| { | |
| "best_metric": 0.6452859350850078, | |
| "best_model_checkpoint": "resnet-50-FV2-finetuned-memes/checkpoint-400", | |
| "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": 1.5967, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5763, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.4281298299845441, | |
| "eval_f1": 0.26687554630409566, | |
| "eval_loss": 1.5574817657470703, | |
| "eval_precision": 0.29655663588874154, | |
| "eval_recall": 0.4281298299845441, | |
| "eval_runtime": 11.3953, | |
| "eval_samples_per_second": 113.556, | |
| "eval_steps_per_second": 1.843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9e-05, | |
| "loss": 1.5775, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.43431221020092736, | |
| "eval_f1": 0.2630209721259926, | |
| "eval_loss": 1.4423725605010986, | |
| "eval_precision": 0.18862709592961452, | |
| "eval_recall": 0.43431221020092736, | |
| "eval_runtime": 10.1591, | |
| "eval_samples_per_second": 127.373, | |
| "eval_steps_per_second": 2.067, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 1.444, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00011333333333333333, | |
| "loss": 1.3563, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.43431221020092736, | |
| "eval_f1": 0.2630209721259926, | |
| "eval_loss": 1.3240060806274414, | |
| "eval_precision": 0.18862709592961452, | |
| "eval_recall": 0.43431221020092736, | |
| "eval_runtime": 10.039, | |
| "eval_samples_per_second": 128.897, | |
| "eval_steps_per_second": 2.092, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00011, | |
| "loss": 1.3356, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 1.2824, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.43894899536321486, | |
| "eval_f1": 0.27337332937410136, | |
| "eval_loss": 1.263592004776001, | |
| "eval_precision": 0.3097252114961456, | |
| "eval_recall": 0.43894899536321486, | |
| "eval_runtime": 10.0514, | |
| "eval_samples_per_second": 128.739, | |
| "eval_steps_per_second": 2.089, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00010333333333333334, | |
| "loss": 1.2695, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2315, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.4528593508500773, | |
| "eval_f1": 0.30415713999389604, | |
| "eval_loss": 1.2118711471557617, | |
| "eval_precision": 0.3235903479528001, | |
| "eval_recall": 0.4528593508500773, | |
| "eval_runtime": 10.1242, | |
| "eval_samples_per_second": 127.813, | |
| "eval_steps_per_second": 2.074, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 1.2096, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 1.1956, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.4899536321483771, | |
| "eval_f1": 0.3692247614974613, | |
| "eval_loss": 1.1763864755630493, | |
| "eval_precision": 0.3730719437429542, | |
| "eval_recall": 0.4899536321483771, | |
| "eval_runtime": 10.0285, | |
| "eval_samples_per_second": 129.033, | |
| "eval_steps_per_second": 2.094, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 9e-05, | |
| "loss": 1.1727, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 1.1452, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.5146831530139103, | |
| "eval_f1": 0.4090229013083186, | |
| "eval_loss": 1.1424295902252197, | |
| "eval_precision": 0.396316505367188, | |
| "eval_recall": 0.5146831530139103, | |
| "eval_runtime": 11.1, | |
| "eval_samples_per_second": 116.577, | |
| "eval_steps_per_second": 1.892, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 1.1455, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 7.999999999999999e-05, | |
| "loss": 1.1076, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.5370942812982998, | |
| "eval_f1": 0.4392356918841944, | |
| "eval_loss": 1.1189799308776855, | |
| "eval_precision": 0.41207140655215574, | |
| "eval_recall": 0.5370942812982998, | |
| "eval_runtime": 10.2542, | |
| "eval_samples_per_second": 126.192, | |
| "eval_steps_per_second": 2.048, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 1.1204, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 7.333333333333334e-05, | |
| "loss": 1.0679, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.5718701700154559, | |
| "eval_f1": 0.48309150932194556, | |
| "eval_loss": 1.0824542045593262, | |
| "eval_precision": 0.44653696889067535, | |
| "eval_recall": 0.5718701700154559, | |
| "eval_runtime": 10.0099, | |
| "eval_samples_per_second": 129.272, | |
| "eval_steps_per_second": 2.098, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 7.000000000000001e-05, | |
| "loss": 1.0551, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.0432, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.5749613601236476, | |
| "eval_f1": 0.4930062944584295, | |
| "eval_loss": 1.0481715202331543, | |
| "eval_precision": 0.5404301068833355, | |
| "eval_recall": 0.5749613601236476, | |
| "eval_runtime": 19.2474, | |
| "eval_samples_per_second": 67.23, | |
| "eval_steps_per_second": 1.091, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 1.0465, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9903, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.5958268933539412, | |
| "eval_f1": 0.5240773887363929, | |
| "eval_loss": 1.0275342464447021, | |
| "eval_precision": 0.545875829974407, | |
| "eval_recall": 0.5958268933539412, | |
| "eval_runtime": 9.9464, | |
| "eval_samples_per_second": 130.097, | |
| "eval_steps_per_second": 2.111, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.6666666666666664e-05, | |
| "loss": 1.0046, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.9675, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_accuracy": 0.6051004636785162, | |
| "eval_f1": 0.5379053813016494, | |
| "eval_loss": 1.0145165920257568, | |
| "eval_precision": 0.5349771722020813, | |
| "eval_recall": 0.6051004636785162, | |
| "eval_runtime": 10.1612, | |
| "eval_samples_per_second": 127.347, | |
| "eval_steps_per_second": 2.067, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 5e-05, | |
| "loss": 0.997, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.9335, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.6174652241112828, | |
| "eval_f1": 0.552720253591733, | |
| "eval_loss": 0.9859771728515625, | |
| "eval_precision": 0.5536990181229813, | |
| "eval_recall": 0.6174652241112828, | |
| "eval_runtime": 11.4078, | |
| "eval_samples_per_second": 113.431, | |
| "eval_steps_per_second": 1.841, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.9501, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 3.9999999999999996e-05, | |
| "loss": 0.9157, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_accuracy": 0.6105100463678517, | |
| "eval_f1": 0.5504384069346341, | |
| "eval_loss": 0.9683175683021545, | |
| "eval_precision": 0.5386397521561105, | |
| "eval_recall": 0.6105100463678517, | |
| "eval_runtime": 10.0837, | |
| "eval_samples_per_second": 128.326, | |
| "eval_steps_per_second": 2.083, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 3.666666666666667e-05, | |
| "loss": 0.9324, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8901, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.6352395672333848, | |
| "eval_f1": 0.5833124251549139, | |
| "eval_loss": 0.95584636926651, | |
| "eval_precision": 0.5686172096380677, | |
| "eval_recall": 0.6352395672333848, | |
| "eval_runtime": 11.1778, | |
| "eval_samples_per_second": 115.766, | |
| "eval_steps_per_second": 1.879, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9157, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.8722, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_accuracy": 0.634466769706337, | |
| "eval_f1": 0.5807225066585998, | |
| "eval_loss": 0.9381548762321472, | |
| "eval_precision": 0.5656504472537988, | |
| "eval_recall": 0.634466769706337, | |
| "eval_runtime": 10.0783, | |
| "eval_samples_per_second": 128.395, | |
| "eval_steps_per_second": 2.084, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.9132, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.854, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.6375579598145286, | |
| "eval_f1": 0.5855599844273062, | |
| "eval_loss": 0.9322208166122437, | |
| "eval_precision": 0.5622591012744048, | |
| "eval_recall": 0.6375579598145286, | |
| "eval_runtime": 10.1911, | |
| "eval_samples_per_second": 126.973, | |
| "eval_steps_per_second": 2.061, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 17.49, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.8979, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.8494, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_accuracy": 0.6421947449768161, | |
| "eval_f1": 0.5918308732628852, | |
| "eval_loss": 0.9286540746688843, | |
| "eval_precision": 0.6675486262621129, | |
| "eval_recall": 0.6421947449768161, | |
| "eval_runtime": 11.41, | |
| "eval_samples_per_second": 113.409, | |
| "eval_steps_per_second": 1.84, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.8649, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.8652, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.6398763523956723, | |
| "eval_f1": 0.586308244884445, | |
| "eval_loss": 0.9211938977241516, | |
| "eval_precision": 0.5640414016020209, | |
| "eval_recall": 0.6398763523956723, | |
| "eval_runtime": 10.0413, | |
| "eval_samples_per_second": 128.867, | |
| "eval_steps_per_second": 2.091, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.8826, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.846, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "eval_accuracy": 0.6452859350850078, | |
| "eval_f1": 0.5963647629954705, | |
| "eval_loss": 0.9262650012969971, | |
| "eval_precision": 0.5727919568038408, | |
| "eval_recall": 0.6452859350850078, | |
| "eval_runtime": 10.2246, | |
| "eval_samples_per_second": 126.557, | |
| "eval_steps_per_second": 2.054, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "step": 400, | |
| "total_flos": 2.1968670326740623e+18, | |
| "train_loss": 1.0949385786056518, | |
| "train_runtime": 1181.8167, | |
| "train_samples_per_second": 87.56, | |
| "train_steps_per_second": 0.338 | |
| } | |
| ], | |
| "max_steps": 400, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.1968670326740623e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |