| { | |
| "best_metric": 0.8624420401854714, | |
| "best_model_checkpoint": "swin-large-patch4-window7-224-fv-finetuned-memes/checkpoint-260", | |
| "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": 1.5175, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6460587326120556, | |
| "eval_f1": 0.5863413021916006, | |
| "eval_loss": 0.9499021172523499, | |
| "eval_precision": 0.6764367410152282, | |
| "eval_recall": 0.6460587326120556, | |
| "eval_runtime": 17.0101, | |
| "eval_samples_per_second": 76.072, | |
| "eval_steps_per_second": 1.235, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9e-05, | |
| "loss": 0.7692, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.7975270479134466, | |
| "eval_f1": 0.7923565752290783, | |
| "eval_loss": 0.5365163683891296, | |
| "eval_precision": 0.8017503324599011, | |
| "eval_recall": 0.7975270479134466, | |
| "eval_runtime": 15.9305, | |
| "eval_samples_per_second": 81.228, | |
| "eval_steps_per_second": 1.318, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 0.3964, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00011333333333333333, | |
| "loss": 0.3607, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8423493044822257, | |
| "eval_f1": 0.8398382940431993, | |
| "eval_loss": 0.4007461667060852, | |
| "eval_precision": 0.8418683077586698, | |
| "eval_recall": 0.8423493044822257, | |
| "eval_runtime": 15.8706, | |
| "eval_samples_per_second": 81.535, | |
| "eval_steps_per_second": 1.323, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00011, | |
| "loss": 0.2239, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 0.203, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.8508500772797527, | |
| "eval_f1": 0.8502738747597961, | |
| "eval_loss": 0.37511739134788513, | |
| "eval_precision": 0.8502306265074059, | |
| "eval_recall": 0.8508500772797527, | |
| "eval_runtime": 17.1672, | |
| "eval_samples_per_second": 75.376, | |
| "eval_steps_per_second": 1.223, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00010333333333333334, | |
| "loss": 0.1377, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1728, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8508500772797527, | |
| "eval_f1": 0.8505730549098866, | |
| "eval_loss": 0.4167707860469818, | |
| "eval_precision": 0.8519036175397052, | |
| "eval_recall": 0.8508500772797527, | |
| "eval_runtime": 16.0386, | |
| "eval_samples_per_second": 80.68, | |
| "eval_steps_per_second": 1.309, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 0.1128, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.0963, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.8585780525502318, | |
| "eval_f1": 0.855520229593311, | |
| "eval_loss": 0.4350760877132416, | |
| "eval_precision": 0.8573159999281582, | |
| "eval_recall": 0.8585780525502318, | |
| "eval_runtime": 16.0034, | |
| "eval_samples_per_second": 80.858, | |
| "eval_steps_per_second": 1.312, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0765, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.0956, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8547140649149922, | |
| "eval_f1": 0.8540764389875939, | |
| "eval_loss": 0.4415300190448761, | |
| "eval_precision": 0.854205518900449, | |
| "eval_recall": 0.8547140649149922, | |
| "eval_runtime": 17.3001, | |
| "eval_samples_per_second": 74.797, | |
| "eval_steps_per_second": 1.214, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 0.0756, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 7.999999999999999e-05, | |
| "loss": 0.079, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.8500772797527048, | |
| "eval_f1": 0.8459002125960169, | |
| "eval_loss": 0.531154990196228, | |
| "eval_precision": 0.8474790934072687, | |
| "eval_recall": 0.8500772797527048, | |
| "eval_runtime": 15.9561, | |
| "eval_samples_per_second": 81.098, | |
| "eval_steps_per_second": 1.316, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 0.0725, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 7.333333333333334e-05, | |
| "loss": 0.0635, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8601236476043277, | |
| "eval_f1": 0.8576618821189325, | |
| "eval_loss": 0.5376073718070984, | |
| "eval_precision": 0.857807955068855, | |
| "eval_recall": 0.8601236476043277, | |
| "eval_runtime": 15.9983, | |
| "eval_samples_per_second": 80.884, | |
| "eval_steps_per_second": 1.313, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 7.000000000000001e-05, | |
| "loss": 0.0663, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0593, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.8608964451313755, | |
| "eval_f1": 0.8604265439449762, | |
| "eval_loss": 0.5060256719589233, | |
| "eval_precision": 0.8615059545164584, | |
| "eval_recall": 0.8608964451313755, | |
| "eval_runtime": 16.9762, | |
| "eval_samples_per_second": 76.224, | |
| "eval_steps_per_second": 1.237, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 0.059, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0656, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.8616692426584235, | |
| "eval_f1": 0.8587396795740828, | |
| "eval_loss": 0.49969562888145447, | |
| "eval_precision": 0.8572557684434807, | |
| "eval_recall": 0.8616692426584235, | |
| "eval_runtime": 16.0811, | |
| "eval_samples_per_second": 80.467, | |
| "eval_steps_per_second": 1.306, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.6666666666666664e-05, | |
| "loss": 0.0572, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.0561, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_accuracy": 0.8585780525502318, | |
| "eval_f1": 0.8588791023200957, | |
| "eval_loss": 0.542958676815033, | |
| "eval_precision": 0.8604335558410716, | |
| "eval_recall": 0.8585780525502318, | |
| "eval_runtime": 16.0649, | |
| "eval_samples_per_second": 80.548, | |
| "eval_steps_per_second": 1.307, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0571, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0523, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8624420401854714, | |
| "eval_f1": 0.8626263407030457, | |
| "eval_loss": 0.5354262590408325, | |
| "eval_precision": 0.864347181311639, | |
| "eval_recall": 0.8624420401854714, | |
| "eval_runtime": 16.9045, | |
| "eval_samples_per_second": 76.548, | |
| "eval_steps_per_second": 1.242, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.052, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 3.9999999999999996e-05, | |
| "loss": 0.0489, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_accuracy": 0.8608964451313755, | |
| "eval_f1": 0.8577206612906209, | |
| "eval_loss": 0.5538966059684753, | |
| "eval_precision": 0.8571591593819834, | |
| "eval_recall": 0.8608964451313755, | |
| "eval_runtime": 15.7779, | |
| "eval_samples_per_second": 82.014, | |
| "eval_steps_per_second": 1.331, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 3.666666666666667e-05, | |
| "loss": 0.0496, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0487, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8608964451313755, | |
| "eval_f1": 0.859123816188036, | |
| "eval_loss": 0.5784664154052734, | |
| "eval_precision": 0.8590888136678329, | |
| "eval_recall": 0.8608964451313755, | |
| "eval_runtime": 16.9672, | |
| "eval_samples_per_second": 76.265, | |
| "eval_steps_per_second": 1.238, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0458, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0485, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_accuracy": 0.8601236476043277, | |
| "eval_f1": 0.8572608771528497, | |
| "eval_loss": 0.6186293363571167, | |
| "eval_precision": 0.8578397224750689, | |
| "eval_recall": 0.8601236476043277, | |
| "eval_runtime": 16.0349, | |
| "eval_samples_per_second": 80.699, | |
| "eval_steps_per_second": 1.31, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0427, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.0518, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8624420401854714, | |
| "eval_f1": 0.8605522010845621, | |
| "eval_loss": 0.6342028975486755, | |
| "eval_precision": 0.8612121254840415, | |
| "eval_recall": 0.8624420401854714, | |
| "eval_runtime": 16.0406, | |
| "eval_samples_per_second": 80.67, | |
| "eval_steps_per_second": 1.309, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 17.49, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0492, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0432, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_accuracy": 0.8585780525502318, | |
| "eval_f1": 0.8579733550892344, | |
| "eval_loss": 0.6302289962768555, | |
| "eval_precision": 0.8597516564232273, | |
| "eval_recall": 0.8585780525502318, | |
| "eval_runtime": 16.8013, | |
| "eval_samples_per_second": 77.018, | |
| "eval_steps_per_second": 1.25, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.0432, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0469, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8616692426584235, | |
| "eval_f1": 0.8603519827698125, | |
| "eval_loss": 0.6323007345199585, | |
| "eval_precision": 0.8606407377798974, | |
| "eval_recall": 0.8616692426584235, | |
| "eval_runtime": 16.0155, | |
| "eval_samples_per_second": 80.797, | |
| "eval_steps_per_second": 1.311, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0452, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.0426, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "eval_accuracy": 0.8601236476043277, | |
| "eval_f1": 0.8582797853944862, | |
| "eval_loss": 0.6502014994621277, | |
| "eval_precision": 0.8582306285016578, | |
| "eval_recall": 0.8601236476043277, | |
| "eval_runtime": 16.0276, | |
| "eval_samples_per_second": 80.736, | |
| "eval_steps_per_second": 1.31, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "step": 400, | |
| "total_flos": 1.8215450718100328e+19, | |
| "train_loss": 0.18401361651718617, | |
| "train_runtime": 2397.1051, | |
| "train_samples_per_second": 43.169, | |
| "train_steps_per_second": 0.167 | |
| } | |
| ], | |
| "max_steps": 400, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.8215450718100328e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |