| { |
| "best_metric": 0.88, |
| "best_model_checkpoint": "dinov2-base-finetuned-dia_eye/checkpoint-2500", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "grad_norm": 90.73234558105469, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 1.7164, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 120.8720932006836, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 1.5765, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 83.37552642822266, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 1.4828, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 72.08551025390625, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 1.4564, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 95.60829162597656, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.3918, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 113.41104888916016, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 1.3633, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 113.49620819091797, |
| "learning_rate": 5.600000000000001e-06, |
| "loss": 1.4582, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 60.3448486328125, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 1.3945, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 87.17510223388672, |
| "learning_rate": 7.2000000000000005e-06, |
| "loss": 1.2236, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 116.16291809082031, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.2932, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 91.94257354736328, |
| "learning_rate": 8.8e-06, |
| "loss": 1.2999, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 85.25334167480469, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 1.4004, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 82.13865661621094, |
| "learning_rate": 1.04e-05, |
| "loss": 1.5986, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 86.27275085449219, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 1.3174, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 120.41253662109375, |
| "learning_rate": 1.2e-05, |
| "loss": 1.3869, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 61.761695861816406, |
| "learning_rate": 1.2800000000000001e-05, |
| "loss": 1.3498, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 53.90617752075195, |
| "learning_rate": 1.3600000000000002e-05, |
| "loss": 1.1202, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 65.96098327636719, |
| "learning_rate": 1.4400000000000001e-05, |
| "loss": 1.3588, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 60.957847595214844, |
| "learning_rate": 1.5200000000000002e-05, |
| "loss": 1.4875, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 31.72243309020996, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.3045, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 81.10260772705078, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 1.2088, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 51.385196685791016, |
| "learning_rate": 1.76e-05, |
| "loss": 1.352, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 43.19595718383789, |
| "learning_rate": 1.8400000000000003e-05, |
| "loss": 1.2643, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 69.54638671875, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 1.3476, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 39.397499084472656, |
| "learning_rate": 2e-05, |
| "loss": 1.2812, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.494, |
| "eval_f1": 0.4460326515069461, |
| "eval_loss": 1.1658940315246582, |
| "eval_runtime": 12.2613, |
| "eval_samples_per_second": 40.779, |
| "eval_steps_per_second": 10.195, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 29.106040954589844, |
| "learning_rate": 1.9911111111111112e-05, |
| "loss": 1.1481, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.08, |
| "grad_norm": 48.481876373291016, |
| "learning_rate": 1.9822222222222226e-05, |
| "loss": 1.2368, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.12, |
| "grad_norm": 36.711673736572266, |
| "learning_rate": 1.9733333333333336e-05, |
| "loss": 1.325, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.16, |
| "grad_norm": 70.87812805175781, |
| "learning_rate": 1.9644444444444447e-05, |
| "loss": 1.1004, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 45.34326171875, |
| "learning_rate": 1.9555555555555557e-05, |
| "loss": 1.2207, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.24, |
| "grad_norm": 39.800941467285156, |
| "learning_rate": 1.9466666666666668e-05, |
| "loss": 1.1775, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.28, |
| "grad_norm": 33.798614501953125, |
| "learning_rate": 1.9377777777777778e-05, |
| "loss": 1.097, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.32, |
| "grad_norm": 95.97491455078125, |
| "learning_rate": 1.928888888888889e-05, |
| "loss": 1.1752, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "grad_norm": 49.4578971862793, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 1.2785, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 48.13294219970703, |
| "learning_rate": 1.9111111111111113e-05, |
| "loss": 1.3751, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.44, |
| "grad_norm": 27.46150779724121, |
| "learning_rate": 1.9022222222222223e-05, |
| "loss": 1.2267, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.48, |
| "grad_norm": 83.89068603515625, |
| "learning_rate": 1.8933333333333334e-05, |
| "loss": 1.1817, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 36.93865203857422, |
| "learning_rate": 1.8844444444444444e-05, |
| "loss": 1.0889, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 36.16452407836914, |
| "learning_rate": 1.8755555555555558e-05, |
| "loss": 1.1369, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 30.880001068115234, |
| "learning_rate": 1.866666666666667e-05, |
| "loss": 1.1892, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.6400000000000001, |
| "grad_norm": 35.53660202026367, |
| "learning_rate": 1.857777777777778e-05, |
| "loss": 1.0495, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "grad_norm": 125.27716827392578, |
| "learning_rate": 1.848888888888889e-05, |
| "loss": 1.0685, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.72, |
| "grad_norm": 45.547950744628906, |
| "learning_rate": 1.8400000000000003e-05, |
| "loss": 1.1031, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.76, |
| "grad_norm": 54.839542388916016, |
| "learning_rate": 1.8311111111111114e-05, |
| "loss": 1.1888, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 20.931964874267578, |
| "learning_rate": 1.8222222222222224e-05, |
| "loss": 1.2119, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.8399999999999999, |
| "grad_norm": 28.963083267211914, |
| "learning_rate": 1.8133333333333335e-05, |
| "loss": 1.0865, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.88, |
| "grad_norm": 59.61734390258789, |
| "learning_rate": 1.8044444444444445e-05, |
| "loss": 1.1195, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.92, |
| "grad_norm": 43.75231170654297, |
| "learning_rate": 1.7955555555555556e-05, |
| "loss": 1.1171, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.96, |
| "grad_norm": 27.184715270996094, |
| "learning_rate": 1.7866666666666666e-05, |
| "loss": 1.1224, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 38.968082427978516, |
| "learning_rate": 1.7777777777777777e-05, |
| "loss": 1.0885, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.46, |
| "eval_f1": 0.40981236448175834, |
| "eval_loss": 1.1569879055023193, |
| "eval_runtime": 12.149, |
| "eval_samples_per_second": 41.156, |
| "eval_steps_per_second": 10.289, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.04, |
| "grad_norm": 50.790748596191406, |
| "learning_rate": 1.768888888888889e-05, |
| "loss": 1.1199, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.08, |
| "grad_norm": 53.71720886230469, |
| "learning_rate": 1.76e-05, |
| "loss": 0.9691, |
| "step": 520 |
| }, |
| { |
| "epoch": 2.12, |
| "grad_norm": 62.33308792114258, |
| "learning_rate": 1.751111111111111e-05, |
| "loss": 1.0077, |
| "step": 530 |
| }, |
| { |
| "epoch": 2.16, |
| "grad_norm": 33.90275192260742, |
| "learning_rate": 1.7422222222222222e-05, |
| "loss": 1.0222, |
| "step": 540 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 71.48577880859375, |
| "learning_rate": 1.7333333333333336e-05, |
| "loss": 1.1158, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.24, |
| "grad_norm": 25.986026763916016, |
| "learning_rate": 1.7244444444444446e-05, |
| "loss": 0.9958, |
| "step": 560 |
| }, |
| { |
| "epoch": 2.2800000000000002, |
| "grad_norm": 47.359107971191406, |
| "learning_rate": 1.7155555555555557e-05, |
| "loss": 1.0862, |
| "step": 570 |
| }, |
| { |
| "epoch": 2.32, |
| "grad_norm": 40.83256530761719, |
| "learning_rate": 1.706666666666667e-05, |
| "loss": 1.0912, |
| "step": 580 |
| }, |
| { |
| "epoch": 2.36, |
| "grad_norm": 63.868675231933594, |
| "learning_rate": 1.697777777777778e-05, |
| "loss": 1.1017, |
| "step": 590 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 45.01089859008789, |
| "learning_rate": 1.688888888888889e-05, |
| "loss": 1.0942, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.44, |
| "grad_norm": 46.86573791503906, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 1.0188, |
| "step": 610 |
| }, |
| { |
| "epoch": 2.48, |
| "grad_norm": 59.64995574951172, |
| "learning_rate": 1.6711111111111112e-05, |
| "loss": 1.035, |
| "step": 620 |
| }, |
| { |
| "epoch": 2.52, |
| "grad_norm": 33.47834014892578, |
| "learning_rate": 1.6622222222222223e-05, |
| "loss": 0.9173, |
| "step": 630 |
| }, |
| { |
| "epoch": 2.56, |
| "grad_norm": 59.513633728027344, |
| "learning_rate": 1.6533333333333333e-05, |
| "loss": 1.0721, |
| "step": 640 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 33.897315979003906, |
| "learning_rate": 1.6444444444444444e-05, |
| "loss": 1.0167, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.64, |
| "grad_norm": 55.43059158325195, |
| "learning_rate": 1.6355555555555557e-05, |
| "loss": 1.0183, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.68, |
| "grad_norm": 36.83810043334961, |
| "learning_rate": 1.6266666666666668e-05, |
| "loss": 1.0661, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.7199999999999998, |
| "grad_norm": 27.871374130249023, |
| "learning_rate": 1.617777777777778e-05, |
| "loss": 0.986, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.76, |
| "grad_norm": 26.579404830932617, |
| "learning_rate": 1.608888888888889e-05, |
| "loss": 1.0217, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 23.805009841918945, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.015, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.84, |
| "grad_norm": 35.254974365234375, |
| "learning_rate": 1.5911111111111113e-05, |
| "loss": 1.0762, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.88, |
| "grad_norm": 20.483610153198242, |
| "learning_rate": 1.5822222222222224e-05, |
| "loss": 1.0583, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.92, |
| "grad_norm": 26.34144401550293, |
| "learning_rate": 1.5733333333333334e-05, |
| "loss": 1.1008, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 54.002681732177734, |
| "learning_rate": 1.5644444444444448e-05, |
| "loss": 0.9295, |
| "step": 740 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 36.5385627746582, |
| "learning_rate": 1.555555555555556e-05, |
| "loss": 1.0673, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.51, |
| "eval_f1": 0.4777248337252371, |
| "eval_loss": 1.1951327323913574, |
| "eval_runtime": 12.1837, |
| "eval_samples_per_second": 41.038, |
| "eval_steps_per_second": 10.26, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.04, |
| "grad_norm": 58.73692321777344, |
| "learning_rate": 1.546666666666667e-05, |
| "loss": 0.9637, |
| "step": 760 |
| }, |
| { |
| "epoch": 3.08, |
| "grad_norm": 18.000825881958008, |
| "learning_rate": 1.537777777777778e-05, |
| "loss": 0.9251, |
| "step": 770 |
| }, |
| { |
| "epoch": 3.12, |
| "grad_norm": 93.39592742919922, |
| "learning_rate": 1.528888888888889e-05, |
| "loss": 1.0542, |
| "step": 780 |
| }, |
| { |
| "epoch": 3.16, |
| "grad_norm": 41.7457389831543, |
| "learning_rate": 1.5200000000000002e-05, |
| "loss": 0.9525, |
| "step": 790 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 25.752269744873047, |
| "learning_rate": 1.5111111111111112e-05, |
| "loss": 0.8786, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.24, |
| "grad_norm": 58.843475341796875, |
| "learning_rate": 1.5022222222222223e-05, |
| "loss": 1.015, |
| "step": 810 |
| }, |
| { |
| "epoch": 3.2800000000000002, |
| "grad_norm": 21.79439353942871, |
| "learning_rate": 1.4933333333333335e-05, |
| "loss": 0.9858, |
| "step": 820 |
| }, |
| { |
| "epoch": 3.32, |
| "grad_norm": 29.008590698242188, |
| "learning_rate": 1.4844444444444445e-05, |
| "loss": 0.9522, |
| "step": 830 |
| }, |
| { |
| "epoch": 3.36, |
| "grad_norm": 25.020465850830078, |
| "learning_rate": 1.4755555555555556e-05, |
| "loss": 1.0351, |
| "step": 840 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 30.38283920288086, |
| "learning_rate": 1.4666666666666666e-05, |
| "loss": 1.0174, |
| "step": 850 |
| }, |
| { |
| "epoch": 3.44, |
| "grad_norm": 21.29317855834961, |
| "learning_rate": 1.457777777777778e-05, |
| "loss": 1.0674, |
| "step": 860 |
| }, |
| { |
| "epoch": 3.48, |
| "grad_norm": 50.27965545654297, |
| "learning_rate": 1.448888888888889e-05, |
| "loss": 1.0266, |
| "step": 870 |
| }, |
| { |
| "epoch": 3.52, |
| "grad_norm": 66.33875274658203, |
| "learning_rate": 1.4400000000000001e-05, |
| "loss": 1.001, |
| "step": 880 |
| }, |
| { |
| "epoch": 3.56, |
| "grad_norm": 34.711116790771484, |
| "learning_rate": 1.4311111111111111e-05, |
| "loss": 0.9511, |
| "step": 890 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 50.2099494934082, |
| "learning_rate": 1.4222222222222224e-05, |
| "loss": 0.9778, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.64, |
| "grad_norm": 20.47673988342285, |
| "learning_rate": 1.4133333333333334e-05, |
| "loss": 0.8044, |
| "step": 910 |
| }, |
| { |
| "epoch": 3.68, |
| "grad_norm": 27.520601272583008, |
| "learning_rate": 1.4044444444444445e-05, |
| "loss": 0.8282, |
| "step": 920 |
| }, |
| { |
| "epoch": 3.7199999999999998, |
| "grad_norm": 30.060382843017578, |
| "learning_rate": 1.3955555555555558e-05, |
| "loss": 0.6744, |
| "step": 930 |
| }, |
| { |
| "epoch": 3.76, |
| "grad_norm": 51.914154052734375, |
| "learning_rate": 1.3866666666666669e-05, |
| "loss": 0.8913, |
| "step": 940 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 32.7239990234375, |
| "learning_rate": 1.377777777777778e-05, |
| "loss": 0.9128, |
| "step": 950 |
| }, |
| { |
| "epoch": 3.84, |
| "grad_norm": 40.4760856628418, |
| "learning_rate": 1.368888888888889e-05, |
| "loss": 0.8142, |
| "step": 960 |
| }, |
| { |
| "epoch": 3.88, |
| "grad_norm": 49.8121223449707, |
| "learning_rate": 1.3600000000000002e-05, |
| "loss": 0.8092, |
| "step": 970 |
| }, |
| { |
| "epoch": 3.92, |
| "grad_norm": 35.05157470703125, |
| "learning_rate": 1.3511111111111112e-05, |
| "loss": 0.7544, |
| "step": 980 |
| }, |
| { |
| "epoch": 3.96, |
| "grad_norm": 46.630287170410156, |
| "learning_rate": 1.3422222222222223e-05, |
| "loss": 1.1021, |
| "step": 990 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 20.62359046936035, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.9863, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.622, |
| "eval_f1": 0.6315847689471261, |
| "eval_loss": 0.8479958176612854, |
| "eval_runtime": 12.0373, |
| "eval_samples_per_second": 41.537, |
| "eval_steps_per_second": 10.384, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.04, |
| "grad_norm": 33.65226364135742, |
| "learning_rate": 1.3244444444444447e-05, |
| "loss": 0.9395, |
| "step": 1010 |
| }, |
| { |
| "epoch": 4.08, |
| "grad_norm": 21.537878036499023, |
| "learning_rate": 1.3155555555555558e-05, |
| "loss": 0.7315, |
| "step": 1020 |
| }, |
| { |
| "epoch": 4.12, |
| "grad_norm": 72.42523956298828, |
| "learning_rate": 1.3066666666666668e-05, |
| "loss": 0.9017, |
| "step": 1030 |
| }, |
| { |
| "epoch": 4.16, |
| "grad_norm": 41.7869873046875, |
| "learning_rate": 1.2977777777777779e-05, |
| "loss": 0.9716, |
| "step": 1040 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 52.05732727050781, |
| "learning_rate": 1.288888888888889e-05, |
| "loss": 0.8553, |
| "step": 1050 |
| }, |
| { |
| "epoch": 4.24, |
| "grad_norm": 45.54288864135742, |
| "learning_rate": 1.2800000000000001e-05, |
| "loss": 0.8538, |
| "step": 1060 |
| }, |
| { |
| "epoch": 4.28, |
| "grad_norm": 37.879661560058594, |
| "learning_rate": 1.2711111111111112e-05, |
| "loss": 0.8716, |
| "step": 1070 |
| }, |
| { |
| "epoch": 4.32, |
| "grad_norm": 42.977272033691406, |
| "learning_rate": 1.2622222222222222e-05, |
| "loss": 0.8166, |
| "step": 1080 |
| }, |
| { |
| "epoch": 4.36, |
| "grad_norm": 36.236854553222656, |
| "learning_rate": 1.2533333333333336e-05, |
| "loss": 0.7672, |
| "step": 1090 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 46.707763671875, |
| "learning_rate": 1.2444444444444446e-05, |
| "loss": 0.7979, |
| "step": 1100 |
| }, |
| { |
| "epoch": 4.44, |
| "grad_norm": 28.657617568969727, |
| "learning_rate": 1.2355555555555557e-05, |
| "loss": 0.7771, |
| "step": 1110 |
| }, |
| { |
| "epoch": 4.48, |
| "grad_norm": 54.733009338378906, |
| "learning_rate": 1.2266666666666667e-05, |
| "loss": 0.8463, |
| "step": 1120 |
| }, |
| { |
| "epoch": 4.52, |
| "grad_norm": 49.474613189697266, |
| "learning_rate": 1.217777777777778e-05, |
| "loss": 0.759, |
| "step": 1130 |
| }, |
| { |
| "epoch": 4.5600000000000005, |
| "grad_norm": 31.721797943115234, |
| "learning_rate": 1.208888888888889e-05, |
| "loss": 0.8087, |
| "step": 1140 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 32.5080680847168, |
| "learning_rate": 1.2e-05, |
| "loss": 0.8189, |
| "step": 1150 |
| }, |
| { |
| "epoch": 4.64, |
| "grad_norm": 29.60678482055664, |
| "learning_rate": 1.191111111111111e-05, |
| "loss": 0.7827, |
| "step": 1160 |
| }, |
| { |
| "epoch": 4.68, |
| "grad_norm": 27.952041625976562, |
| "learning_rate": 1.1822222222222225e-05, |
| "loss": 0.7894, |
| "step": 1170 |
| }, |
| { |
| "epoch": 4.72, |
| "grad_norm": 39.61127471923828, |
| "learning_rate": 1.1733333333333335e-05, |
| "loss": 0.8418, |
| "step": 1180 |
| }, |
| { |
| "epoch": 4.76, |
| "grad_norm": 29.20393180847168, |
| "learning_rate": 1.1644444444444446e-05, |
| "loss": 0.6856, |
| "step": 1190 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 40.39738082885742, |
| "learning_rate": 1.1555555555555556e-05, |
| "loss": 0.7397, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.84, |
| "grad_norm": 30.21686363220215, |
| "learning_rate": 1.1466666666666668e-05, |
| "loss": 0.8024, |
| "step": 1210 |
| }, |
| { |
| "epoch": 4.88, |
| "grad_norm": 41.96994400024414, |
| "learning_rate": 1.1377777777777779e-05, |
| "loss": 0.8058, |
| "step": 1220 |
| }, |
| { |
| "epoch": 4.92, |
| "grad_norm": 24.6497802734375, |
| "learning_rate": 1.1288888888888889e-05, |
| "loss": 0.7722, |
| "step": 1230 |
| }, |
| { |
| "epoch": 4.96, |
| "grad_norm": 61.19656753540039, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 0.8071, |
| "step": 1240 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 28.335107803344727, |
| "learning_rate": 1.1111111111111113e-05, |
| "loss": 0.8241, |
| "step": 1250 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.706, |
| "eval_f1": 0.7049416744459689, |
| "eval_loss": 0.7028206586837769, |
| "eval_runtime": 12.1037, |
| "eval_samples_per_second": 41.31, |
| "eval_steps_per_second": 10.327, |
| "step": 1250 |
| }, |
| { |
| "epoch": 5.04, |
| "grad_norm": 35.011070251464844, |
| "learning_rate": 1.1022222222222224e-05, |
| "loss": 0.6987, |
| "step": 1260 |
| }, |
| { |
| "epoch": 5.08, |
| "grad_norm": 69.44827270507812, |
| "learning_rate": 1.0933333333333334e-05, |
| "loss": 0.7744, |
| "step": 1270 |
| }, |
| { |
| "epoch": 5.12, |
| "grad_norm": 56.46673583984375, |
| "learning_rate": 1.0844444444444446e-05, |
| "loss": 0.7145, |
| "step": 1280 |
| }, |
| { |
| "epoch": 5.16, |
| "grad_norm": 31.053302764892578, |
| "learning_rate": 1.0755555555555557e-05, |
| "loss": 0.8252, |
| "step": 1290 |
| }, |
| { |
| "epoch": 5.2, |
| "grad_norm": 43.00981140136719, |
| "learning_rate": 1.0666666666666667e-05, |
| "loss": 0.6484, |
| "step": 1300 |
| }, |
| { |
| "epoch": 5.24, |
| "grad_norm": 19.58731460571289, |
| "learning_rate": 1.0577777777777778e-05, |
| "loss": 0.671, |
| "step": 1310 |
| }, |
| { |
| "epoch": 5.28, |
| "grad_norm": 61.77705001831055, |
| "learning_rate": 1.048888888888889e-05, |
| "loss": 0.6228, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.32, |
| "grad_norm": 39.46787643432617, |
| "learning_rate": 1.04e-05, |
| "loss": 0.604, |
| "step": 1330 |
| }, |
| { |
| "epoch": 5.36, |
| "grad_norm": 37.76319885253906, |
| "learning_rate": 1.0311111111111113e-05, |
| "loss": 0.7439, |
| "step": 1340 |
| }, |
| { |
| "epoch": 5.4, |
| "grad_norm": 86.55498504638672, |
| "learning_rate": 1.0222222222222223e-05, |
| "loss": 0.6356, |
| "step": 1350 |
| }, |
| { |
| "epoch": 5.44, |
| "grad_norm": 50.998966217041016, |
| "learning_rate": 1.0133333333333335e-05, |
| "loss": 0.8106, |
| "step": 1360 |
| }, |
| { |
| "epoch": 5.48, |
| "grad_norm": 41.33028793334961, |
| "learning_rate": 1.0044444444444446e-05, |
| "loss": 0.6859, |
| "step": 1370 |
| }, |
| { |
| "epoch": 5.52, |
| "grad_norm": 27.738656997680664, |
| "learning_rate": 9.955555555555556e-06, |
| "loss": 0.6726, |
| "step": 1380 |
| }, |
| { |
| "epoch": 5.5600000000000005, |
| "grad_norm": 65.7751235961914, |
| "learning_rate": 9.866666666666668e-06, |
| "loss": 0.7502, |
| "step": 1390 |
| }, |
| { |
| "epoch": 5.6, |
| "grad_norm": 35.19927978515625, |
| "learning_rate": 9.777777777777779e-06, |
| "loss": 0.8105, |
| "step": 1400 |
| }, |
| { |
| "epoch": 5.64, |
| "grad_norm": 49.49024200439453, |
| "learning_rate": 9.688888888888889e-06, |
| "loss": 0.6238, |
| "step": 1410 |
| }, |
| { |
| "epoch": 5.68, |
| "grad_norm": 69.92552947998047, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 0.6782, |
| "step": 1420 |
| }, |
| { |
| "epoch": 5.72, |
| "grad_norm": 35.6678352355957, |
| "learning_rate": 9.511111111111112e-06, |
| "loss": 0.8168, |
| "step": 1430 |
| }, |
| { |
| "epoch": 5.76, |
| "grad_norm": 26.826770782470703, |
| "learning_rate": 9.422222222222222e-06, |
| "loss": 0.6466, |
| "step": 1440 |
| }, |
| { |
| "epoch": 5.8, |
| "grad_norm": 44.43244934082031, |
| "learning_rate": 9.333333333333334e-06, |
| "loss": 0.7103, |
| "step": 1450 |
| }, |
| { |
| "epoch": 5.84, |
| "grad_norm": 29.49979591369629, |
| "learning_rate": 9.244444444444445e-06, |
| "loss": 0.7882, |
| "step": 1460 |
| }, |
| { |
| "epoch": 5.88, |
| "grad_norm": 68.5856704711914, |
| "learning_rate": 9.155555555555557e-06, |
| "loss": 0.7308, |
| "step": 1470 |
| }, |
| { |
| "epoch": 5.92, |
| "grad_norm": 59.66977310180664, |
| "learning_rate": 9.066666666666667e-06, |
| "loss": 0.6081, |
| "step": 1480 |
| }, |
| { |
| "epoch": 5.96, |
| "grad_norm": 44.2071418762207, |
| "learning_rate": 8.977777777777778e-06, |
| "loss": 0.6688, |
| "step": 1490 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 35.35416030883789, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 0.7208, |
| "step": 1500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.712, |
| "eval_f1": 0.6909848104243247, |
| "eval_loss": 0.7059077024459839, |
| "eval_runtime": 12.0866, |
| "eval_samples_per_second": 41.368, |
| "eval_steps_per_second": 10.342, |
| "step": 1500 |
| }, |
| { |
| "epoch": 6.04, |
| "grad_norm": 28.48759651184082, |
| "learning_rate": 8.8e-06, |
| "loss": 0.7302, |
| "step": 1510 |
| }, |
| { |
| "epoch": 6.08, |
| "grad_norm": 24.124494552612305, |
| "learning_rate": 8.711111111111111e-06, |
| "loss": 0.5639, |
| "step": 1520 |
| }, |
| { |
| "epoch": 6.12, |
| "grad_norm": 46.50981521606445, |
| "learning_rate": 8.622222222222223e-06, |
| "loss": 0.7587, |
| "step": 1530 |
| }, |
| { |
| "epoch": 6.16, |
| "grad_norm": 31.084308624267578, |
| "learning_rate": 8.533333333333335e-06, |
| "loss": 0.662, |
| "step": 1540 |
| }, |
| { |
| "epoch": 6.2, |
| "grad_norm": 45.10621643066406, |
| "learning_rate": 8.444444444444446e-06, |
| "loss": 0.7906, |
| "step": 1550 |
| }, |
| { |
| "epoch": 6.24, |
| "grad_norm": 34.53160095214844, |
| "learning_rate": 8.355555555555556e-06, |
| "loss": 0.6335, |
| "step": 1560 |
| }, |
| { |
| "epoch": 6.28, |
| "grad_norm": 50.21031951904297, |
| "learning_rate": 8.266666666666667e-06, |
| "loss": 0.6376, |
| "step": 1570 |
| }, |
| { |
| "epoch": 6.32, |
| "grad_norm": 40.00431823730469, |
| "learning_rate": 8.177777777777779e-06, |
| "loss": 0.5273, |
| "step": 1580 |
| }, |
| { |
| "epoch": 6.36, |
| "grad_norm": 44.98348617553711, |
| "learning_rate": 8.08888888888889e-06, |
| "loss": 0.6106, |
| "step": 1590 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 77.24087524414062, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.5021, |
| "step": 1600 |
| }, |
| { |
| "epoch": 6.44, |
| "grad_norm": 43.97039031982422, |
| "learning_rate": 7.911111111111112e-06, |
| "loss": 0.721, |
| "step": 1610 |
| }, |
| { |
| "epoch": 6.48, |
| "grad_norm": 63.44462203979492, |
| "learning_rate": 7.822222222222224e-06, |
| "loss": 0.7287, |
| "step": 1620 |
| }, |
| { |
| "epoch": 6.52, |
| "grad_norm": 34.81692123413086, |
| "learning_rate": 7.733333333333334e-06, |
| "loss": 0.6739, |
| "step": 1630 |
| }, |
| { |
| "epoch": 6.5600000000000005, |
| "grad_norm": 60.13438034057617, |
| "learning_rate": 7.644444444444445e-06, |
| "loss": 0.5785, |
| "step": 1640 |
| }, |
| { |
| "epoch": 6.6, |
| "grad_norm": 55.27112579345703, |
| "learning_rate": 7.555555555555556e-06, |
| "loss": 0.5858, |
| "step": 1650 |
| }, |
| { |
| "epoch": 6.64, |
| "grad_norm": 35.41032028198242, |
| "learning_rate": 7.4666666666666675e-06, |
| "loss": 0.5187, |
| "step": 1660 |
| }, |
| { |
| "epoch": 6.68, |
| "grad_norm": 43.339637756347656, |
| "learning_rate": 7.377777777777778e-06, |
| "loss": 0.6068, |
| "step": 1670 |
| }, |
| { |
| "epoch": 6.72, |
| "grad_norm": 47.03825759887695, |
| "learning_rate": 7.28888888888889e-06, |
| "loss": 0.627, |
| "step": 1680 |
| }, |
| { |
| "epoch": 6.76, |
| "grad_norm": 65.18019104003906, |
| "learning_rate": 7.2000000000000005e-06, |
| "loss": 0.4992, |
| "step": 1690 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 31.7502384185791, |
| "learning_rate": 7.111111111111112e-06, |
| "loss": 0.4831, |
| "step": 1700 |
| }, |
| { |
| "epoch": 6.84, |
| "grad_norm": 58.455284118652344, |
| "learning_rate": 7.022222222222222e-06, |
| "loss": 0.6985, |
| "step": 1710 |
| }, |
| { |
| "epoch": 6.88, |
| "grad_norm": 39.89744186401367, |
| "learning_rate": 6.9333333333333344e-06, |
| "loss": 0.6184, |
| "step": 1720 |
| }, |
| { |
| "epoch": 6.92, |
| "grad_norm": 47.30400466918945, |
| "learning_rate": 6.844444444444445e-06, |
| "loss": 0.544, |
| "step": 1730 |
| }, |
| { |
| "epoch": 6.96, |
| "grad_norm": 35.126983642578125, |
| "learning_rate": 6.755555555555556e-06, |
| "loss": 0.6523, |
| "step": 1740 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 34.56584930419922, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.5563, |
| "step": 1750 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.782, |
| "eval_f1": 0.7813244154636514, |
| "eval_loss": 0.5727885365486145, |
| "eval_runtime": 12.134, |
| "eval_samples_per_second": 41.206, |
| "eval_steps_per_second": 10.302, |
| "step": 1750 |
| }, |
| { |
| "epoch": 7.04, |
| "grad_norm": 41.27728271484375, |
| "learning_rate": 6.577777777777779e-06, |
| "loss": 0.5345, |
| "step": 1760 |
| }, |
| { |
| "epoch": 7.08, |
| "grad_norm": 45.002113342285156, |
| "learning_rate": 6.488888888888889e-06, |
| "loss": 0.4454, |
| "step": 1770 |
| }, |
| { |
| "epoch": 7.12, |
| "grad_norm": 54.88307571411133, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 0.4505, |
| "step": 1780 |
| }, |
| { |
| "epoch": 7.16, |
| "grad_norm": 61.16643524169922, |
| "learning_rate": 6.311111111111111e-06, |
| "loss": 0.4595, |
| "step": 1790 |
| }, |
| { |
| "epoch": 7.2, |
| "grad_norm": 40.985477447509766, |
| "learning_rate": 6.222222222222223e-06, |
| "loss": 0.394, |
| "step": 1800 |
| }, |
| { |
| "epoch": 7.24, |
| "grad_norm": 47.477718353271484, |
| "learning_rate": 6.133333333333334e-06, |
| "loss": 0.5319, |
| "step": 1810 |
| }, |
| { |
| "epoch": 7.28, |
| "grad_norm": 36.49656677246094, |
| "learning_rate": 6.044444444444445e-06, |
| "loss": 0.4503, |
| "step": 1820 |
| }, |
| { |
| "epoch": 7.32, |
| "grad_norm": 58.11835479736328, |
| "learning_rate": 5.955555555555555e-06, |
| "loss": 0.4832, |
| "step": 1830 |
| }, |
| { |
| "epoch": 7.36, |
| "grad_norm": 12.562129020690918, |
| "learning_rate": 5.8666666666666675e-06, |
| "loss": 0.5398, |
| "step": 1840 |
| }, |
| { |
| "epoch": 7.4, |
| "grad_norm": 55.433841705322266, |
| "learning_rate": 5.777777777777778e-06, |
| "loss": 0.4846, |
| "step": 1850 |
| }, |
| { |
| "epoch": 7.44, |
| "grad_norm": 45.45614242553711, |
| "learning_rate": 5.688888888888889e-06, |
| "loss": 0.5762, |
| "step": 1860 |
| }, |
| { |
| "epoch": 7.48, |
| "grad_norm": 56.408843994140625, |
| "learning_rate": 5.600000000000001e-06, |
| "loss": 0.5523, |
| "step": 1870 |
| }, |
| { |
| "epoch": 7.52, |
| "grad_norm": 51.10346984863281, |
| "learning_rate": 5.511111111111112e-06, |
| "loss": 0.5049, |
| "step": 1880 |
| }, |
| { |
| "epoch": 7.5600000000000005, |
| "grad_norm": 66.00965881347656, |
| "learning_rate": 5.422222222222223e-06, |
| "loss": 0.4715, |
| "step": 1890 |
| }, |
| { |
| "epoch": 7.6, |
| "grad_norm": 76.69068908691406, |
| "learning_rate": 5.333333333333334e-06, |
| "loss": 0.5237, |
| "step": 1900 |
| }, |
| { |
| "epoch": 7.64, |
| "grad_norm": 57.46429443359375, |
| "learning_rate": 5.244444444444445e-06, |
| "loss": 0.4419, |
| "step": 1910 |
| }, |
| { |
| "epoch": 7.68, |
| "grad_norm": 47.936641693115234, |
| "learning_rate": 5.155555555555556e-06, |
| "loss": 0.6135, |
| "step": 1920 |
| }, |
| { |
| "epoch": 7.72, |
| "grad_norm": 56.27345275878906, |
| "learning_rate": 5.0666666666666676e-06, |
| "loss": 0.4293, |
| "step": 1930 |
| }, |
| { |
| "epoch": 7.76, |
| "grad_norm": 66.12334442138672, |
| "learning_rate": 4.977777777777778e-06, |
| "loss": 0.5966, |
| "step": 1940 |
| }, |
| { |
| "epoch": 7.8, |
| "grad_norm": 52.354122161865234, |
| "learning_rate": 4.888888888888889e-06, |
| "loss": 0.5202, |
| "step": 1950 |
| }, |
| { |
| "epoch": 7.84, |
| "grad_norm": 34.89662170410156, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 0.4621, |
| "step": 1960 |
| }, |
| { |
| "epoch": 7.88, |
| "grad_norm": 67.30014038085938, |
| "learning_rate": 4.711111111111111e-06, |
| "loss": 0.4718, |
| "step": 1970 |
| }, |
| { |
| "epoch": 7.92, |
| "grad_norm": 59.92790603637695, |
| "learning_rate": 4.622222222222222e-06, |
| "loss": 0.4111, |
| "step": 1980 |
| }, |
| { |
| "epoch": 7.96, |
| "grad_norm": 60.730255126953125, |
| "learning_rate": 4.533333333333334e-06, |
| "loss": 0.4406, |
| "step": 1990 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 25.637128829956055, |
| "learning_rate": 4.444444444444444e-06, |
| "loss": 0.3988, |
| "step": 2000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.826, |
| "eval_f1": 0.8239121231432465, |
| "eval_loss": 0.5472010970115662, |
| "eval_runtime": 12.1827, |
| "eval_samples_per_second": 41.042, |
| "eval_steps_per_second": 10.26, |
| "step": 2000 |
| }, |
| { |
| "epoch": 8.04, |
| "grad_norm": 36.69926834106445, |
| "learning_rate": 4.3555555555555555e-06, |
| "loss": 0.4001, |
| "step": 2010 |
| }, |
| { |
| "epoch": 8.08, |
| "grad_norm": 40.46434783935547, |
| "learning_rate": 4.266666666666668e-06, |
| "loss": 0.3608, |
| "step": 2020 |
| }, |
| { |
| "epoch": 8.12, |
| "grad_norm": 41.12105178833008, |
| "learning_rate": 4.177777777777778e-06, |
| "loss": 0.3893, |
| "step": 2030 |
| }, |
| { |
| "epoch": 8.16, |
| "grad_norm": 84.14956665039062, |
| "learning_rate": 4.088888888888889e-06, |
| "loss": 0.4152, |
| "step": 2040 |
| }, |
| { |
| "epoch": 8.2, |
| "grad_norm": 49.22280502319336, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.4308, |
| "step": 2050 |
| }, |
| { |
| "epoch": 8.24, |
| "grad_norm": 45.23503112792969, |
| "learning_rate": 3.911111111111112e-06, |
| "loss": 0.3673, |
| "step": 2060 |
| }, |
| { |
| "epoch": 8.28, |
| "grad_norm": 47.49519348144531, |
| "learning_rate": 3.8222222222222224e-06, |
| "loss": 0.3846, |
| "step": 2070 |
| }, |
| { |
| "epoch": 8.32, |
| "grad_norm": 68.24031829833984, |
| "learning_rate": 3.7333333333333337e-06, |
| "loss": 0.3908, |
| "step": 2080 |
| }, |
| { |
| "epoch": 8.36, |
| "grad_norm": 23.122114181518555, |
| "learning_rate": 3.644444444444445e-06, |
| "loss": 0.3358, |
| "step": 2090 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 59.9205436706543, |
| "learning_rate": 3.555555555555556e-06, |
| "loss": 0.3517, |
| "step": 2100 |
| }, |
| { |
| "epoch": 8.44, |
| "grad_norm": 38.14185333251953, |
| "learning_rate": 3.4666666666666672e-06, |
| "loss": 0.4558, |
| "step": 2110 |
| }, |
| { |
| "epoch": 8.48, |
| "grad_norm": 50.6385498046875, |
| "learning_rate": 3.377777777777778e-06, |
| "loss": 0.3912, |
| "step": 2120 |
| }, |
| { |
| "epoch": 8.52, |
| "grad_norm": 30.214555740356445, |
| "learning_rate": 3.2888888888888894e-06, |
| "loss": 0.4873, |
| "step": 2130 |
| }, |
| { |
| "epoch": 8.56, |
| "grad_norm": 53.54391860961914, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 0.3847, |
| "step": 2140 |
| }, |
| { |
| "epoch": 8.6, |
| "grad_norm": 29.186870574951172, |
| "learning_rate": 3.1111111111111116e-06, |
| "loss": 0.3381, |
| "step": 2150 |
| }, |
| { |
| "epoch": 8.64, |
| "grad_norm": 31.920259475708008, |
| "learning_rate": 3.0222222222222225e-06, |
| "loss": 0.3559, |
| "step": 2160 |
| }, |
| { |
| "epoch": 8.68, |
| "grad_norm": 86.72305297851562, |
| "learning_rate": 2.9333333333333338e-06, |
| "loss": 0.3753, |
| "step": 2170 |
| }, |
| { |
| "epoch": 8.72, |
| "grad_norm": 68.44404602050781, |
| "learning_rate": 2.8444444444444446e-06, |
| "loss": 0.4498, |
| "step": 2180 |
| }, |
| { |
| "epoch": 8.76, |
| "grad_norm": 29.52780532836914, |
| "learning_rate": 2.755555555555556e-06, |
| "loss": 0.4367, |
| "step": 2190 |
| }, |
| { |
| "epoch": 8.8, |
| "grad_norm": 57.7866096496582, |
| "learning_rate": 2.666666666666667e-06, |
| "loss": 0.4172, |
| "step": 2200 |
| }, |
| { |
| "epoch": 8.84, |
| "grad_norm": 21.049448013305664, |
| "learning_rate": 2.577777777777778e-06, |
| "loss": 0.3221, |
| "step": 2210 |
| }, |
| { |
| "epoch": 8.88, |
| "grad_norm": 96.43756103515625, |
| "learning_rate": 2.488888888888889e-06, |
| "loss": 0.3575, |
| "step": 2220 |
| }, |
| { |
| "epoch": 8.92, |
| "grad_norm": 42.55648422241211, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.3055, |
| "step": 2230 |
| }, |
| { |
| "epoch": 8.96, |
| "grad_norm": 44.407386779785156, |
| "learning_rate": 2.311111111111111e-06, |
| "loss": 0.3991, |
| "step": 2240 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 23.83012580871582, |
| "learning_rate": 2.222222222222222e-06, |
| "loss": 0.4643, |
| "step": 2250 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.85, |
| "eval_f1": 0.8502768157768157, |
| "eval_loss": 0.47364383935928345, |
| "eval_runtime": 12.1944, |
| "eval_samples_per_second": 41.002, |
| "eval_steps_per_second": 10.251, |
| "step": 2250 |
| }, |
| { |
| "epoch": 9.04, |
| "grad_norm": 33.42547607421875, |
| "learning_rate": 2.133333333333334e-06, |
| "loss": 0.3178, |
| "step": 2260 |
| }, |
| { |
| "epoch": 9.08, |
| "grad_norm": 33.77496337890625, |
| "learning_rate": 2.0444444444444447e-06, |
| "loss": 0.2743, |
| "step": 2270 |
| }, |
| { |
| "epoch": 9.12, |
| "grad_norm": 73.40355682373047, |
| "learning_rate": 1.955555555555556e-06, |
| "loss": 0.4977, |
| "step": 2280 |
| }, |
| { |
| "epoch": 9.16, |
| "grad_norm": 51.72673034667969, |
| "learning_rate": 1.8666666666666669e-06, |
| "loss": 0.294, |
| "step": 2290 |
| }, |
| { |
| "epoch": 9.2, |
| "grad_norm": 25.48830795288086, |
| "learning_rate": 1.777777777777778e-06, |
| "loss": 0.2909, |
| "step": 2300 |
| }, |
| { |
| "epoch": 9.24, |
| "grad_norm": 32.16721725463867, |
| "learning_rate": 1.688888888888889e-06, |
| "loss": 0.3173, |
| "step": 2310 |
| }, |
| { |
| "epoch": 9.28, |
| "grad_norm": 31.670467376708984, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 0.3557, |
| "step": 2320 |
| }, |
| { |
| "epoch": 9.32, |
| "grad_norm": 26.01582145690918, |
| "learning_rate": 1.5111111111111112e-06, |
| "loss": 0.2405, |
| "step": 2330 |
| }, |
| { |
| "epoch": 9.36, |
| "grad_norm": 27.004608154296875, |
| "learning_rate": 1.4222222222222223e-06, |
| "loss": 0.3557, |
| "step": 2340 |
| }, |
| { |
| "epoch": 9.4, |
| "grad_norm": 57.54291915893555, |
| "learning_rate": 1.3333333333333334e-06, |
| "loss": 0.411, |
| "step": 2350 |
| }, |
| { |
| "epoch": 9.44, |
| "grad_norm": 57.62574005126953, |
| "learning_rate": 1.2444444444444445e-06, |
| "loss": 0.3942, |
| "step": 2360 |
| }, |
| { |
| "epoch": 9.48, |
| "grad_norm": 60.00413131713867, |
| "learning_rate": 1.1555555555555556e-06, |
| "loss": 0.2951, |
| "step": 2370 |
| }, |
| { |
| "epoch": 9.52, |
| "grad_norm": 54.96599197387695, |
| "learning_rate": 1.066666666666667e-06, |
| "loss": 0.368, |
| "step": 2380 |
| }, |
| { |
| "epoch": 9.56, |
| "grad_norm": 22.52992057800293, |
| "learning_rate": 9.77777777777778e-07, |
| "loss": 0.4472, |
| "step": 2390 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 42.04111862182617, |
| "learning_rate": 8.88888888888889e-07, |
| "loss": 0.3283, |
| "step": 2400 |
| }, |
| { |
| "epoch": 9.64, |
| "grad_norm": 72.67633056640625, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 0.4713, |
| "step": 2410 |
| }, |
| { |
| "epoch": 9.68, |
| "grad_norm": 32.135921478271484, |
| "learning_rate": 7.111111111111112e-07, |
| "loss": 0.2854, |
| "step": 2420 |
| }, |
| { |
| "epoch": 9.72, |
| "grad_norm": 95.6978759765625, |
| "learning_rate": 6.222222222222223e-07, |
| "loss": 0.3126, |
| "step": 2430 |
| }, |
| { |
| "epoch": 9.76, |
| "grad_norm": 26.696413040161133, |
| "learning_rate": 5.333333333333335e-07, |
| "loss": 0.2417, |
| "step": 2440 |
| }, |
| { |
| "epoch": 9.8, |
| "grad_norm": 32.3356819152832, |
| "learning_rate": 4.444444444444445e-07, |
| "loss": 0.326, |
| "step": 2450 |
| }, |
| { |
| "epoch": 9.84, |
| "grad_norm": 51.74174499511719, |
| "learning_rate": 3.555555555555556e-07, |
| "loss": 0.3181, |
| "step": 2460 |
| }, |
| { |
| "epoch": 9.88, |
| "grad_norm": 44.073734283447266, |
| "learning_rate": 2.666666666666667e-07, |
| "loss": 0.2574, |
| "step": 2470 |
| }, |
| { |
| "epoch": 9.92, |
| "grad_norm": 48.75944519042969, |
| "learning_rate": 1.777777777777778e-07, |
| "loss": 0.3372, |
| "step": 2480 |
| }, |
| { |
| "epoch": 9.96, |
| "grad_norm": 35.41460037231445, |
| "learning_rate": 8.88888888888889e-08, |
| "loss": 0.2653, |
| "step": 2490 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 27.246013641357422, |
| "learning_rate": 0.0, |
| "loss": 0.2625, |
| "step": 2500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.88, |
| "eval_f1": 0.8802333980766498, |
| "eval_loss": 0.4214743971824646, |
| "eval_runtime": 12.0989, |
| "eval_samples_per_second": 41.326, |
| "eval_steps_per_second": 10.331, |
| "step": 2500 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 2500, |
| "total_flos": 4.0857422266368e+18, |
| "train_loss": 0.7867561736106873, |
| "train_runtime": 2885.7234, |
| "train_samples_per_second": 13.861, |
| "train_steps_per_second": 0.866 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.0857422266368e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
