| "eval_f1": 0.06999759781046332, | |
| "eval_loss": 3.0226213932037354, | |
| "eval_precision": 0.0456331710295125, | |
| "eval_recall": 0.1712962962962963, | |
| "eval_runtime": 5.7818, | |
| "eval_samples_per_second": 74.718, | |
| "eval_steps_per_second": 1.211, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 8.888888888888888e-05, | |
| "loss": 3.4662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "eval_accuracy": 0.16666666666666666, | |
| "eval_f1": 0.07065656451437614, | |
| "eval_loss": 2.9997007846832275, | |
| "eval_precision": 0.04987179172442097, | |
| "eval_recall": 0.16666666666666666, | |
| "eval_runtime": 5.8712, | |
| "eval_samples_per_second": 73.579, | |
| "eval_steps_per_second": 1.192, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_accuracy": 0.1550925925925926, | |
| "eval_f1": 0.06279659825962769, | |
| "eval_loss": 2.977167844772339, | |
| "eval_precision": 0.046044346719881876, | |
| "eval_recall": 0.1550925925925926, | |
| "eval_runtime": 5.7878, | |
| "eval_samples_per_second": 74.64, | |
| "eval_steps_per_second": 1.209, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 3.4141, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_accuracy": 0.18518518518518517, | |
| "eval_f1": 0.08918606274115107, | |
| "eval_loss": 2.9533445835113525, | |
| "eval_precision": 0.16404070934618162, | |
| "eval_recall": 0.18518518518518517, | |
| "eval_runtime": 6.9368, | |
| "eval_samples_per_second": 62.277, | |
| "eval_steps_per_second": 1.009, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.1376, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_accuracy": 0.16666666666666666, | |
| "eval_f1": 0.07419287680822054, | |
| "eval_loss": 2.931124448776245, | |
| "eval_precision": 0.08951358417023512, | |
| "eval_recall": 0.16666666666666666, | |
| "eval_runtime": 5.8186, | |
| "eval_samples_per_second": 74.244, | |
| "eval_steps_per_second": 1.203, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "eval_accuracy": 0.16435185185185186, | |
| "eval_f1": 0.0724480953675622, | |
| "eval_loss": 2.920067310333252, | |
| "eval_precision": 0.08232943904512993, | |
| "eval_recall": 0.16435185185185186, | |
| "eval_runtime": 5.8821, | |
| "eval_samples_per_second": 73.444, | |
| "eval_steps_per_second": 1.19, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 3.3113, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "eval_accuracy": 0.16435185185185186, | |
| "eval_f1": 0.07315703439667075, | |
| "eval_loss": 2.896663188934326, | |
| "eval_precision": 0.0995273854967043, | |
| "eval_recall": 0.16435185185185186, | |
| "eval_runtime": 5.8475, | |
| "eval_samples_per_second": 73.877, | |
| "eval_steps_per_second": 1.197, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "eval_accuracy": 0.1574074074074074, | |
| "eval_f1": 0.06788189816821627, | |
| "eval_loss": 2.8926467895507812, | |
| "eval_precision": 0.07378815753932359, | |
| "eval_recall": 0.1574074074074074, | |
| "eval_runtime": 6.731, | |
| "eval_samples_per_second": 64.181, | |
| "eval_steps_per_second": 1.04, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 4.444444444444444e-05, | |
| "loss": 3.2872, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "eval_accuracy": 0.1712962962962963, | |
| "eval_f1": 0.07606979068720418, | |
| "eval_loss": 2.8844218254089355, | |
| "eval_precision": 0.0804587704274602, | |
| "eval_recall": 0.1712962962962963, | |
| "eval_runtime": 5.7658, | |
| "eval_samples_per_second": 74.924, | |
| "eval_steps_per_second": 1.214, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.0305, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_accuracy": 0.1712962962962963, | |
| "eval_f1": 0.07456109408196694, | |
| "eval_loss": 2.8605401515960693, | |
| "eval_precision": 0.09364712421465295, | |
| "eval_recall": 0.1712962962962963, | |
| "eval_runtime": 5.8764, | |
| "eval_samples_per_second": 73.515, | |
| "eval_steps_per_second": 1.191, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "eval_accuracy": 0.17592592592592593, | |
| "eval_f1": 0.077154753687655, | |
| "eval_loss": 2.8563218116760254, | |
| "eval_precision": 0.09599160283239885, | |
| "eval_recall": 0.17592592592592593, | |
| "eval_runtime": 5.8036, | |
| "eval_samples_per_second": 74.436, | |
| "eval_steps_per_second": 1.206, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 2.222222222222222e-05, | |
| "loss": 3.2263, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "eval_accuracy": 0.1712962962962963, | |
| "eval_f1": 0.07532319701759846, | |
| "eval_loss": 2.8487489223480225, | |
| "eval_precision": 0.10121344883941782, | |
| "eval_recall": 0.1712962962962963, | |
| "eval_runtime": 5.766, | |
| "eval_samples_per_second": 74.921, | |
| "eval_steps_per_second": 1.214, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "eval_accuracy": 0.1712962962962963, | |
| "eval_f1": 0.07721457778893034, | |
| "eval_loss": 2.8424181938171387, | |
| "eval_precision": 0.12103390482470601, | |
| "eval_recall": 0.1712962962962963, | |
| "eval_runtime": 5.8577, | |
| "eval_samples_per_second": 73.749, | |
| "eval_steps_per_second": 1.195, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 1.111111111111111e-05, | |
| "loss": 3.1927, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "eval_accuracy": 0.1736111111111111, | |
| "eval_f1": 0.07100199262795664, | |
| "eval_loss": 2.837003707885742, | |
| "eval_precision": 0.05610008615248136, | |
| "eval_recall": 0.1736111111111111, | |
| "eval_runtime": 5.7707, | |
| "eval_samples_per_second": 74.861, | |
| "eval_steps_per_second": 1.213, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 0.0, | |
| "loss": 2.992, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "eval_accuracy": 0.18055555555555555, | |
| "eval_f1": 0.08808104613908821, | |
| "eval_loss": 2.849083423614502, | |
| "eval_precision": 0.15482731189307494, | |
| "eval_recall": 0.18055555555555555, | |
| "eval_runtime": 5.8109, | |
| "eval_samples_per_second": 74.343, | |
| "eval_steps_per_second": 1.205, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "step": 120, | |
| "total_flos": 7.312175696361554e+17, | |
| "train_loss": 3.2800607363382976, | |
| "train_runtime": 455.8097, | |
| "train_samples_per_second": 75.821, | |
| "train_steps_per_second": 0.263 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 20, | |
| "total_flos": 7.312175696361554e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |