| { | |
| "best_metric": 0.8855140186915887, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-cassava3/checkpoint-1064", | |
| "epoch": 9.994392523364485, | |
| "global_step": 1330, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.7593984962406014e-06, | |
| "loss": 1.5873, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.518796992481203e-06, | |
| "loss": 1.5448, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.1278195488721805e-05, | |
| "loss": 1.4433, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5037593984962406e-05, | |
| "loss": 1.2664, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.8796992481203007e-05, | |
| "loss": 1.1417, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.255639097744361e-05, | |
| "loss": 1.0343, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.9283, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.007518796992481e-05, | |
| "loss": 0.8431, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3834586466165414e-05, | |
| "loss": 0.764, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.759398496240601e-05, | |
| "loss": 0.7234, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.135338345864662e-05, | |
| "loss": 0.6497, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.511278195488722e-05, | |
| "loss": 0.6193, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.887218045112782e-05, | |
| "loss": 0.5624, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.8165887850467289, | |
| "eval_loss": 0.5866310596466064, | |
| "eval_runtime": 93.7262, | |
| "eval_samples_per_second": 45.665, | |
| "eval_steps_per_second": 1.43, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.6142, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.928989139515455e-05, | |
| "loss": 0.5625, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.887218045112782e-05, | |
| "loss": 0.5064, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.8454469507101085e-05, | |
| "loss": 0.5359, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.803675856307435e-05, | |
| "loss": 0.4852, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.4538, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.720133667502089e-05, | |
| "loss": 0.4947, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.4568, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.6365914786967416e-05, | |
| "loss": 0.4609, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.5948203842940684e-05, | |
| "loss": 0.4919, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.553049289891395e-05, | |
| "loss": 0.5054, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.511278195488722e-05, | |
| "loss": 0.4133, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.4695071010860486e-05, | |
| "loss": 0.4717, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.8691588785046729, | |
| "eval_loss": 0.4245365262031555, | |
| "eval_runtime": 92.5089, | |
| "eval_samples_per_second": 46.266, | |
| "eval_steps_per_second": 1.449, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.4277360066833754e-05, | |
| "loss": 0.4125, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.4693, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.344193817878028e-05, | |
| "loss": 0.444, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.302422723475355e-05, | |
| "loss": 0.376, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.260651629072682e-05, | |
| "loss": 0.3967, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.2188805346700084e-05, | |
| "loss": 0.4269, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 4.177109440267335e-05, | |
| "loss": 0.4132, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.135338345864662e-05, | |
| "loss": 0.4072, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.4125, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.051796157059315e-05, | |
| "loss": 0.4108, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.0100250626566415e-05, | |
| "loss": 0.4008, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.3809, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 3.926482873851295e-05, | |
| "loss": 0.4105, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8810747663551401, | |
| "eval_loss": 0.37081509828567505, | |
| "eval_runtime": 92.7737, | |
| "eval_samples_per_second": 46.134, | |
| "eval_steps_per_second": 1.444, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.884711779448622e-05, | |
| "loss": 0.4151, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.8429406850459485e-05, | |
| "loss": 0.3712, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.395, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.759398496240601e-05, | |
| "loss": 0.3889, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.717627401837928e-05, | |
| "loss": 0.343, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.675856307435255e-05, | |
| "loss": 0.3729, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 3.6340852130325816e-05, | |
| "loss": 0.4083, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.592314118629908e-05, | |
| "loss": 0.4003, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.5505430242272344e-05, | |
| "loss": 0.379, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.3461, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 3.467000835421888e-05, | |
| "loss": 0.3892, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 3.4252297410192146e-05, | |
| "loss": 0.4018, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 3.3834586466165414e-05, | |
| "loss": 0.4032, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.341687552213868e-05, | |
| "loss": 0.3753, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.8787383177570094, | |
| "eval_loss": 0.36458322405815125, | |
| "eval_runtime": 86.4304, | |
| "eval_samples_per_second": 49.52, | |
| "eval_steps_per_second": 1.55, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.299916457811195e-05, | |
| "loss": 0.3589, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 3.258145363408521e-05, | |
| "loss": 0.344, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.3571, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.3762, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 3.132832080200501e-05, | |
| "loss": 0.3885, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.091060985797828e-05, | |
| "loss": 0.3582, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 3.0492898913951544e-05, | |
| "loss": 0.333, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 3.007518796992481e-05, | |
| "loss": 0.3758, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.965747702589808e-05, | |
| "loss": 0.3531, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.3627, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.882205513784461e-05, | |
| "loss": 0.3575, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.8404344193817878e-05, | |
| "loss": 0.3805, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 2.7986633249791145e-05, | |
| "loss": 0.2997, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8780373831775701, | |
| "eval_loss": 0.36552494764328003, | |
| "eval_runtime": 85.8197, | |
| "eval_samples_per_second": 49.872, | |
| "eval_steps_per_second": 1.561, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.756892230576441e-05, | |
| "loss": 0.3479, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 2.7151211361737677e-05, | |
| "loss": 0.3436, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 2.6733500417710944e-05, | |
| "loss": 0.3158, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.312, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.5898078529657476e-05, | |
| "loss": 0.3412, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 2.5480367585630744e-05, | |
| "loss": 0.3333, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 2.506265664160401e-05, | |
| "loss": 0.3272, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 2.4644945697577275e-05, | |
| "loss": 0.3344, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 2.4227234753550543e-05, | |
| "loss": 0.3864, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.3322, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.3333, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 2.2974101921470342e-05, | |
| "loss": 0.3277, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.255639097744361e-05, | |
| "loss": 0.3176, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.8822429906542056, | |
| "eval_loss": 0.35449549555778503, | |
| "eval_runtime": 90.8772, | |
| "eval_samples_per_second": 47.097, | |
| "eval_steps_per_second": 1.475, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.2138680033416877e-05, | |
| "loss": 0.3596, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 2.172096908939014e-05, | |
| "loss": 0.2984, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 2.130325814536341e-05, | |
| "loss": 0.3512, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 2.0885547201336676e-05, | |
| "loss": 0.3356, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.3269, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 2.0050125313283208e-05, | |
| "loss": 0.2984, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.9632414369256475e-05, | |
| "loss": 0.3279, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 1.9214703425229743e-05, | |
| "loss": 0.2778, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 1.8796992481203007e-05, | |
| "loss": 0.3247, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 1.8379281537176274e-05, | |
| "loss": 0.3076, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.796157059314954e-05, | |
| "loss": 0.3283, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.2951, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 1.7126148705096073e-05, | |
| "loss": 0.3126, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.670843776106934e-05, | |
| "loss": 0.2849, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8850467289719626, | |
| "eval_loss": 0.3441033363342285, | |
| "eval_runtime": 85.0261, | |
| "eval_samples_per_second": 50.337, | |
| "eval_steps_per_second": 1.576, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.6290726817042605e-05, | |
| "loss": 0.3229, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.2997, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.545530492898914e-05, | |
| "loss": 0.2961, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 1.5037593984962406e-05, | |
| "loss": 0.3217, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.282, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.4202172096908939e-05, | |
| "loss": 0.2629, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 1.3784461152882205e-05, | |
| "loss": 0.3394, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.3366750208855472e-05, | |
| "loss": 0.3002, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.2949039264828738e-05, | |
| "loss": 0.3042, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.2531328320802006e-05, | |
| "loss": 0.2942, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.2113617376775271e-05, | |
| "loss": 0.3077, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.298, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.1278195488721805e-05, | |
| "loss": 0.2931, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.8855140186915887, | |
| "eval_loss": 0.3418597877025604, | |
| "eval_runtime": 84.489, | |
| "eval_samples_per_second": 50.657, | |
| "eval_steps_per_second": 1.586, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1.086048454469507e-05, | |
| "loss": 0.3204, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.0442773600668338e-05, | |
| "loss": 0.2924, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 1.0025062656641604e-05, | |
| "loss": 0.2871, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 9.607351712614871e-06, | |
| "loss": 0.2625, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 9.189640768588137e-06, | |
| "loss": 0.2914, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.2909, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 8.35421888053467e-06, | |
| "loss": 0.28, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.2703, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.518796992481203e-06, | |
| "loss": 0.3228, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 7.1010860484544695e-06, | |
| "loss": 0.3069, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 6.683375104427736e-06, | |
| "loss": 0.2699, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 6.265664160401003e-06, | |
| "loss": 0.281, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.27, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8848130841121495, | |
| "eval_loss": 0.341878741979599, | |
| "eval_runtime": 84.7924, | |
| "eval_samples_per_second": 50.476, | |
| "eval_steps_per_second": 1.58, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 5.430242272347535e-06, | |
| "loss": 0.2934, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 5.012531328320802e-06, | |
| "loss": 0.2769, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 4.5948203842940685e-06, | |
| "loss": 0.2903, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 4.177109440267335e-06, | |
| "loss": 0.3092, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.7593984962406014e-06, | |
| "loss": 0.2552, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.341687552213868e-06, | |
| "loss": 0.3038, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.2546, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2.506265664160401e-06, | |
| "loss": 0.2846, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 2.0885547201336676e-06, | |
| "loss": 0.2794, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.670843776106934e-06, | |
| "loss": 0.2541, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.2531328320802005e-06, | |
| "loss": 0.2613, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 8.35421888053467e-07, | |
| "loss": 0.2633, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 4.177109440267335e-07, | |
| "loss": 0.2787, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.2927, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.8852803738317757, | |
| "eval_loss": 0.34026381373405457, | |
| "eval_runtime": 84.6819, | |
| "eval_samples_per_second": 50.542, | |
| "eval_steps_per_second": 1.582, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "step": 1330, | |
| "total_flos": 1.3257453564799912e+19, | |
| "train_loss": 0.4158173976984239, | |
| "train_runtime": 6524.231, | |
| "train_samples_per_second": 26.236, | |
| "train_steps_per_second": 0.204 | |
| } | |
| ], | |
| "max_steps": 1330, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.3257453564799912e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |