| { | |
| "best_metric": 0.8578052550231839, | |
| "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-memes/checkpoint-340", | |
| "epoch": 19.987654320987655, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1655, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6955177743431221, | |
| "eval_f1": 0.6682587615239292, | |
| "eval_loss": 0.8572999835014343, | |
| "eval_precision": 0.6952978724784165, | |
| "eval_recall": 0.6955177743431221, | |
| "eval_runtime": 14.2645, | |
| "eval_samples_per_second": 90.715, | |
| "eval_steps_per_second": 1.472, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9e-05, | |
| "loss": 0.7275, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5506, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.8083462132921174, | |
| "eval_f1": 0.7962870636686081, | |
| "eval_loss": 0.5326675176620483, | |
| "eval_precision": 0.8049703591765521, | |
| "eval_recall": 0.8083462132921174, | |
| "eval_runtime": 12.6486, | |
| "eval_samples_per_second": 102.304, | |
| "eval_steps_per_second": 1.66, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 0.3788, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00011333333333333333, | |
| "loss": 0.3573, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8338485316846986, | |
| "eval_f1": 0.831666163408815, | |
| "eval_loss": 0.4496992528438568, | |
| "eval_precision": 0.8339121233593048, | |
| "eval_recall": 0.8338485316846986, | |
| "eval_runtime": 12.8713, | |
| "eval_samples_per_second": 100.534, | |
| "eval_steps_per_second": 1.632, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00011, | |
| "loss": 0.2378, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 0.2083, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.8353941267387944, | |
| "eval_f1": 0.8368249403721092, | |
| "eval_loss": 0.45606011152267456, | |
| "eval_precision": 0.84498910302744, | |
| "eval_recall": 0.8353941267387944, | |
| "eval_runtime": 12.8489, | |
| "eval_samples_per_second": 100.709, | |
| "eval_steps_per_second": 1.634, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00010333333333333334, | |
| "loss": 0.1314, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1545, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8423493044822257, | |
| "eval_f1": 0.8429773996176875, | |
| "eval_loss": 0.4605261981487274, | |
| "eval_precision": 0.8457880236763888, | |
| "eval_recall": 0.8423493044822257, | |
| "eval_runtime": 13.8028, | |
| "eval_samples_per_second": 93.749, | |
| "eval_steps_per_second": 1.521, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 0.124, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.1014, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.8523956723338485, | |
| "eval_f1": 0.8538473676550408, | |
| "eval_loss": 0.4924044609069824, | |
| "eval_precision": 0.8570555975028126, | |
| "eval_recall": 0.8523956723338485, | |
| "eval_runtime": 13.153, | |
| "eval_samples_per_second": 98.381, | |
| "eval_steps_per_second": 1.597, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0886, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.0854, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.839258114374034, | |
| "eval_f1": 0.8399595295849303, | |
| "eval_loss": 0.575903594493866, | |
| "eval_precision": 0.8452221761378239, | |
| "eval_recall": 0.839258114374034, | |
| "eval_runtime": 12.9566, | |
| "eval_samples_per_second": 99.872, | |
| "eval_steps_per_second": 1.621, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 0.0804, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 7.999999999999999e-05, | |
| "loss": 0.1012, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.8361669242658424, | |
| "eval_f1": 0.8361306593636055, | |
| "eval_loss": 0.5141878724098206, | |
| "eval_precision": 0.8378496563621973, | |
| "eval_recall": 0.8361669242658424, | |
| "eval_runtime": 12.9916, | |
| "eval_samples_per_second": 99.602, | |
| "eval_steps_per_second": 1.616, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 0.0745, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 7.333333333333334e-05, | |
| "loss": 0.077, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8330757341576507, | |
| "eval_f1": 0.8406946514001388, | |
| "eval_loss": 0.5646628141403198, | |
| "eval_precision": 0.8537522286474765, | |
| "eval_recall": 0.8330757341576507, | |
| "eval_runtime": 13.9321, | |
| "eval_samples_per_second": 92.879, | |
| "eval_steps_per_second": 1.507, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 7.000000000000001e-05, | |
| "loss": 0.0587, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0667, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.8462132921174652, | |
| "eval_f1": 0.8482978184490837, | |
| "eval_loss": 0.5293765068054199, | |
| "eval_precision": 0.8508576163797781, | |
| "eval_recall": 0.8462132921174652, | |
| "eval_runtime": 13.4474, | |
| "eval_samples_per_second": 96.227, | |
| "eval_steps_per_second": 1.562, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 0.0452, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0666, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.8384853168469861, | |
| "eval_f1": 0.839606513626033, | |
| "eval_loss": 0.6037518382072449, | |
| "eval_precision": 0.84149883116413, | |
| "eval_recall": 0.8384853168469861, | |
| "eval_runtime": 12.7726, | |
| "eval_samples_per_second": 101.311, | |
| "eval_steps_per_second": 1.644, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.6666666666666664e-05, | |
| "loss": 0.0577, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.0574, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_accuracy": 0.8408037094281299, | |
| "eval_f1": 0.8411127335807149, | |
| "eval_loss": 0.6383613348007202, | |
| "eval_precision": 0.8431342855971845, | |
| "eval_recall": 0.8408037094281299, | |
| "eval_runtime": 13.1432, | |
| "eval_samples_per_second": 98.454, | |
| "eval_steps_per_second": 1.598, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0509, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0488, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8516228748068007, | |
| "eval_f1": 0.8532381219142173, | |
| "eval_loss": 0.6304579973220825, | |
| "eval_precision": 0.8561226939263563, | |
| "eval_recall": 0.8516228748068007, | |
| "eval_runtime": 13.6608, | |
| "eval_samples_per_second": 94.723, | |
| "eval_steps_per_second": 1.537, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.0517, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 3.9999999999999996e-05, | |
| "loss": 0.0524, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_accuracy": 0.8508500772797527, | |
| "eval_f1": 0.8510093409043722, | |
| "eval_loss": 0.6410980224609375, | |
| "eval_precision": 0.8526221088238606, | |
| "eval_recall": 0.8508500772797527, | |
| "eval_runtime": 12.8216, | |
| "eval_samples_per_second": 100.923, | |
| "eval_steps_per_second": 1.638, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 3.666666666666667e-05, | |
| "loss": 0.0377, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0511, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8547140649149922, | |
| "eval_f1": 0.8543059086099318, | |
| "eval_loss": 0.6461631655693054, | |
| "eval_precision": 0.8541819570387084, | |
| "eval_recall": 0.8547140649149922, | |
| "eval_runtime": 14.3489, | |
| "eval_samples_per_second": 90.181, | |
| "eval_steps_per_second": 1.464, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0446, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0495, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_accuracy": 0.8531684698608965, | |
| "eval_f1": 0.8527356330319577, | |
| "eval_loss": 0.6869231462478638, | |
| "eval_precision": 0.8533821751799587, | |
| "eval_recall": 0.8531684698608965, | |
| "eval_runtime": 12.6457, | |
| "eval_samples_per_second": 102.327, | |
| "eval_steps_per_second": 1.661, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0489, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.0412, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8578052550231839, | |
| "eval_f1": 0.8563934506342421, | |
| "eval_loss": 0.6643078327178955, | |
| "eval_precision": 0.8553636638149845, | |
| "eval_recall": 0.8578052550231839, | |
| "eval_runtime": 13.1315, | |
| "eval_samples_per_second": 98.542, | |
| "eval_steps_per_second": 1.599, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 17.49, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0447, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0411, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_accuracy": 0.857032457496136, | |
| "eval_f1": 0.8552106741098364, | |
| "eval_loss": 0.7213734984397888, | |
| "eval_precision": 0.8538988900347119, | |
| "eval_recall": 0.857032457496136, | |
| "eval_runtime": 12.729, | |
| "eval_samples_per_second": 101.658, | |
| "eval_steps_per_second": 1.65, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.0411, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0434, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8523956723338485, | |
| "eval_f1": 0.8514088692604659, | |
| "eval_loss": 0.7037173509597778, | |
| "eval_precision": 0.850651377920994, | |
| "eval_recall": 0.8523956723338485, | |
| "eval_runtime": 13.5738, | |
| "eval_samples_per_second": 95.331, | |
| "eval_steps_per_second": 1.547, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0445, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.0394, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "eval_accuracy": 0.8562596599690881, | |
| "eval_f1": 0.8552274649509984, | |
| "eval_loss": 0.7093907594680786, | |
| "eval_precision": 0.8545652818321074, | |
| "eval_recall": 0.8562596599690881, | |
| "eval_runtime": 12.9239, | |
| "eval_samples_per_second": 100.124, | |
| "eval_steps_per_second": 1.625, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "step": 400, | |
| "total_flos": 8.103254675374559e+18, | |
| "train_loss": 0.18201538026332856, | |
| "train_runtime": 1691.2716, | |
| "train_samples_per_second": 61.185, | |
| "train_steps_per_second": 0.237 | |
| } | |
| ], | |
| "max_steps": 400, | |
| "num_train_epochs": 20, | |
| "total_flos": 8.103254675374559e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |