| { | |
| "best_metric": 1.0753477811813354, | |
| "best_model_checkpoint": "ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v2/checkpoint-750", | |
| "epoch": 9.997091815538013, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.9783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.9545, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9517, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9666, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9694, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9526, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7e-06, | |
| "loss": 0.9504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.9766, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9e-06, | |
| "loss": 0.951, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9501, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.92857142857143e-06, | |
| "loss": 0.9476, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.857142857142859e-06, | |
| "loss": 0.9734, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.785714285714286e-06, | |
| "loss": 0.9455, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.714285714285715e-06, | |
| "loss": 0.9558, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.642857142857144e-06, | |
| "loss": 0.945, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0766645669937134, | |
| "eval_runtime": 396.7921, | |
| "eval_samples_per_second": 6.739, | |
| "eval_steps_per_second": 0.675, | |
| "eval_wer": 0.7282187472042114, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.571428571428573e-06, | |
| "loss": 1.009, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.9516, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.42857142857143e-06, | |
| "loss": 0.9492, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.357142857142859e-06, | |
| "loss": 0.9623, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 0.9597, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.214285714285715e-06, | |
| "loss": 0.9379, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 0.9417, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.071428571428573e-06, | |
| "loss": 0.9649, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9e-06, | |
| "loss": 0.9412, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.944, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.857142857142858e-06, | |
| "loss": 0.9537, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.785714285714286e-06, | |
| "loss": 0.9674, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.714285714285715e-06, | |
| "loss": 0.9479, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.642857142857144e-06, | |
| "loss": 0.9496, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.9445, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.077294111251831, | |
| "eval_runtime": 387.2792, | |
| "eval_samples_per_second": 6.905, | |
| "eval_steps_per_second": 0.692, | |
| "eval_wer": 0.7164846755472682, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.5e-06, | |
| "loss": 1.0108, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.428571428571429e-06, | |
| "loss": 0.939, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.357142857142858e-06, | |
| "loss": 0.9354, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.285714285714287e-06, | |
| "loss": 0.9539, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.214285714285714e-06, | |
| "loss": 0.9509, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.142857142857143e-06, | |
| "loss": 0.94, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.071428571428572e-06, | |
| "loss": 0.9391, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.9588, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.928571428571429e-06, | |
| "loss": 0.9306, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 0.9358, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.785714285714287e-06, | |
| "loss": 0.938, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.714285714285716e-06, | |
| "loss": 0.9591, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.642857142857143e-06, | |
| "loss": 0.9435, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.571428571428572e-06, | |
| "loss": 0.9339, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.9392, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.081303358078003, | |
| "eval_runtime": 381.1488, | |
| "eval_samples_per_second": 7.016, | |
| "eval_steps_per_second": 0.703, | |
| "eval_wer": 0.7141350359979847, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.428571428571429e-06, | |
| "loss": 0.9972, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.357142857142858e-06, | |
| "loss": 0.9387, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.285714285714286e-06, | |
| "loss": 0.936, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 7.2142857142857145e-06, | |
| "loss": 0.9475, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 0.9346, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.0714285714285726e-06, | |
| "loss": 0.9356, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 7e-06, | |
| "loss": 0.93, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 6.928571428571429e-06, | |
| "loss": 0.9631, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 0.9329, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 6.785714285714287e-06, | |
| "loss": 0.9321, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 6.714285714285714e-06, | |
| "loss": 0.9318, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 6.642857142857143e-06, | |
| "loss": 0.9546, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.571428571428572e-06, | |
| "loss": 0.9314, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.9306, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.4285714285714295e-06, | |
| "loss": 0.933, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0858107805252075, | |
| "eval_runtime": 378.2791, | |
| "eval_samples_per_second": 7.069, | |
| "eval_steps_per_second": 0.708, | |
| "eval_wer": 0.7032296949235544, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 6.357142857142858e-06, | |
| "loss": 0.9928, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.285714285714286e-06, | |
| "loss": 0.9338, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.214285714285715e-06, | |
| "loss": 0.9252, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 6.142857142857144e-06, | |
| "loss": 0.9404, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 6.071428571428571e-06, | |
| "loss": 0.943, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9282, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 5.928571428571429e-06, | |
| "loss": 0.9262, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 5.857142857142858e-06, | |
| "loss": 0.953, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 5.785714285714286e-06, | |
| "loss": 0.9247, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.9275, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 5.6428571428571435e-06, | |
| "loss": 0.9281, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 5.571428571428572e-06, | |
| "loss": 0.9534, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.9313, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 5.428571428571429e-06, | |
| "loss": 0.924, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.921, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0753477811813354, | |
| "eval_runtime": 381.1227, | |
| "eval_samples_per_second": 7.016, | |
| "eval_steps_per_second": 0.703, | |
| "eval_wer": 0.7017134946532751, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 5.285714285714286e-06, | |
| "loss": 0.9959, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 5.214285714285715e-06, | |
| "loss": 0.9258, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 5.142857142857142e-06, | |
| "loss": 0.9243, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 5.071428571428571e-06, | |
| "loss": 0.9383, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9343, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 4.928571428571429e-06, | |
| "loss": 0.9226, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 4.857142857142858e-06, | |
| "loss": 0.9173, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 4.785714285714287e-06, | |
| "loss": 0.9431, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.714285714285715e-06, | |
| "loss": 0.9244, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 4.642857142857144e-06, | |
| "loss": 0.9241, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 4.571428571428572e-06, | |
| "loss": 0.9178, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.9462, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 4.428571428571429e-06, | |
| "loss": 0.9264, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 4.357142857142857e-06, | |
| "loss": 0.9198, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 0.9241, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.0786956548690796, | |
| "eval_runtime": 379.7908, | |
| "eval_samples_per_second": 7.041, | |
| "eval_steps_per_second": 0.706, | |
| "eval_wer": 0.6975557156512363, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 4.2142857142857145e-06, | |
| "loss": 0.9893, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 4.1428571428571435e-06, | |
| "loss": 0.9191, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 4.071428571428572e-06, | |
| "loss": 0.9263, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9254, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 3.928571428571429e-06, | |
| "loss": 0.9332, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 3.857142857142858e-06, | |
| "loss": 0.9199, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 3.785714285714286e-06, | |
| "loss": 0.9154, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 3.7142857142857146e-06, | |
| "loss": 0.9424, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 3.642857142857143e-06, | |
| "loss": 0.9172, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 0.9224, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.918, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 3.428571428571429e-06, | |
| "loss": 0.9374, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 3.357142857142857e-06, | |
| "loss": 0.9137, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 3.285714285714286e-06, | |
| "loss": 0.9242, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.2142857142857147e-06, | |
| "loss": 0.9282, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.082495927810669, | |
| "eval_runtime": 383.2073, | |
| "eval_samples_per_second": 6.978, | |
| "eval_steps_per_second": 0.699, | |
| "eval_wer": 0.6959123805756853, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 3.142857142857143e-06, | |
| "loss": 0.9848, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 3.071428571428572e-06, | |
| "loss": 0.9162, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9152, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 2.928571428571429e-06, | |
| "loss": 0.929, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.9288, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 2.785714285714286e-06, | |
| "loss": 0.9184, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 2.7142857142857144e-06, | |
| "loss": 0.9173, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 2.642857142857143e-06, | |
| "loss": 0.9402, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 2.571428571428571e-06, | |
| "loss": 0.921, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.915, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 2.428571428571429e-06, | |
| "loss": 0.9187, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 2.3642857142857144e-06, | |
| "loss": 0.9379, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 2.292857142857143e-06, | |
| "loss": 0.9123, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 2.2214285714285716e-06, | |
| "loss": 0.9096, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.15e-06, | |
| "loss": 0.9184, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.075991153717041, | |
| "eval_runtime": 379.1679, | |
| "eval_samples_per_second": 7.052, | |
| "eval_steps_per_second": 0.707, | |
| "eval_wer": 0.6929788626614495, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 2.0785714285714288e-06, | |
| "loss": 0.9763, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 2.0071428571428573e-06, | |
| "loss": 0.9114, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 1.935714285714286e-06, | |
| "loss": 0.9196, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 1.8642857142857143e-06, | |
| "loss": 0.9268, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 1.7928571428571431e-06, | |
| "loss": 0.9293, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 1.7214285714285717e-06, | |
| "loss": 0.9128, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 1.6500000000000003e-06, | |
| "loss": 0.907, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 1.5785714285714287e-06, | |
| "loss": 0.9437, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.5071428571428573e-06, | |
| "loss": 0.9165, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 1.4357142857142859e-06, | |
| "loss": 0.9177, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 1.3642857142857144e-06, | |
| "loss": 0.9063, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 1.2928571428571428e-06, | |
| "loss": 0.9389, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 1.2214285714285714e-06, | |
| "loss": 0.9135, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 1.1500000000000002e-06, | |
| "loss": 0.9128, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0785714285714286e-06, | |
| "loss": 0.915, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.0773109197616577, | |
| "eval_runtime": 373.9554, | |
| "eval_samples_per_second": 7.151, | |
| "eval_steps_per_second": 0.717, | |
| "eval_wer": 0.6905538839683011, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1.0071428571428572e-06, | |
| "loss": 0.9846, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 9.357142857142858e-07, | |
| "loss": 0.9192, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 8.642857142857144e-07, | |
| "loss": 0.9162, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 7.928571428571428e-07, | |
| "loss": 0.9243, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 7.214285714285715e-07, | |
| "loss": 0.9208, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 6.5e-07, | |
| "loss": 0.9158, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 5.785714285714286e-07, | |
| "loss": 0.9122, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 5.071428571428572e-07, | |
| "loss": 0.9437, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.357142857142858e-07, | |
| "loss": 0.9085, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 3.6428571428571433e-07, | |
| "loss": 0.9151, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 2.9285714285714287e-07, | |
| "loss": 0.9117, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 2.2142857142857143e-07, | |
| "loss": 0.9325, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.9114, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 7.857142857142858e-08, | |
| "loss": 0.9152, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.142857142857144e-09, | |
| "loss": 0.9094, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.0785654783248901, | |
| "eval_runtime": 377.596, | |
| "eval_samples_per_second": 7.082, | |
| "eval_steps_per_second": 0.71, | |
| "eval_wer": 0.6899935490858066, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1500, | |
| "total_flos": 7.288767136199884e+19, | |
| "train_loss": 0.9371341470082601, | |
| "train_runtime": 79168.6766, | |
| "train_samples_per_second": 3.039, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 10, | |
| "total_flos": 7.288767136199884e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |