| { | |
| "best_metric": 0.9099099099099099, | |
| "best_model_checkpoint": "10-convnextv2-nano-22k-384-finetuned-spiderTraining20-500/checkpoint-800", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.25e-06, | |
| "loss": 3.1451, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.25e-05, | |
| "loss": 3.1259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 2.9715, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.7642, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.5662, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.2829, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.375e-05, | |
| "loss": 2.0106, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7156, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6316316316316316, | |
| "eval_f1": 0.6154711933932746, | |
| "eval_loss": 1.4313874244689941, | |
| "eval_precision": 0.6182233977895779, | |
| "eval_recall": 0.6246499047821599, | |
| "eval_runtime": 10.8324, | |
| "eval_samples_per_second": 92.223, | |
| "eval_steps_per_second": 3.693, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 1.4422, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.2846, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.791666666666667e-05, | |
| "loss": 1.0943, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.024, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.652777777777778e-05, | |
| "loss": 0.8952, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.8542, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.8182, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.7565, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8168168168168168, | |
| "eval_f1": 0.8095428833652196, | |
| "eval_loss": 0.634009063243866, | |
| "eval_precision": 0.8213363501056982, | |
| "eval_recall": 0.8074183342516351, | |
| "eval_runtime": 11.5227, | |
| "eval_samples_per_second": 86.698, | |
| "eval_steps_per_second": 3.471, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.7224, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.6599, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.236111111111111e-05, | |
| "loss": 0.617, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6116, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.0972222222222225e-05, | |
| "loss": 0.5726, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.6103, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.958333333333333e-05, | |
| "loss": 0.5996, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.5802, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8588588588588588, | |
| "eval_f1": 0.8539214264372446, | |
| "eval_loss": 0.4632730782032013, | |
| "eval_precision": 0.8566478880124299, | |
| "eval_recall": 0.8544949553061285, | |
| "eval_runtime": 10.9172, | |
| "eval_samples_per_second": 91.507, | |
| "eval_steps_per_second": 3.664, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.528, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.481, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.6805555555555556e-05, | |
| "loss": 0.4882, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.5335, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 3.541666666666667e-05, | |
| "loss": 0.5088, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.4647, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.402777777777778e-05, | |
| "loss": 0.4677, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4765, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8758758758758759, | |
| "eval_f1": 0.8708195092986228, | |
| "eval_loss": 0.4005794823169708, | |
| "eval_precision": 0.8745697101491127, | |
| "eval_recall": 0.8709417256085896, | |
| "eval_runtime": 10.712, | |
| "eval_samples_per_second": 93.26, | |
| "eval_steps_per_second": 3.734, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.263888888888889e-05, | |
| "loss": 0.4197, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.3985, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.4315, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.4256, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.9861111111111113e-05, | |
| "loss": 0.4086, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.3753, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 0.4019, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3644, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9019019019019019, | |
| "eval_f1": 0.8979132685961181, | |
| "eval_loss": 0.35299161076545715, | |
| "eval_precision": 0.8994843529874992, | |
| "eval_recall": 0.8984207235280925, | |
| "eval_runtime": 11.3754, | |
| "eval_samples_per_second": 87.821, | |
| "eval_steps_per_second": 3.516, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.4145, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.3786, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 0.3845, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3951, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.361, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.3661, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.3278, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3622, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9049049049049049, | |
| "eval_f1": 0.9013077009350899, | |
| "eval_loss": 0.33261367678642273, | |
| "eval_precision": 0.9019378592590697, | |
| "eval_recall": 0.9019909969066763, | |
| "eval_runtime": 10.7748, | |
| "eval_samples_per_second": 92.716, | |
| "eval_steps_per_second": 3.712, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 2.152777777777778e-05, | |
| "loss": 0.3612, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.3223, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 0.3559, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.3575, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.3275, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.3051, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.3303, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.3232, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8938938938938938, | |
| "eval_f1": 0.8892011579580226, | |
| "eval_loss": 0.3179842531681061, | |
| "eval_precision": 0.8909630589714048, | |
| "eval_recall": 0.8889252861904225, | |
| "eval_runtime": 10.838, | |
| "eval_samples_per_second": 92.176, | |
| "eval_steps_per_second": 3.691, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 1.597222222222222e-05, | |
| "loss": 0.3028, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.3362, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 1.4583333333333335e-05, | |
| "loss": 0.2878, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3264, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.3194444444444446e-05, | |
| "loss": 0.2952, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3197, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 0.3291, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2968, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.908908908908909, | |
| "eval_f1": 0.9038850741319278, | |
| "eval_loss": 0.3018168807029724, | |
| "eval_precision": 0.9049510380750571, | |
| "eval_recall": 0.903886107847755, | |
| "eval_runtime": 11.3593, | |
| "eval_samples_per_second": 87.946, | |
| "eval_steps_per_second": 3.521, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.2701, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.3409, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 9.027777777777777e-06, | |
| "loss": 0.2587, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.3128, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 7.63888888888889e-06, | |
| "loss": 0.2789, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3111, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.2833, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.285, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9029029029029029, | |
| "eval_f1": 0.8974149218187346, | |
| "eval_loss": 0.30974340438842773, | |
| "eval_precision": 0.897913672792708, | |
| "eval_recall": 0.8990571292245519, | |
| "eval_runtime": 10.8119, | |
| "eval_samples_per_second": 92.398, | |
| "eval_steps_per_second": 3.7, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 4.861111111111111e-06, | |
| "loss": 0.293, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.2697, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.254, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.2803, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.2539, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.2605, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 6.944444444444445e-07, | |
| "loss": 0.249, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2889, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9099099099099099, | |
| "eval_f1": 0.9048297543768958, | |
| "eval_loss": 0.2969054877758026, | |
| "eval_precision": 0.9049316662055762, | |
| "eval_recall": 0.9057042739377195, | |
| "eval_runtime": 10.8178, | |
| "eval_samples_per_second": 92.347, | |
| "eval_steps_per_second": 3.698, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 800, | |
| "total_flos": 3.1805375717677466e+18, | |
| "train_loss": 0.6694481897354126, | |
| "train_runtime": 1321.2072, | |
| "train_samples_per_second": 60.483, | |
| "train_steps_per_second": 0.606 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 800, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 3.1805375717677466e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |