| { | |
| "best_metric": 0.758887171561051, | |
| "best_model_checkpoint": "resnet152-FV-finetuned-memes/checkpoint-300", | |
| "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": 1.605, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.4520865533230294, | |
| "eval_f1": 0.2879543301590467, | |
| "eval_loss": 1.542733907699585, | |
| "eval_precision": 0.31310616306027816, | |
| "eval_recall": 0.4520865533230294, | |
| "eval_runtime": 13.5797, | |
| "eval_samples_per_second": 95.289, | |
| "eval_steps_per_second": 1.546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9e-05, | |
| "loss": 1.557, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4353, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.44899536321483774, | |
| "eval_f1": 0.27913559166246477, | |
| "eval_loss": 1.378554105758667, | |
| "eval_precision": 0.3849846576082604, | |
| "eval_recall": 0.44899536321483774, | |
| "eval_runtime": 11.7486, | |
| "eval_samples_per_second": 110.141, | |
| "eval_steps_per_second": 1.787, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 1.3861, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00011333333333333333, | |
| "loss": 1.3026, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.47990726429675423, | |
| "eval_f1": 0.33925239665034806, | |
| "eval_loss": 1.2733628749847412, | |
| "eval_precision": 0.3072903900501765, | |
| "eval_recall": 0.47990726429675423, | |
| "eval_runtime": 11.82, | |
| "eval_samples_per_second": 109.475, | |
| "eval_steps_per_second": 1.777, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00011, | |
| "loss": 1.2728, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 1.1579, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.5278207109737248, | |
| "eval_f1": 0.41425802390052474, | |
| "eval_loss": 1.137792706489563, | |
| "eval_precision": 0.4299797234929115, | |
| "eval_recall": 0.5278207109737248, | |
| "eval_runtime": 11.7797, | |
| "eval_samples_per_second": 109.85, | |
| "eval_steps_per_second": 1.783, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00010333333333333334, | |
| "loss": 1.1096, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0276, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.5734157650695518, | |
| "eval_f1": 0.4864664230611172, | |
| "eval_loss": 1.0231207609176636, | |
| "eval_precision": 0.449744448551538, | |
| "eval_recall": 0.5734157650695518, | |
| "eval_runtime": 11.7657, | |
| "eval_samples_per_second": 109.98, | |
| "eval_steps_per_second": 1.785, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 0.9751, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.8826, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.625193199381762, | |
| "eval_f1": 0.5636892396732486, | |
| "eval_loss": 0.9227971434593201, | |
| "eval_precision": 0.5982698615367767, | |
| "eval_recall": 0.625193199381762, | |
| "eval_runtime": 12.7817, | |
| "eval_samples_per_second": 101.239, | |
| "eval_steps_per_second": 1.643, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8232, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.766, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.6661514683153014, | |
| "eval_f1": 0.6320349212780727, | |
| "eval_loss": 0.8440618515014648, | |
| "eval_precision": 0.647375804405681, | |
| "eval_recall": 0.6661514683153014, | |
| "eval_runtime": 11.8583, | |
| "eval_samples_per_second": 109.122, | |
| "eval_steps_per_second": 1.771, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 0.7145, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 7.999999999999999e-05, | |
| "loss": 0.6732, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.6901081916537867, | |
| "eval_f1": 0.6704100670249821, | |
| "eval_loss": 0.8009499311447144, | |
| "eval_precision": 0.6758956033590393, | |
| "eval_recall": 0.6901081916537867, | |
| "eval_runtime": 11.8229, | |
| "eval_samples_per_second": 109.449, | |
| "eval_steps_per_second": 1.776, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 0.635, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 7.333333333333334e-05, | |
| "loss": 0.5653, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.7217928902627512, | |
| "eval_f1": 0.7129313347452736, | |
| "eval_loss": 0.7535430192947388, | |
| "eval_precision": 0.7141409959676454, | |
| "eval_recall": 0.7217928902627512, | |
| "eval_runtime": 11.8519, | |
| "eval_samples_per_second": 109.181, | |
| "eval_steps_per_second": 1.772, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 7.000000000000001e-05, | |
| "loss": 0.5358, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4957, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.7256568778979907, | |
| "eval_f1": 0.7199928490312443, | |
| "eval_loss": 0.731657087802887, | |
| "eval_precision": 0.7247700086876532, | |
| "eval_recall": 0.7256568778979907, | |
| "eval_runtime": 12.0809, | |
| "eval_samples_per_second": 107.111, | |
| "eval_steps_per_second": 1.738, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 0.471, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 6e-05, | |
| "loss": 0.4534, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.7434312210200927, | |
| "eval_f1": 0.7389905178601613, | |
| "eval_loss": 0.6807736158370972, | |
| "eval_precision": 0.7405180153510328, | |
| "eval_recall": 0.7434312210200927, | |
| "eval_runtime": 12.457, | |
| "eval_samples_per_second": 103.877, | |
| "eval_steps_per_second": 1.686, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.6666666666666664e-05, | |
| "loss": 0.4102, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.3792, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_accuracy": 0.7449768160741885, | |
| "eval_f1": 0.7398936491076405, | |
| "eval_loss": 0.694913387298584, | |
| "eval_precision": 0.7453650213081748, | |
| "eval_recall": 0.7449768160741885, | |
| "eval_runtime": 11.855, | |
| "eval_samples_per_second": 109.153, | |
| "eval_steps_per_second": 1.771, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3766, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.3489, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.749613601236476, | |
| "eval_f1": 0.7474367490892962, | |
| "eval_loss": 0.6745789647102356, | |
| "eval_precision": 0.751086737820255, | |
| "eval_recall": 0.749613601236476, | |
| "eval_runtime": 11.7383, | |
| "eval_samples_per_second": 110.237, | |
| "eval_steps_per_second": 1.789, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.3487, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 3.9999999999999996e-05, | |
| "loss": 0.3113, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_accuracy": 0.7573415765069552, | |
| "eval_f1": 0.7578669772980416, | |
| "eval_loss": 0.6637156009674072, | |
| "eval_precision": 0.7638354392114911, | |
| "eval_recall": 0.7573415765069552, | |
| "eval_runtime": 11.864, | |
| "eval_samples_per_second": 109.069, | |
| "eval_steps_per_second": 1.77, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 3.666666666666667e-05, | |
| "loss": 0.3036, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2947, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.758887171561051, | |
| "eval_f1": 0.7609777447379339, | |
| "eval_loss": 0.6451451182365417, | |
| "eval_precision": 0.7666890251959252, | |
| "eval_recall": 0.758887171561051, | |
| "eval_runtime": 11.5648, | |
| "eval_samples_per_second": 111.891, | |
| "eval_steps_per_second": 1.816, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2748, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.2776, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_accuracy": 0.7542503863987635, | |
| "eval_f1": 0.7525049520726458, | |
| "eval_loss": 0.6754108667373657, | |
| "eval_precision": 0.7565187938926003, | |
| "eval_recall": 0.7542503863987635, | |
| "eval_runtime": 12.7697, | |
| "eval_samples_per_second": 101.334, | |
| "eval_steps_per_second": 1.645, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.272, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.2611, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.7550231839258115, | |
| "eval_f1": 0.7529156321916382, | |
| "eval_loss": 0.6808292269706726, | |
| "eval_precision": 0.7606561956666212, | |
| "eval_recall": 0.7550231839258115, | |
| "eval_runtime": 11.6273, | |
| "eval_samples_per_second": 111.29, | |
| "eval_steps_per_second": 1.806, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 17.49, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2508, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.2428, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_accuracy": 0.7457496136012365, | |
| "eval_f1": 0.7403755418120831, | |
| "eval_loss": 0.7005118727684021, | |
| "eval_precision": 0.7497269917356472, | |
| "eval_recall": 0.7457496136012365, | |
| "eval_runtime": 11.7515, | |
| "eval_samples_per_second": 110.114, | |
| "eval_steps_per_second": 1.787, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.2479, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2346, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.7573415765069552, | |
| "eval_f1": 0.7590201528020784, | |
| "eval_loss": 0.6597253680229187, | |
| "eval_precision": 0.7642128778135023, | |
| "eval_recall": 0.7573415765069552, | |
| "eval_runtime": 11.869, | |
| "eval_samples_per_second": 109.024, | |
| "eval_steps_per_second": 1.769, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.2312, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.2367, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "eval_accuracy": 0.7557959814528593, | |
| "eval_f1": 0.7545674798253312, | |
| "eval_loss": 0.6771848797798157, | |
| "eval_precision": 0.7556690736625777, | |
| "eval_recall": 0.7557959814528593, | |
| "eval_runtime": 12.018, | |
| "eval_samples_per_second": 107.672, | |
| "eval_steps_per_second": 1.747, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "step": 400, | |
| "total_flos": 5.432231359979311e+18, | |
| "train_loss": 0.6680345350503921, | |
| "train_runtime": 1446.6101, | |
| "train_samples_per_second": 71.533, | |
| "train_steps_per_second": 0.277 | |
| } | |
| ], | |
| "max_steps": 400, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.432231359979311e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |