| { | |
| "best_metric": 0.8535053727979772, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-110", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 6.745112895965576, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.6636, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 20.618379592895508, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5603, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6816720257234726, | |
| "eval_f1": 0.5559040132339913, | |
| "eval_loss": 0.5609580278396606, | |
| "eval_precision": 0.7833316046053315, | |
| "eval_recall": 0.6816720257234726, | |
| "eval_runtime": 114.3233, | |
| "eval_samples_per_second": 2.72, | |
| "eval_steps_per_second": 0.087, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 26.414987564086914, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.4589, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 67.25880432128906, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7909967845659164, | |
| "eval_f1": 0.7768331822733873, | |
| "eval_loss": 0.39760062098503113, | |
| "eval_precision": 0.7878999937662005, | |
| "eval_recall": 0.7909967845659164, | |
| "eval_runtime": 15.7768, | |
| "eval_samples_per_second": 19.713, | |
| "eval_steps_per_second": 0.634, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 27.342533111572266, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.3475, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 20.105819702148438, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.2992, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8070739549839229, | |
| "eval_f1": 0.7964534816572959, | |
| "eval_loss": 0.30361202359199524, | |
| "eval_precision": 0.8044150749918517, | |
| "eval_recall": 0.8070739549839229, | |
| "eval_runtime": 15.7833, | |
| "eval_samples_per_second": 19.704, | |
| "eval_steps_per_second": 0.634, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.1818181818181817, | |
| "grad_norm": 18.851722717285156, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.299, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 11.8802490234375, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.2746, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7877813504823151, | |
| "eval_f1": 0.7799243840827713, | |
| "eval_loss": 0.35377901792526245, | |
| "eval_precision": 0.7811877113589711, | |
| "eval_recall": 0.7877813504823151, | |
| "eval_runtime": 15.7385, | |
| "eval_samples_per_second": 19.76, | |
| "eval_steps_per_second": 0.635, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.090909090909091, | |
| "grad_norm": 28.75580596923828, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.2718, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 20.20217514038086, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.275, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 4.023470878601074, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2573, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8520900321543409, | |
| "eval_f1": 0.8535053727979772, | |
| "eval_loss": 0.22417089343070984, | |
| "eval_precision": 0.8561132846530342, | |
| "eval_recall": 0.8520900321543409, | |
| "eval_runtime": 16.34, | |
| "eval_samples_per_second": 19.033, | |
| "eval_steps_per_second": 0.612, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 10.749618530273438, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.2656, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.909090909090909, | |
| "grad_norm": 18.935693740844727, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.2724, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.77491961414791, | |
| "eval_f1": 0.7347099697338514, | |
| "eval_loss": 0.38007885217666626, | |
| "eval_precision": 0.8145331611697926, | |
| "eval_recall": 0.77491961414791, | |
| "eval_runtime": 17.438, | |
| "eval_samples_per_second": 17.835, | |
| "eval_steps_per_second": 0.573, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 11.04854679107666, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.2445, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.818181818181818, | |
| "grad_norm": 5.090071201324463, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.2344, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8231511254019293, | |
| "eval_f1": 0.801136511467, | |
| "eval_loss": 0.332674115896225, | |
| "eval_precision": 0.8543834389596174, | |
| "eval_recall": 0.8231511254019293, | |
| "eval_runtime": 15.8127, | |
| "eval_samples_per_second": 19.668, | |
| "eval_steps_per_second": 0.632, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 6.6000776290893555, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.241, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.7272727272727275, | |
| "grad_norm": 3.889106035232544, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.2225, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8392282958199357, | |
| "eval_f1": 0.8220529088336219, | |
| "eval_loss": 0.3736245632171631, | |
| "eval_precision": 0.8654598204437431, | |
| "eval_recall": 0.8392282958199357, | |
| "eval_runtime": 15.8357, | |
| "eval_samples_per_second": 19.639, | |
| "eval_steps_per_second": 0.631, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 8.181818181818182, | |
| "grad_norm": 11.122193336486816, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.2323, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.636363636363637, | |
| "grad_norm": 35.049468994140625, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.225, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8327974276527331, | |
| "eval_f1": 0.8137864007121186, | |
| "eval_loss": 0.3479458689689636, | |
| "eval_precision": 0.860997154156041, | |
| "eval_recall": 0.8327974276527331, | |
| "eval_runtime": 16.0275, | |
| "eval_samples_per_second": 19.404, | |
| "eval_steps_per_second": 0.624, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 2.3715155124664307, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.2363, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.545454545454545, | |
| "grad_norm": 4.342611789703369, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2184, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 11.119804382324219, | |
| "learning_rate": 0.0, | |
| "loss": 0.2308, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8327974276527331, | |
| "eval_f1": 0.8137864007121186, | |
| "eval_loss": 0.32772162556648254, | |
| "eval_precision": 0.860997154156041, | |
| "eval_recall": 0.8327974276527331, | |
| "eval_runtime": 17.0105, | |
| "eval_samples_per_second": 18.283, | |
| "eval_steps_per_second": 0.588, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 220, | |
| "total_flos": 6.954705718242509e+17, | |
| "train_loss": 0.305623214895075, | |
| "train_runtime": 2743.5676, | |
| "train_samples_per_second": 10.198, | |
| "train_steps_per_second": 0.08 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 6.954705718242509e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |