| { | |
| "best_metric": 0.9350796341896057, | |
| "best_model_checkpoint": "marvel_heroes_image_detection/checkpoint-1625", | |
| "epoch": 25.0, | |
| "eval_steps": 500, | |
| "global_step": 1625, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2514506769825919, | |
| "eval_loss": 2.031909227371216, | |
| "eval_runtime": 10.5044, | |
| "eval_samples_per_second": 49.218, | |
| "eval_steps_per_second": 6.188, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.48549323017408125, | |
| "eval_loss": 1.9182429313659668, | |
| "eval_runtime": 10.4516, | |
| "eval_samples_per_second": 49.466, | |
| "eval_steps_per_second": 6.219, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6092843326885881, | |
| "eval_loss": 1.7771351337432861, | |
| "eval_runtime": 10.5159, | |
| "eval_samples_per_second": 49.164, | |
| "eval_steps_per_second": 6.181, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6634429400386848, | |
| "eval_loss": 1.622236967086792, | |
| "eval_runtime": 10.6077, | |
| "eval_samples_per_second": 48.738, | |
| "eval_steps_per_second": 6.128, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6808510638297872, | |
| "eval_loss": 1.4729310274124146, | |
| "eval_runtime": 10.7259, | |
| "eval_samples_per_second": 48.201, | |
| "eval_steps_per_second": 6.06, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6847195357833655, | |
| "eval_loss": 1.3464027643203735, | |
| "eval_runtime": 10.5753, | |
| "eval_samples_per_second": 48.887, | |
| "eval_steps_per_second": 6.146, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7021276595744681, | |
| "eval_loss": 1.2494332790374756, | |
| "eval_runtime": 10.6814, | |
| "eval_samples_per_second": 48.402, | |
| "eval_steps_per_second": 6.085, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 8.59375e-06, | |
| "loss": 1.5805, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7176015473887815, | |
| "eval_loss": 1.1711503267288208, | |
| "eval_runtime": 10.4186, | |
| "eval_samples_per_second": 49.623, | |
| "eval_steps_per_second": 6.239, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.723404255319149, | |
| "eval_loss": 1.1158246994018555, | |
| "eval_runtime": 10.4118, | |
| "eval_samples_per_second": 49.655, | |
| "eval_steps_per_second": 6.243, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.723404255319149, | |
| "eval_loss": 1.0686367750167847, | |
| "eval_runtime": 10.392, | |
| "eval_samples_per_second": 49.75, | |
| "eval_steps_per_second": 6.255, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7137330754352031, | |
| "eval_loss": 1.0390865802764893, | |
| "eval_runtime": 10.4138, | |
| "eval_samples_per_second": 49.646, | |
| "eval_steps_per_second": 6.242, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7156673114119922, | |
| "eval_loss": 1.0162136554718018, | |
| "eval_runtime": 10.4356, | |
| "eval_samples_per_second": 49.542, | |
| "eval_steps_per_second": 6.229, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7156673114119922, | |
| "eval_loss": 0.993504524230957, | |
| "eval_runtime": 10.4092, | |
| "eval_samples_per_second": 49.668, | |
| "eval_steps_per_second": 6.244, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7040618955512572, | |
| "eval_loss": 0.9884597659111023, | |
| "eval_runtime": 10.3867, | |
| "eval_samples_per_second": 49.775, | |
| "eval_steps_per_second": 6.258, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7137330754352031, | |
| "eval_loss": 0.971124529838562, | |
| "eval_runtime": 10.5321, | |
| "eval_samples_per_second": 49.088, | |
| "eval_steps_per_second": 6.172, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 7.031250000000001e-06, | |
| "loss": 0.784, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7156673114119922, | |
| "eval_loss": 0.9606119990348816, | |
| "eval_runtime": 10.3697, | |
| "eval_samples_per_second": 49.857, | |
| "eval_steps_per_second": 6.268, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7137330754352031, | |
| "eval_loss": 0.9606834650039673, | |
| "eval_runtime": 10.3723, | |
| "eval_samples_per_second": 49.844, | |
| "eval_steps_per_second": 6.267, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7195357833655706, | |
| "eval_loss": 0.9507700204849243, | |
| "eval_runtime": 10.5, | |
| "eval_samples_per_second": 49.238, | |
| "eval_steps_per_second": 6.191, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9467002749443054, | |
| "eval_runtime": 10.3715, | |
| "eval_samples_per_second": 49.848, | |
| "eval_steps_per_second": 6.267, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7117988394584139, | |
| "eval_loss": 0.9470967054367065, | |
| "eval_runtime": 10.3883, | |
| "eval_samples_per_second": 49.767, | |
| "eval_steps_per_second": 6.257, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7176015473887815, | |
| "eval_loss": 0.9421167969703674, | |
| "eval_runtime": 10.518, | |
| "eval_samples_per_second": 49.154, | |
| "eval_steps_per_second": 6.18, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7195357833655706, | |
| "eval_loss": 0.9433531761169434, | |
| "eval_runtime": 10.4467, | |
| "eval_samples_per_second": 49.489, | |
| "eval_steps_per_second": 6.222, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7253384912959381, | |
| "eval_loss": 0.9400549530982971, | |
| "eval_runtime": 10.764, | |
| "eval_samples_per_second": 48.031, | |
| "eval_steps_per_second": 6.039, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 5.468750000000001e-06, | |
| "loss": 0.4835, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7137330754352031, | |
| "eval_loss": 0.9435180425643921, | |
| "eval_runtime": 10.4222, | |
| "eval_samples_per_second": 49.606, | |
| "eval_steps_per_second": 6.237, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7330754352030948, | |
| "eval_loss": 0.9350796341896057, | |
| "eval_runtime": 10.8587, | |
| "eval_samples_per_second": 47.612, | |
| "eval_steps_per_second": 5.986, | |
| "step": 1625 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3250, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 4.004613904280371e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |