| { | |
| "best_metric": 1.3654530048370361, | |
| "best_model_checkpoint": "75_butterfly_types_image_detection/checkpoint-6150", | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 6150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.10483460559796437, | |
| "eval_loss": 4.219280242919922, | |
| "eval_runtime": 16.1158, | |
| "eval_samples_per_second": 121.93, | |
| "eval_steps_per_second": 3.847, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.416793893129771, | |
| "eval_loss": 4.0515265464782715, | |
| "eval_runtime": 16.031, | |
| "eval_samples_per_second": 122.575, | |
| "eval_steps_per_second": 3.868, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6743002544529262, | |
| "eval_loss": 3.868370532989502, | |
| "eval_runtime": 16.1588, | |
| "eval_samples_per_second": 121.605, | |
| "eval_steps_per_second": 3.837, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7791348600508906, | |
| "eval_loss": 3.682469129562378, | |
| "eval_runtime": 16.1954, | |
| "eval_samples_per_second": 121.331, | |
| "eval_steps_per_second": 3.828, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 4.631147540983607e-06, | |
| "loss": 4.0027, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8213740458015267, | |
| "eval_loss": 3.506803035736084, | |
| "eval_runtime": 16.0347, | |
| "eval_samples_per_second": 122.546, | |
| "eval_steps_per_second": 3.867, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8396946564885496, | |
| "eval_loss": 3.344095468521118, | |
| "eval_runtime": 16.3499, | |
| "eval_samples_per_second": 120.184, | |
| "eval_steps_per_second": 3.792, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8569974554707379, | |
| "eval_loss": 3.1964809894561768, | |
| "eval_runtime": 16.1751, | |
| "eval_samples_per_second": 121.483, | |
| "eval_steps_per_second": 3.833, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8661577608142493, | |
| "eval_loss": 3.0642857551574707, | |
| "eval_runtime": 16.1962, | |
| "eval_samples_per_second": 121.325, | |
| "eval_steps_per_second": 3.828, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 4.221311475409837e-06, | |
| "loss": 3.2743, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8743002544529263, | |
| "eval_loss": 2.9428579807281494, | |
| "eval_runtime": 16.3097, | |
| "eval_samples_per_second": 120.48, | |
| "eval_steps_per_second": 3.801, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8844783715012723, | |
| "eval_loss": 2.832017183303833, | |
| "eval_runtime": 16.1405, | |
| "eval_samples_per_second": 121.743, | |
| "eval_steps_per_second": 3.841, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8875318066157761, | |
| "eval_loss": 2.7307262420654297, | |
| "eval_runtime": 16.6796, | |
| "eval_samples_per_second": 117.808, | |
| "eval_steps_per_second": 3.717, | |
| "step": 1353 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8941475826972011, | |
| "eval_loss": 2.635011911392212, | |
| "eval_runtime": 16.1864, | |
| "eval_samples_per_second": 121.398, | |
| "eval_steps_per_second": 3.83, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 3.811475409836066e-06, | |
| "loss": 2.7379, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9012722646310433, | |
| "eval_loss": 2.54408597946167, | |
| "eval_runtime": 16.1725, | |
| "eval_samples_per_second": 121.503, | |
| "eval_steps_per_second": 3.834, | |
| "step": 1599 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9038167938931297, | |
| "eval_loss": 2.461076259613037, | |
| "eval_runtime": 16.188, | |
| "eval_samples_per_second": 121.386, | |
| "eval_steps_per_second": 3.83, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.905852417302799, | |
| "eval_loss": 2.3826189041137695, | |
| "eval_runtime": 16.0942, | |
| "eval_samples_per_second": 122.094, | |
| "eval_steps_per_second": 3.852, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9104325699745547, | |
| "eval_loss": 2.3125312328338623, | |
| "eval_runtime": 16.0801, | |
| "eval_samples_per_second": 122.201, | |
| "eval_steps_per_second": 3.856, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 3.4016393442622954e-06, | |
| "loss": 2.3551, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9150127226463104, | |
| "eval_loss": 2.2421457767486572, | |
| "eval_runtime": 16.1647, | |
| "eval_samples_per_second": 121.561, | |
| "eval_steps_per_second": 3.836, | |
| "step": 2091 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9180661577608142, | |
| "eval_loss": 2.177084445953369, | |
| "eval_runtime": 16.1219, | |
| "eval_samples_per_second": 121.884, | |
| "eval_steps_per_second": 3.846, | |
| "step": 2214 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9185750636132316, | |
| "eval_loss": 2.118427038192749, | |
| "eval_runtime": 16.2975, | |
| "eval_samples_per_second": 120.571, | |
| "eval_steps_per_second": 3.804, | |
| "step": 2337 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9206106870229007, | |
| "eval_loss": 2.0600903034210205, | |
| "eval_runtime": 16.1374, | |
| "eval_samples_per_second": 121.767, | |
| "eval_steps_per_second": 3.842, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 2.991803278688525e-06, | |
| "loss": 2.0646, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9231552162849873, | |
| "eval_loss": 2.0077874660491943, | |
| "eval_runtime": 16.1894, | |
| "eval_samples_per_second": 121.376, | |
| "eval_steps_per_second": 3.83, | |
| "step": 2583 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9246819338422392, | |
| "eval_loss": 1.9560858011245728, | |
| "eval_runtime": 16.2039, | |
| "eval_samples_per_second": 121.267, | |
| "eval_steps_per_second": 3.826, | |
| "step": 2706 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9246819338422392, | |
| "eval_loss": 1.9086360931396484, | |
| "eval_runtime": 16.1264, | |
| "eval_samples_per_second": 121.85, | |
| "eval_steps_per_second": 3.845, | |
| "step": 2829 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9272264631043257, | |
| "eval_loss": 1.8643087148666382, | |
| "eval_runtime": 16.2238, | |
| "eval_samples_per_second": 121.118, | |
| "eval_steps_per_second": 3.822, | |
| "step": 2952 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 2.5819672131147543e-06, | |
| "loss": 1.8362, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9292620865139949, | |
| "eval_loss": 1.8223220109939575, | |
| "eval_runtime": 16.1769, | |
| "eval_samples_per_second": 121.47, | |
| "eval_steps_per_second": 3.833, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9323155216284987, | |
| "eval_loss": 1.781746745109558, | |
| "eval_runtime": 16.1733, | |
| "eval_samples_per_second": 121.496, | |
| "eval_steps_per_second": 3.833, | |
| "step": 3198 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.932824427480916, | |
| "eval_loss": 1.7436439990997314, | |
| "eval_runtime": 16.25, | |
| "eval_samples_per_second": 120.923, | |
| "eval_steps_per_second": 3.815, | |
| "step": 3321 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 1.7096657752990723, | |
| "eval_runtime": 16.2645, | |
| "eval_samples_per_second": 120.815, | |
| "eval_steps_per_second": 3.812, | |
| "step": 3444 | |
| }, | |
| { | |
| "epoch": 28.46, | |
| "learning_rate": 2.1721311475409838e-06, | |
| "loss": 1.6594, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.934351145038168, | |
| "eval_loss": 1.6767544746398926, | |
| "eval_runtime": 16.0446, | |
| "eval_samples_per_second": 122.471, | |
| "eval_steps_per_second": 3.864, | |
| "step": 3567 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9363867684478372, | |
| "eval_loss": 1.6452341079711914, | |
| "eval_runtime": 16.2929, | |
| "eval_samples_per_second": 120.605, | |
| "eval_steps_per_second": 3.805, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9368956743002544, | |
| "eval_loss": 1.6171735525131226, | |
| "eval_runtime": 16.1612, | |
| "eval_samples_per_second": 121.587, | |
| "eval_steps_per_second": 3.836, | |
| "step": 3813 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9394402035623409, | |
| "eval_loss": 1.5884838104248047, | |
| "eval_runtime": 16.0285, | |
| "eval_samples_per_second": 122.594, | |
| "eval_steps_per_second": 3.868, | |
| "step": 3936 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 1.7622950819672133e-06, | |
| "loss": 1.5202, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9399491094147583, | |
| "eval_loss": 1.5642931461334229, | |
| "eval_runtime": 16.0014, | |
| "eval_samples_per_second": 122.801, | |
| "eval_steps_per_second": 3.875, | |
| "step": 4059 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9379134860050891, | |
| "eval_loss": 1.5411930084228516, | |
| "eval_runtime": 16.0783, | |
| "eval_samples_per_second": 122.214, | |
| "eval_steps_per_second": 3.856, | |
| "step": 4182 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9409669211195929, | |
| "eval_loss": 1.518629789352417, | |
| "eval_runtime": 16.0126, | |
| "eval_samples_per_second": 122.716, | |
| "eval_steps_per_second": 3.872, | |
| "step": 4305 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9419847328244275, | |
| "eval_loss": 1.4979873895645142, | |
| "eval_runtime": 16.1815, | |
| "eval_samples_per_second": 121.435, | |
| "eval_steps_per_second": 3.832, | |
| "step": 4428 | |
| }, | |
| { | |
| "epoch": 36.59, | |
| "learning_rate": 1.352459016393443e-06, | |
| "loss": 1.4134, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9424936386768448, | |
| "eval_loss": 1.4799128770828247, | |
| "eval_runtime": 16.1592, | |
| "eval_samples_per_second": 121.603, | |
| "eval_steps_per_second": 3.837, | |
| "step": 4551 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.944529262086514, | |
| "eval_loss": 1.462226390838623, | |
| "eval_runtime": 16.17, | |
| "eval_samples_per_second": 121.522, | |
| "eval_steps_per_second": 3.834, | |
| "step": 4674 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9435114503816794, | |
| "eval_loss": 1.4462333917617798, | |
| "eval_runtime": 16.3661, | |
| "eval_samples_per_second": 120.065, | |
| "eval_steps_per_second": 3.788, | |
| "step": 4797 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9435114503816794, | |
| "eval_loss": 1.432714581489563, | |
| "eval_runtime": 16.2167, | |
| "eval_samples_per_second": 121.171, | |
| "eval_steps_per_second": 3.823, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "learning_rate": 9.426229508196721e-07, | |
| "loss": 1.3371, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.9435114503816794, | |
| "eval_loss": 1.4191633462905884, | |
| "eval_runtime": 16.352, | |
| "eval_samples_per_second": 120.169, | |
| "eval_steps_per_second": 3.792, | |
| "step": 5043 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.944529262086514, | |
| "eval_loss": 1.4076900482177734, | |
| "eval_runtime": 16.453, | |
| "eval_samples_per_second": 119.431, | |
| "eval_steps_per_second": 3.768, | |
| "step": 5166 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.9450381679389313, | |
| "eval_loss": 1.3978630304336548, | |
| "eval_runtime": 16.2004, | |
| "eval_samples_per_second": 121.293, | |
| "eval_steps_per_second": 3.827, | |
| "step": 5289 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.3894777297973633, | |
| "eval_runtime": 16.3005, | |
| "eval_samples_per_second": 120.549, | |
| "eval_steps_per_second": 3.804, | |
| "step": 5412 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 5.327868852459017e-07, | |
| "loss": 1.2847, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.3816895484924316, | |
| "eval_runtime": 16.1887, | |
| "eval_samples_per_second": 121.381, | |
| "eval_steps_per_second": 3.83, | |
| "step": 5535 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.376446008682251, | |
| "eval_runtime": 16.3897, | |
| "eval_samples_per_second": 119.893, | |
| "eval_steps_per_second": 3.783, | |
| "step": 5658 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.3714139461517334, | |
| "eval_runtime": 16.2429, | |
| "eval_samples_per_second": 120.976, | |
| "eval_steps_per_second": 3.817, | |
| "step": 5781 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.3681418895721436, | |
| "eval_runtime": 16.2361, | |
| "eval_samples_per_second": 121.027, | |
| "eval_steps_per_second": 3.819, | |
| "step": 5904 | |
| }, | |
| { | |
| "epoch": 48.78, | |
| "learning_rate": 1.2295081967213116e-07, | |
| "loss": 1.2536, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.3659467697143555, | |
| "eval_runtime": 16.2019, | |
| "eval_samples_per_second": 121.282, | |
| "eval_steps_per_second": 3.827, | |
| "step": 6027 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.9455470737913486, | |
| "eval_loss": 1.3654530048370361, | |
| "eval_runtime": 16.2047, | |
| "eval_samples_per_second": 121.261, | |
| "eval_steps_per_second": 3.826, | |
| "step": 6150 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6150, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 3.0474277467346944e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |