| { | |
| "best_metric": 0.8922222222222222, | |
| "best_model_checkpoint": "mobilevit-xx-small-finetuned-eurosat/checkpoint-570", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 2.499504327774048, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 1.6238, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 3.030421018600464, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 1.6049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 2.953359365463257, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.5841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.1098451614379883, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.5514, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 3.6047229766845703, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 1.521, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 2.3976938724517822, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 1.4668, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 5.425637245178223, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 1.406, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 3.227510452270508, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 1.4218, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 2.7980666160583496, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 1.3878, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 2.8665292263031006, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 1.3493, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 2.128242015838623, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 1.2967, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 3.452329635620117, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 1.301, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 2.992901563644409, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 1.2565, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 4.7219343185424805, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 1.2084, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 5.003918170928955, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 1.1951, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 3.202345371246338, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 1.1977, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 4.2679243087768555, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 1.191, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 4.404182434082031, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 1.1389, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.484068870544434, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.1283, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8355555555555556, | |
| "eval_loss": 0.8987089395523071, | |
| "eval_runtime": 641.465, | |
| "eval_samples_per_second": 4.209, | |
| "eval_steps_per_second": 0.133, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 6.229562759399414, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 1.0966, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 3.731093645095825, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.0866, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 5.640038013458252, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 1.0759, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 3.6837992668151855, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 1.074, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 7.346179008483887, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 1.0639, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 6.602072238922119, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 1.0198, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 4.163863658905029, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.9974, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 5.383280277252197, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.9492, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 4.670665740966797, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.9776, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 5.218229293823242, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 1.0044, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 3.5674266815185547, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.9821, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 8.3242769241333, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.9502, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 4.583398342132568, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.9619, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 5.249886989593506, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.9912, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 3.927725076675415, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.9223, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 8.165482521057129, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.9174, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 3.3622968196868896, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.911, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 6.024033069610596, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.9137, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.1243367195129395, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.902, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8851851851851852, | |
| "eval_loss": 0.6551592946052551, | |
| "eval_runtime": 642.4494, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.132, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 4.805797576904297, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.8861, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 5.6864423751831055, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.8756, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 8.343716621398926, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.8962, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 5.397374629974365, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.8812, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 4.699794769287109, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.8698, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 5.595669269561768, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.924, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 8.696515083312988, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.8899, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 3.1540162563323975, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.8461, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 8.347066879272461, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.8491, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 3.625857353210449, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.8682, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 7.956964492797852, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.8541, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 5.349480628967285, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.8264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 10.98034381866455, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.8413, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 7.160295486450195, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.8387, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 5.040878772735596, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.848, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 3.559468984603882, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.8328, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 5.02614164352417, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.8512, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 3.587019443511963, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.823, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.714681148529053, | |
| "learning_rate": 0.0, | |
| "loss": 0.8583, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8922222222222222, | |
| "eval_loss": 0.5839348435401917, | |
| "eval_runtime": 650.1881, | |
| "eval_samples_per_second": 4.153, | |
| "eval_steps_per_second": 0.131, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 1.038579857805312e+17, | |
| "train_loss": 1.069958934449313, | |
| "train_runtime": 19530.3177, | |
| "train_samples_per_second": 3.733, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 570, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.038579857805312e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |