| { |
| "best_metric": 0.7454545454545455, |
| "best_model_checkpoint": "musical_instrument_detection/checkpoint-880", |
| "epoch": 9.0, |
| "global_step": 990, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09, |
| "learning_rate": 2.2727272727272728e-06, |
| "loss": 1.3832, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 6.363636363636363e-06, |
| "loss": 1.3826, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 1.0909090909090909e-05, |
| "loss": 1.3771, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 1.5454545454545454e-05, |
| "loss": 1.3637, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 2e-05, |
| "loss": 1.3153, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 2.4090909090909093e-05, |
| "loss": 1.2652, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 2.818181818181818e-05, |
| "loss": 1.206, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 3.272727272727273e-05, |
| "loss": 1.1668, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 3.7272727272727276e-05, |
| "loss": 1.0206, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 4.181818181818182e-05, |
| "loss": 0.9209, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.636363636363636e-05, |
| "loss": 0.915, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6840909090909091, |
| "eval_loss": 0.7616810202598572, |
| "eval_runtime": 1.7303, |
| "eval_samples_per_second": 254.292, |
| "eval_steps_per_second": 16.182, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 4.98989898989899e-05, |
| "loss": 0.8261, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 4.93939393939394e-05, |
| "loss": 0.7007, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 4.888888888888889e-05, |
| "loss": 0.6626, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 4.838383838383839e-05, |
| "loss": 0.7052, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 4.787878787878788e-05, |
| "loss": 0.5762, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 4.7373737373737375e-05, |
| "loss": 0.6254, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 4.686868686868687e-05, |
| "loss": 0.6862, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 4.636363636363636e-05, |
| "loss": 0.6261, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 4.585858585858586e-05, |
| "loss": 0.4829, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 4.535353535353535e-05, |
| "loss": 0.6237, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.484848484848485e-05, |
| "loss": 0.5571, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7, |
| "eval_loss": 0.5293846130371094, |
| "eval_runtime": 1.6933, |
| "eval_samples_per_second": 259.853, |
| "eval_steps_per_second": 16.536, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 4.4343434343434346e-05, |
| "loss": 0.5672, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 4.383838383838384e-05, |
| "loss": 0.4679, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 4.3333333333333334e-05, |
| "loss": 0.5218, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 4.282828282828283e-05, |
| "loss": 0.5658, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 4.232323232323233e-05, |
| "loss": 0.5014, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 4.181818181818182e-05, |
| "loss": 0.6555, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 4.131313131313132e-05, |
| "loss": 0.5774, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 4.0808080808080814e-05, |
| "loss": 0.6724, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 4.0303030303030305e-05, |
| "loss": 0.6298, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 3.97979797979798e-05, |
| "loss": 0.749, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3.929292929292929e-05, |
| "loss": 0.5629, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7068181818181818, |
| "eval_loss": 0.5072448253631592, |
| "eval_runtime": 1.7135, |
| "eval_samples_per_second": 256.784, |
| "eval_steps_per_second": 16.341, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 3.878787878787879e-05, |
| "loss": 0.4553, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 3.828282828282829e-05, |
| "loss": 0.6201, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 3.777777777777778e-05, |
| "loss": 0.5706, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 3.7272727272727276e-05, |
| "loss": 0.55, |
| "step": 370 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 3.6767676767676766e-05, |
| "loss": 0.7007, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 3.6262626262626264e-05, |
| "loss": 0.6223, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.64, |
| "learning_rate": 3.580808080808081e-05, |
| "loss": 0.5043, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 3.5303030303030305e-05, |
| "loss": 0.4435, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 3.47979797979798e-05, |
| "loss": 0.505, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 3.429292929292929e-05, |
| "loss": 0.5386, |
| "step": 430 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3.378787878787879e-05, |
| "loss": 0.4404, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7363636363636363, |
| "eval_loss": 0.5771055817604065, |
| "eval_runtime": 1.7404, |
| "eval_samples_per_second": 252.816, |
| "eval_steps_per_second": 16.088, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.09, |
| "learning_rate": 3.328282828282828e-05, |
| "loss": 0.5319, |
| "step": 450 |
| }, |
| { |
| "epoch": 4.18, |
| "learning_rate": 3.277777777777778e-05, |
| "loss": 0.8757, |
| "step": 460 |
| }, |
| { |
| "epoch": 4.27, |
| "learning_rate": 3.2272727272727276e-05, |
| "loss": 0.5095, |
| "step": 470 |
| }, |
| { |
| "epoch": 4.36, |
| "learning_rate": 3.176767676767677e-05, |
| "loss": 0.5075, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.45, |
| "learning_rate": 3.1262626262626264e-05, |
| "loss": 0.4275, |
| "step": 490 |
| }, |
| { |
| "epoch": 4.55, |
| "learning_rate": 3.0757575757575755e-05, |
| "loss": 0.5852, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.64, |
| "learning_rate": 3.0252525252525255e-05, |
| "loss": 0.5715, |
| "step": 510 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 2.9747474747474746e-05, |
| "loss": 0.5707, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.82, |
| "learning_rate": 2.9242424242424243e-05, |
| "loss": 0.5304, |
| "step": 530 |
| }, |
| { |
| "epoch": 4.91, |
| "learning_rate": 2.873737373737374e-05, |
| "loss": 0.4553, |
| "step": 540 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 2.823232323232323e-05, |
| "loss": 0.5738, |
| "step": 550 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7045454545454546, |
| "eval_loss": 0.573459267616272, |
| "eval_runtime": 1.7421, |
| "eval_samples_per_second": 252.566, |
| "eval_steps_per_second": 16.072, |
| "step": 550 |
| }, |
| { |
| "epoch": 5.09, |
| "learning_rate": 2.772727272727273e-05, |
| "loss": 0.555, |
| "step": 560 |
| }, |
| { |
| "epoch": 5.18, |
| "learning_rate": 2.7222222222222223e-05, |
| "loss": 0.4679, |
| "step": 570 |
| }, |
| { |
| "epoch": 5.27, |
| "learning_rate": 2.6717171717171717e-05, |
| "loss": 0.4835, |
| "step": 580 |
| }, |
| { |
| "epoch": 5.36, |
| "learning_rate": 2.6212121212121214e-05, |
| "loss": 0.5586, |
| "step": 590 |
| }, |
| { |
| "epoch": 5.45, |
| "learning_rate": 2.5707070707070708e-05, |
| "loss": 0.4947, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.55, |
| "learning_rate": 2.5202020202020206e-05, |
| "loss": 0.6546, |
| "step": 610 |
| }, |
| { |
| "epoch": 5.64, |
| "learning_rate": 2.46969696969697e-05, |
| "loss": 0.5381, |
| "step": 620 |
| }, |
| { |
| "epoch": 5.73, |
| "learning_rate": 2.4191919191919194e-05, |
| "loss": 0.5108, |
| "step": 630 |
| }, |
| { |
| "epoch": 5.82, |
| "learning_rate": 2.3686868686868688e-05, |
| "loss": 0.3424, |
| "step": 640 |
| }, |
| { |
| "epoch": 5.91, |
| "learning_rate": 2.318181818181818e-05, |
| "loss": 0.4423, |
| "step": 650 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 2.2676767676767676e-05, |
| "loss": 0.4274, |
| "step": 660 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7113636363636363, |
| "eval_loss": 0.4726010859012604, |
| "eval_runtime": 1.7193, |
| "eval_samples_per_second": 255.911, |
| "eval_steps_per_second": 16.285, |
| "step": 660 |
| }, |
| { |
| "epoch": 6.09, |
| "learning_rate": 2.2171717171717173e-05, |
| "loss": 0.4989, |
| "step": 670 |
| }, |
| { |
| "epoch": 6.18, |
| "learning_rate": 2.1666666666666667e-05, |
| "loss": 0.4573, |
| "step": 680 |
| }, |
| { |
| "epoch": 6.27, |
| "learning_rate": 2.1161616161616164e-05, |
| "loss": 0.4592, |
| "step": 690 |
| }, |
| { |
| "epoch": 6.36, |
| "learning_rate": 2.065656565656566e-05, |
| "loss": 0.3652, |
| "step": 700 |
| }, |
| { |
| "epoch": 6.45, |
| "learning_rate": 2.0151515151515152e-05, |
| "loss": 0.4113, |
| "step": 710 |
| }, |
| { |
| "epoch": 6.55, |
| "learning_rate": 1.9646464646464646e-05, |
| "loss": 0.4354, |
| "step": 720 |
| }, |
| { |
| "epoch": 6.64, |
| "learning_rate": 1.9141414141414144e-05, |
| "loss": 0.4011, |
| "step": 730 |
| }, |
| { |
| "epoch": 6.73, |
| "learning_rate": 1.8636363636363638e-05, |
| "loss": 0.5458, |
| "step": 740 |
| }, |
| { |
| "epoch": 6.82, |
| "learning_rate": 1.8131313131313132e-05, |
| "loss": 0.4843, |
| "step": 750 |
| }, |
| { |
| "epoch": 6.91, |
| "learning_rate": 1.7626262626262626e-05, |
| "loss": 0.3717, |
| "step": 760 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 1.712121212121212e-05, |
| "loss": 0.4862, |
| "step": 770 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.7295454545454545, |
| "eval_loss": 0.5498502254486084, |
| "eval_runtime": 1.7249, |
| "eval_samples_per_second": 255.081, |
| "eval_steps_per_second": 16.232, |
| "step": 770 |
| }, |
| { |
| "epoch": 7.09, |
| "learning_rate": 1.6616161616161617e-05, |
| "loss": 0.4092, |
| "step": 780 |
| }, |
| { |
| "epoch": 7.18, |
| "learning_rate": 1.6111111111111115e-05, |
| "loss": 0.5646, |
| "step": 790 |
| }, |
| { |
| "epoch": 7.27, |
| "learning_rate": 1.560606060606061e-05, |
| "loss": 0.4574, |
| "step": 800 |
| }, |
| { |
| "epoch": 7.36, |
| "learning_rate": 1.5101010101010103e-05, |
| "loss": 0.3753, |
| "step": 810 |
| }, |
| { |
| "epoch": 7.45, |
| "learning_rate": 1.4595959595959597e-05, |
| "loss": 0.4217, |
| "step": 820 |
| }, |
| { |
| "epoch": 7.55, |
| "learning_rate": 1.409090909090909e-05, |
| "loss": 0.3904, |
| "step": 830 |
| }, |
| { |
| "epoch": 7.64, |
| "learning_rate": 1.3585858585858585e-05, |
| "loss": 0.4661, |
| "step": 840 |
| }, |
| { |
| "epoch": 7.73, |
| "learning_rate": 1.3080808080808082e-05, |
| "loss": 0.4999, |
| "step": 850 |
| }, |
| { |
| "epoch": 7.82, |
| "learning_rate": 1.2575757575757578e-05, |
| "loss": 0.4028, |
| "step": 860 |
| }, |
| { |
| "epoch": 7.91, |
| "learning_rate": 1.2070707070707072e-05, |
| "loss": 0.4746, |
| "step": 870 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 1.1565656565656566e-05, |
| "loss": 0.4858, |
| "step": 880 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.7454545454545455, |
| "eval_loss": 0.48499324917793274, |
| "eval_runtime": 1.757, |
| "eval_samples_per_second": 250.426, |
| "eval_steps_per_second": 15.936, |
| "step": 880 |
| }, |
| { |
| "epoch": 8.09, |
| "learning_rate": 1.1060606060606061e-05, |
| "loss": 0.4253, |
| "step": 890 |
| }, |
| { |
| "epoch": 8.18, |
| "learning_rate": 1.0555555555555555e-05, |
| "loss": 0.3727, |
| "step": 900 |
| }, |
| { |
| "epoch": 8.27, |
| "learning_rate": 1.0050505050505051e-05, |
| "loss": 0.4128, |
| "step": 910 |
| }, |
| { |
| "epoch": 8.36, |
| "learning_rate": 9.545454545454547e-06, |
| "loss": 0.3716, |
| "step": 920 |
| }, |
| { |
| "epoch": 8.45, |
| "learning_rate": 9.04040404040404e-06, |
| "loss": 0.5014, |
| "step": 930 |
| }, |
| { |
| "epoch": 8.55, |
| "learning_rate": 8.535353535353535e-06, |
| "loss": 0.3035, |
| "step": 940 |
| }, |
| { |
| "epoch": 8.64, |
| "learning_rate": 8.03030303030303e-06, |
| "loss": 0.4856, |
| "step": 950 |
| }, |
| { |
| "epoch": 8.73, |
| "learning_rate": 7.525252525252525e-06, |
| "loss": 0.4145, |
| "step": 960 |
| }, |
| { |
| "epoch": 8.82, |
| "learning_rate": 7.02020202020202e-06, |
| "loss": 0.4519, |
| "step": 970 |
| }, |
| { |
| "epoch": 8.91, |
| "learning_rate": 6.515151515151516e-06, |
| "loss": 0.4519, |
| "step": 980 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 6.01010101010101e-06, |
| "loss": 0.4069, |
| "step": 990 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.7068181818181818, |
| "eval_loss": 0.5249894261360168, |
| "eval_runtime": 1.716, |
| "eval_samples_per_second": 256.412, |
| "eval_steps_per_second": 16.317, |
| "step": 990 |
| } |
| ], |
| "max_steps": 1100, |
| "num_train_epochs": 10, |
| "total_flos": 1.43479490075136e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
