| { | |
| "best_metric": 0.9985872380503885, | |
| "best_model_checkpoint": "vit_base_aihub_model_py/checkpoint-745", | |
| "epoch": 4.983277591973244, | |
| "global_step": 745, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.2997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 1.134, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.9478, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7246, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5165, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.3778, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.9626865671641794e-05, | |
| "loss": 0.2721, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.888059701492538e-05, | |
| "loss": 0.217, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.813432835820896e-05, | |
| "loss": 0.186, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.738805970149254e-05, | |
| "loss": 0.1654, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.664179104477612e-05, | |
| "loss": 0.1533, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.58955223880597e-05, | |
| "loss": 0.1389, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.5149253731343286e-05, | |
| "loss": 0.1235, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9857546503414175, | |
| "eval_f1": 0.9829586496374041, | |
| "eval_loss": 0.09358736127614975, | |
| "eval_precision": 0.9845287058827537, | |
| "eval_recall": 0.9814155430620309, | |
| "eval_runtime": 111.262, | |
| "eval_samples_per_second": 76.342, | |
| "eval_steps_per_second": 0.602, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.440298507462687e-05, | |
| "loss": 0.1106, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.3656716417910446e-05, | |
| "loss": 0.1162, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.2910447761194036e-05, | |
| "loss": 0.1059, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.216417910447761e-05, | |
| "loss": 0.1115, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.1417910447761195e-05, | |
| "loss": 0.0924, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.067164179104478e-05, | |
| "loss": 0.0972, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.992537313432836e-05, | |
| "loss": 0.0909, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.9179104477611945e-05, | |
| "loss": 0.0977, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.843283582089552e-05, | |
| "loss": 0.0931, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.7686567164179104e-05, | |
| "loss": 0.0756, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.694029850746269e-05, | |
| "loss": 0.083, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.619402985074627e-05, | |
| "loss": 0.0751, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.5447761194029854e-05, | |
| "loss": 0.0666, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.470149253731344e-05, | |
| "loss": 0.0673, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 3.395522388059701e-05, | |
| "loss": 0.067, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.987756063103367, | |
| "eval_f1": 0.9859294798786484, | |
| "eval_loss": 0.06216855347156525, | |
| "eval_precision": 0.990943040361106, | |
| "eval_recall": 0.9812800326186175, | |
| "eval_runtime": 108.9574, | |
| "eval_samples_per_second": 77.957, | |
| "eval_steps_per_second": 0.615, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.32089552238806e-05, | |
| "loss": 0.0754, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.246268656716418e-05, | |
| "loss": 0.0657, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.171641791044776e-05, | |
| "loss": 0.0683, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.0970149253731346e-05, | |
| "loss": 0.0569, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.0223880597014926e-05, | |
| "loss": 0.0515, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.9477611940298512e-05, | |
| "loss": 0.0557, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.8731343283582092e-05, | |
| "loss": 0.0558, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.7985074626865672e-05, | |
| "loss": 0.0592, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.7238805970149255e-05, | |
| "loss": 0.0502, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.6492537313432835e-05, | |
| "loss": 0.0567, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.574626865671642e-05, | |
| "loss": 0.0539, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0512, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 2.4253731343283584e-05, | |
| "loss": 0.0544, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.3507462686567168e-05, | |
| "loss": 0.0561, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.2761194029850747e-05, | |
| "loss": 0.049, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9968212856133741, | |
| "eval_f1": 0.9964206807723841, | |
| "eval_loss": 0.03217490762472153, | |
| "eval_precision": 0.9969469418365854, | |
| "eval_recall": 0.99589824183686, | |
| "eval_runtime": 106.3062, | |
| "eval_samples_per_second": 79.901, | |
| "eval_steps_per_second": 0.63, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.201492537313433e-05, | |
| "loss": 0.0493, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.126865671641791e-05, | |
| "loss": 0.0544, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 2.0522388059701493e-05, | |
| "loss": 0.0495, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.9776119402985073e-05, | |
| "loss": 0.044, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.9029850746268656e-05, | |
| "loss": 0.0452, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.828358208955224e-05, | |
| "loss": 0.0437, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.7537313432835823e-05, | |
| "loss": 0.0374, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.6791044776119406e-05, | |
| "loss": 0.0389, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.6044776119402986e-05, | |
| "loss": 0.0321, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.529850746268657e-05, | |
| "loss": 0.0347, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.455223880597015e-05, | |
| "loss": 0.0359, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.3805970149253733e-05, | |
| "loss": 0.0369, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.3059701492537313e-05, | |
| "loss": 0.0367, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.2313432835820896e-05, | |
| "loss": 0.0353, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.1567164179104478e-05, | |
| "loss": 0.0477, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9977631269131152, | |
| "eval_f1": 0.997511338692231, | |
| "eval_loss": 0.024851497262716293, | |
| "eval_precision": 0.9985286326587551, | |
| "eval_recall": 0.9965020764725261, | |
| "eval_runtime": 103.7864, | |
| "eval_samples_per_second": 81.841, | |
| "eval_steps_per_second": 0.646, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.082089552238806e-05, | |
| "loss": 0.0382, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.0074626865671643e-05, | |
| "loss": 0.0347, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.328358208955226e-06, | |
| "loss": 0.0304, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.582089552238805e-06, | |
| "loss": 0.0373, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 7.835820895522389e-06, | |
| "loss": 0.0311, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 7.08955223880597e-06, | |
| "loss": 0.0332, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.343283582089552e-06, | |
| "loss": 0.0334, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 5.597014925373135e-06, | |
| "loss": 0.0329, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.850746268656717e-06, | |
| "loss": 0.0332, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.1044776119402985e-06, | |
| "loss": 0.0303, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 3.358208955223881e-06, | |
| "loss": 0.0276, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.6119402985074627e-06, | |
| "loss": 0.0332, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.8656716417910446e-06, | |
| "loss": 0.0317, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 1.119402985074627e-06, | |
| "loss": 0.0315, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 3.7313432835820895e-07, | |
| "loss": 0.0336, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "eval_accuracy": 0.9985872380503885, | |
| "eval_f1": 0.9985770990024514, | |
| "eval_loss": 0.021681277081370354, | |
| "eval_precision": 0.9989954885489135, | |
| "eval_recall": 0.998161142953993, | |
| "eval_runtime": 106.6587, | |
| "eval_samples_per_second": 79.637, | |
| "eval_steps_per_second": 0.628, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "step": 745, | |
| "total_flos": 2.9526217173796848e+19, | |
| "train_loss": 0.14726725356690837, | |
| "train_runtime": 5241.8792, | |
| "train_samples_per_second": 72.911, | |
| "train_steps_per_second": 0.142 | |
| } | |
| ], | |
| "max_steps": 745, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.9526217173796848e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |