| { | |
| "best_metric": 0.8418079096045198, | |
| "best_model_checkpoint": "convnextv2-base-22k-224-finetuned-eurosat/checkpoint-396", | |
| "epoch": 2.9962168978562422, | |
| "eval_steps": 500, | |
| "global_step": 594, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.2525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.9977, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9665, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.7126, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 0.728, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.906367041198502e-05, | |
| "loss": 0.7651, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.812734082397004e-05, | |
| "loss": 0.7771, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.719101123595506e-05, | |
| "loss": 0.6614, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.625468164794008e-05, | |
| "loss": 0.6218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.531835205992509e-05, | |
| "loss": 0.6318, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.438202247191011e-05, | |
| "loss": 0.5905, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.344569288389513e-05, | |
| "loss": 0.6299, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.250936329588015e-05, | |
| "loss": 0.6222, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.157303370786517e-05, | |
| "loss": 0.5438, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.063670411985019e-05, | |
| "loss": 0.5207, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.970037453183521e-05, | |
| "loss": 0.5481, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.876404494382023e-05, | |
| "loss": 0.5603, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.782771535580524e-05, | |
| "loss": 0.5909, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7966101694915254, | |
| "eval_loss": 0.5286521315574646, | |
| "eval_runtime": 5.9941, | |
| "eval_samples_per_second": 29.529, | |
| "eval_steps_per_second": 14.848, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.689138576779027e-05, | |
| "loss": 0.3812, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.595505617977528e-05, | |
| "loss": 0.3082, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.5018726591760305e-05, | |
| "loss": 0.3588, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.408239700374532e-05, | |
| "loss": 0.4855, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.314606741573034e-05, | |
| "loss": 0.3966, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.220973782771536e-05, | |
| "loss": 0.2686, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.1273408239700376e-05, | |
| "loss": 0.4901, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.0337078651685396e-05, | |
| "loss": 0.4859, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.940074906367041e-05, | |
| "loss": 0.4439, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.846441947565543e-05, | |
| "loss": 0.3942, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.752808988764045e-05, | |
| "loss": 0.3957, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6591760299625466e-05, | |
| "loss": 0.4238, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.565543071161049e-05, | |
| "loss": 0.4087, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.4719101123595505e-05, | |
| "loss": 0.3913, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3782771535580524e-05, | |
| "loss": 0.301, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.2846441947565544e-05, | |
| "loss": 0.3868, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1910112359550563e-05, | |
| "loss": 0.3086, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0973782771535582e-05, | |
| "loss": 0.3019, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.00374531835206e-05, | |
| "loss": 0.3578, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.9101123595505618e-05, | |
| "loss": 0.2224, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8418079096045198, | |
| "eval_loss": 0.4224812686443329, | |
| "eval_runtime": 6.0015, | |
| "eval_samples_per_second": 29.493, | |
| "eval_steps_per_second": 14.83, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8164794007490637e-05, | |
| "loss": 0.2681, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.7228464419475657e-05, | |
| "loss": 0.2608, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6292134831460676e-05, | |
| "loss": 0.2281, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5355805243445692e-05, | |
| "loss": 0.1541, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4419475655430711e-05, | |
| "loss": 0.4201, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.348314606741573e-05, | |
| "loss": 0.2288, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.254681647940075e-05, | |
| "loss": 0.23, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.161048689138577e-05, | |
| "loss": 0.2587, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0674157303370787e-05, | |
| "loss": 0.0679, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.737827715355806e-06, | |
| "loss": 0.3435, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.801498127340826e-06, | |
| "loss": 0.2798, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.865168539325843e-06, | |
| "loss": 0.2222, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.928838951310862e-06, | |
| "loss": 0.2538, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.9925093632958805e-06, | |
| "loss": 0.2586, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.056179775280899e-06, | |
| "loss": 0.1283, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.1198501872659175e-06, | |
| "loss": 0.349, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.1835205992509364e-06, | |
| "loss": 0.189, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.247191011235955e-06, | |
| "loss": 0.1864, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.310861423220974e-06, | |
| "loss": 0.2067, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.7453183520599253e-07, | |
| "loss": 0.1975, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8418079096045198, | |
| "eval_loss": 0.4207219183444977, | |
| "eval_runtime": 6.0523, | |
| "eval_samples_per_second": 29.245, | |
| "eval_steps_per_second": 14.705, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 594, | |
| "total_flos": 3.76219513152e+17, | |
| "train_loss": 0.4336023674368457, | |
| "train_runtime": 545.8523, | |
| "train_samples_per_second": 8.711, | |
| "train_steps_per_second": 1.088 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 594, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.76219513152e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |