| { | |
| "best_metric": 0.7344809133071709, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1678", | |
| "epoch": 29.772151898734176, | |
| "global_step": 2940, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7006802721088438e-06, | |
| "loss": 0.7145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.4013605442176877e-06, | |
| "loss": 0.6942, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5.102040816326531e-06, | |
| "loss": 0.6747, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.802721088435375e-06, | |
| "loss": 0.6626, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 8.503401360544217e-06, | |
| "loss": 0.645, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.0204081632653061e-05, | |
| "loss": 0.643, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.6353, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.360544217687075e-05, | |
| "loss": 0.6242, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.5306122448979594e-05, | |
| "loss": 0.6271, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6925615412058509, | |
| "eval_loss": 0.6034993529319763, | |
| "eval_runtime": 291.7633, | |
| "eval_samples_per_second": 38.428, | |
| "eval_steps_per_second": 0.151, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.7006802721088435e-05, | |
| "loss": 0.625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.8707482993197282e-05, | |
| "loss": 0.6206, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.0408163265306123e-05, | |
| "loss": 0.6208, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.2108843537414966e-05, | |
| "loss": 0.625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.6198, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.5510204081632654e-05, | |
| "loss": 0.613, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.72108843537415e-05, | |
| "loss": 0.6242, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.891156462585034e-05, | |
| "loss": 0.616, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.061224489795919e-05, | |
| "loss": 0.6145, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.231292517006803e-05, | |
| "loss": 0.6156, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.7005886550124866, | |
| "eval_loss": 0.5843892097473145, | |
| "eval_runtime": 301.4707, | |
| "eval_samples_per_second": 37.191, | |
| "eval_steps_per_second": 0.146, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.401360544217687e-05, | |
| "loss": 0.6069, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.6087, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.7414965986394564e-05, | |
| "loss": 0.6116, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 3.9115646258503405e-05, | |
| "loss": 0.6085, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 4.0816326530612245e-05, | |
| "loss": 0.6049, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.2517006802721085e-05, | |
| "loss": 0.6013, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.421768707482993e-05, | |
| "loss": 0.6009, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.591836734693878e-05, | |
| "loss": 0.608, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.6145, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 4.931972789115647e-05, | |
| "loss": 0.6148, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7103995718872637, | |
| "eval_loss": 0.5758489966392517, | |
| "eval_runtime": 290.2528, | |
| "eval_samples_per_second": 38.628, | |
| "eval_steps_per_second": 0.152, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.9886621315192745e-05, | |
| "loss": 0.5965, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.969765684051398e-05, | |
| "loss": 0.601, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.9508692365835225e-05, | |
| "loss": 0.6087, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 4.931972789115647e-05, | |
| "loss": 0.6063, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 4.9130763416477704e-05, | |
| "loss": 0.6034, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 4.894179894179895e-05, | |
| "loss": 0.5962, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 4.875283446712018e-05, | |
| "loss": 0.605, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.8563869992441426e-05, | |
| "loss": 0.5962, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 4.837490551776266e-05, | |
| "loss": 0.5986, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 4.8185941043083905e-05, | |
| "loss": 0.6055, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7014805565465573, | |
| "eval_loss": 0.5852587819099426, | |
| "eval_runtime": 287.2656, | |
| "eval_samples_per_second": 39.03, | |
| "eval_steps_per_second": 0.153, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 4.799697656840514e-05, | |
| "loss": 0.597, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 4.7808012093726384e-05, | |
| "loss": 0.5931, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.5942, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.7430083144368857e-05, | |
| "loss": 0.5989, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 4.72411186696901e-05, | |
| "loss": 0.5947, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.7052154195011336e-05, | |
| "loss": 0.5972, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 4.686318972033258e-05, | |
| "loss": 0.5864, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 4.667422524565382e-05, | |
| "loss": 0.5975, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 4.648526077097506e-05, | |
| "loss": 0.598, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5938, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.7103995718872637, | |
| "eval_loss": 0.5857925415039062, | |
| "eval_runtime": 270.8215, | |
| "eval_samples_per_second": 41.4, | |
| "eval_steps_per_second": 0.162, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 4.610733182161754e-05, | |
| "loss": 0.5987, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 4.591836734693878e-05, | |
| "loss": 0.5889, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 4.5729402872260016e-05, | |
| "loss": 0.5908, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 4.554043839758126e-05, | |
| "loss": 0.5908, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 4.53514739229025e-05, | |
| "loss": 0.5871, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 4.516250944822374e-05, | |
| "loss": 0.593, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 4.4973544973544974e-05, | |
| "loss": 0.5891, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 4.478458049886621e-05, | |
| "loss": 0.594, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 4.4595616024187454e-05, | |
| "loss": 0.5924, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 4.4406651549508697e-05, | |
| "loss": 0.5878, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.7210132001427042, | |
| "eval_loss": 0.5630102753639221, | |
| "eval_runtime": 271.5122, | |
| "eval_samples_per_second": 41.295, | |
| "eval_steps_per_second": 0.162, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.421768707482993e-05, | |
| "loss": 0.5898, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 4.4028722600151176e-05, | |
| "loss": 0.5872, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 4.383975812547241e-05, | |
| "loss": 0.5885, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 0.5811, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 4.346182917611489e-05, | |
| "loss": 0.5859, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 4.3272864701436134e-05, | |
| "loss": 0.5914, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 4.308390022675737e-05, | |
| "loss": 0.5867, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 4.289493575207861e-05, | |
| "loss": 0.5865, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 4.2705971277399856e-05, | |
| "loss": 0.5881, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 4.2517006802721085e-05, | |
| "loss": 0.5873, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7235997145915091, | |
| "eval_loss": 0.5619792938232422, | |
| "eval_runtime": 267.8238, | |
| "eval_samples_per_second": 41.863, | |
| "eval_steps_per_second": 0.164, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 4.232804232804233e-05, | |
| "loss": 0.5803, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 4.2139077853363565e-05, | |
| "loss": 0.5775, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 4.195011337868481e-05, | |
| "loss": 0.5849, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 4.176114890400605e-05, | |
| "loss": 0.5856, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 4.157218442932729e-05, | |
| "loss": 0.5843, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 4.138321995464853e-05, | |
| "loss": 0.5889, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 4.1194255479969766e-05, | |
| "loss": 0.5763, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 4.100529100529101e-05, | |
| "loss": 0.5833, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 4.0816326530612245e-05, | |
| "loss": 0.5781, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062736205593349e-05, | |
| "loss": 0.5947, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7195861576881912, | |
| "eval_loss": 0.5669898390769958, | |
| "eval_runtime": 271.8958, | |
| "eval_samples_per_second": 41.236, | |
| "eval_steps_per_second": 0.162, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 4.043839758125473e-05, | |
| "loss": 0.5784, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 4.024943310657597e-05, | |
| "loss": 0.578, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.006046863189721e-05, | |
| "loss": 0.5888, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 3.987150415721844e-05, | |
| "loss": 0.5828, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.582, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 3.9493575207860925e-05, | |
| "loss": 0.5817, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 3.930461073318216e-05, | |
| "loss": 0.5729, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 3.9115646258503405e-05, | |
| "loss": 0.5831, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 3.892668178382464e-05, | |
| "loss": 0.5866, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.7265429896539422, | |
| "eval_loss": 0.5592203736305237, | |
| "eval_runtime": 270.4426, | |
| "eval_samples_per_second": 41.458, | |
| "eval_steps_per_second": 0.163, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 3.8737717309145884e-05, | |
| "loss": 0.5808, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 3.854875283446712e-05, | |
| "loss": 0.5863, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 3.835978835978836e-05, | |
| "loss": 0.5783, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.81708238851096e-05, | |
| "loss": 0.578, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 3.798185941043084e-05, | |
| "loss": 0.569, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 3.7792894935752085e-05, | |
| "loss": 0.5821, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 3.760393046107332e-05, | |
| "loss": 0.5827, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 3.7414965986394564e-05, | |
| "loss": 0.5817, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.7226001511715794e-05, | |
| "loss": 0.5774, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5807, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.7253835176596504, | |
| "eval_loss": 0.557357132434845, | |
| "eval_runtime": 270.5413, | |
| "eval_samples_per_second": 41.443, | |
| "eval_steps_per_second": 0.163, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 3.684807256235828e-05, | |
| "loss": 0.5883, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 3.6659108087679516e-05, | |
| "loss": 0.5711, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 3.647014361300076e-05, | |
| "loss": 0.5794, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 3.6281179138321995e-05, | |
| "loss": 0.5869, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 3.609221466364324e-05, | |
| "loss": 0.584, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 3.5903250188964474e-05, | |
| "loss": 0.5716, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.5783, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 3.552532123960696e-05, | |
| "loss": 0.577, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 3.5336356764928196e-05, | |
| "loss": 0.5779, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 3.514739229024944e-05, | |
| "loss": 0.5764, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7244916161255798, | |
| "eval_loss": 0.565514862537384, | |
| "eval_runtime": 273.5069, | |
| "eval_samples_per_second": 40.993, | |
| "eval_steps_per_second": 0.161, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.4958427815570675e-05, | |
| "loss": 0.5806, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 3.476946334089191e-05, | |
| "loss": 0.5779, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 3.4580498866213154e-05, | |
| "loss": 0.5799, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 3.439153439153439e-05, | |
| "loss": 0.5844, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 3.4202569916855634e-05, | |
| "loss": 0.5715, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 3.401360544217687e-05, | |
| "loss": 0.5809, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 3.382464096749811e-05, | |
| "loss": 0.5695, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 3.363567649281935e-05, | |
| "loss": 0.576, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 3.344671201814059e-05, | |
| "loss": 0.5736, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 3.325774754346183e-05, | |
| "loss": 0.5729, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7236889047449162, | |
| "eval_loss": 0.5611264109611511, | |
| "eval_runtime": 268.1746, | |
| "eval_samples_per_second": 41.809, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 3.306878306878307e-05, | |
| "loss": 0.5775, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 3.2879818594104314e-05, | |
| "loss": 0.5774, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 3.269085411942555e-05, | |
| "loss": 0.5751, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 3.250188964474679e-05, | |
| "loss": 0.5767, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 3.231292517006803e-05, | |
| "loss": 0.5717, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 3.2123960695389265e-05, | |
| "loss": 0.5738, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 3.193499622071051e-05, | |
| "loss": 0.5749, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.5741, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 3.155706727135299e-05, | |
| "loss": 0.5789, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.1368102796674224e-05, | |
| "loss": 0.577, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.7188726364609347, | |
| "eval_loss": 0.5702112913131714, | |
| "eval_runtime": 267.6574, | |
| "eval_samples_per_second": 41.889, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1283 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 3.117913832199547e-05, | |
| "loss": 0.5767, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 3.09901738473167e-05, | |
| "loss": 0.5727, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 3.0801209372637946e-05, | |
| "loss": 0.5702, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 13.37, | |
| "learning_rate": 3.061224489795919e-05, | |
| "loss": 0.5768, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 3.0423280423280425e-05, | |
| "loss": 0.5708, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 3.0234315948601665e-05, | |
| "loss": 0.5708, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 3.0045351473922904e-05, | |
| "loss": 0.5677, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 2.9856386999244147e-05, | |
| "loss": 0.5755, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 2.9667422524565387e-05, | |
| "loss": 0.5731, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 2.947845804988662e-05, | |
| "loss": 0.5702, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_accuracy": 0.7259186585800927, | |
| "eval_loss": 0.5587979555130005, | |
| "eval_runtime": 267.9851, | |
| "eval_samples_per_second": 41.838, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.928949357520786e-05, | |
| "loss": 0.5713, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 2.91005291005291e-05, | |
| "loss": 0.5648, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 2.891156462585034e-05, | |
| "loss": 0.5715, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 2.872260015117158e-05, | |
| "loss": 0.5711, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 2.853363567649282e-05, | |
| "loss": 0.5598, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 2.834467120181406e-05, | |
| "loss": 0.5746, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 2.81557067271353e-05, | |
| "loss": 0.5702, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 2.796674225245654e-05, | |
| "loss": 0.58, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5706, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 2.758881330309902e-05, | |
| "loss": 0.5717, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7244024259721726, | |
| "eval_loss": 0.5564510226249695, | |
| "eval_runtime": 273.2108, | |
| "eval_samples_per_second": 41.038, | |
| "eval_steps_per_second": 0.161, | |
| "step": 1481 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 2.739984882842026e-05, | |
| "loss": 0.5678, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 2.72108843537415e-05, | |
| "loss": 0.5653, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 2.7021919879062734e-05, | |
| "loss": 0.5599, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 2.6832955404383974e-05, | |
| "loss": 0.5745, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 2.6643990929705213e-05, | |
| "loss": 0.5701, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 2.6455026455026456e-05, | |
| "loss": 0.5715, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 2.6266061980347696e-05, | |
| "loss": 0.5677, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.6077097505668935e-05, | |
| "loss": 0.5749, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 2.5888133030990175e-05, | |
| "loss": 0.5741, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5699168556311414e-05, | |
| "loss": 0.5646, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7302889760970389, | |
| "eval_loss": 0.5536319017410278, | |
| "eval_runtime": 270.439, | |
| "eval_samples_per_second": 41.459, | |
| "eval_steps_per_second": 0.163, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 2.5510204081632654e-05, | |
| "loss": 0.5717, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 2.5321239606953894e-05, | |
| "loss": 0.565, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 2.5132275132275137e-05, | |
| "loss": 0.5749, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 2.4943310657596373e-05, | |
| "loss": 0.5701, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 2.4754346182917612e-05, | |
| "loss": 0.5717, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 2.4565381708238852e-05, | |
| "loss": 0.5641, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 2.437641723356009e-05, | |
| "loss": 0.5663, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 2.418745275888133e-05, | |
| "loss": 0.5674, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 2.399848828420257e-05, | |
| "loss": 0.5591, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.7344809133071709, | |
| "eval_loss": 0.5525398254394531, | |
| "eval_runtime": 269.9721, | |
| "eval_samples_per_second": 41.53, | |
| "eval_steps_per_second": 0.163, | |
| "step": 1678 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.5754, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 2.362055933484505e-05, | |
| "loss": 0.5734, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 2.343159486016629e-05, | |
| "loss": 0.5671, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 2.324263038548753e-05, | |
| "loss": 0.5663, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 2.305366591080877e-05, | |
| "loss": 0.5707, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 2.2864701436130008e-05, | |
| "loss": 0.5635, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 17.62, | |
| "learning_rate": 2.267573696145125e-05, | |
| "loss": 0.569, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 2.2486772486772487e-05, | |
| "loss": 0.5675, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 2.2297808012093727e-05, | |
| "loss": 0.5623, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2108843537414966e-05, | |
| "loss": 0.5586, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_accuracy": 0.7285943631823046, | |
| "eval_loss": 0.5565158724784851, | |
| "eval_runtime": 267.0513, | |
| "eval_samples_per_second": 41.984, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1777 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 2.1919879062736206e-05, | |
| "loss": 0.5606, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 2.1730914588057446e-05, | |
| "loss": 0.5611, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 2.1541950113378685e-05, | |
| "loss": 0.5693, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 2.1352985638699928e-05, | |
| "loss": 0.559, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 18.43, | |
| "learning_rate": 2.1164021164021164e-05, | |
| "loss": 0.5673, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 2.0975056689342404e-05, | |
| "loss": 0.5635, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 2.0786092214663643e-05, | |
| "loss": 0.567, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 2.0597127739984883e-05, | |
| "loss": 0.5637, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 2.0408163265306123e-05, | |
| "loss": 0.5648, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 2.0219198790627365e-05, | |
| "loss": 0.5668, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7303781662504459, | |
| "eval_loss": 0.5519587993621826, | |
| "eval_runtime": 272.9351, | |
| "eval_samples_per_second": 41.079, | |
| "eval_steps_per_second": 0.161, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.0030234315948605e-05, | |
| "loss": 0.5628, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.5642, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 1.965230536659108e-05, | |
| "loss": 0.5563, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 1.946334089191232e-05, | |
| "loss": 0.5642, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 1.927437641723356e-05, | |
| "loss": 0.5618, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 1.90854119425548e-05, | |
| "loss": 0.5578, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 19.65, | |
| "learning_rate": 1.8896447467876043e-05, | |
| "loss": 0.5636, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 1.8707482993197282e-05, | |
| "loss": 0.5749, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.5628, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 1.8329554043839758e-05, | |
| "loss": 0.5617, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7288619336425258, | |
| "eval_loss": 0.5557389855384827, | |
| "eval_runtime": 270.9737, | |
| "eval_samples_per_second": 41.377, | |
| "eval_steps_per_second": 0.162, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 20.05, | |
| "learning_rate": 1.8140589569160997e-05, | |
| "loss": 0.5541, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 20.15, | |
| "learning_rate": 1.7951625094482237e-05, | |
| "loss": 0.5693, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 1.776266061980348e-05, | |
| "loss": 0.5652, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 20.35, | |
| "learning_rate": 1.757369614512472e-05, | |
| "loss": 0.5579, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 20.46, | |
| "learning_rate": 1.7384731670445956e-05, | |
| "loss": 0.5597, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "learning_rate": 1.7195767195767195e-05, | |
| "loss": 0.5674, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 1.7006802721088435e-05, | |
| "loss": 0.5634, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 1.6817838246409674e-05, | |
| "loss": 0.567, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "learning_rate": 1.6628873771730914e-05, | |
| "loss": 0.5571, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 1.6439909297052157e-05, | |
| "loss": 0.5546, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.7325187299322155, | |
| "eval_loss": 0.5561436414718628, | |
| "eval_runtime": 269.5801, | |
| "eval_samples_per_second": 41.591, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2073 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "learning_rate": 1.6250944822373397e-05, | |
| "loss": 0.5589, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 1.6061980347694633e-05, | |
| "loss": 0.5658, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.5596, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 1.5684051398337112e-05, | |
| "loss": 0.5618, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "learning_rate": 1.549508692365835e-05, | |
| "loss": 0.5624, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 1.5306122448979594e-05, | |
| "loss": 0.5619, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 21.67, | |
| "learning_rate": 1.5117157974300832e-05, | |
| "loss": 0.5554, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 21.77, | |
| "learning_rate": 1.4928193499622074e-05, | |
| "loss": 0.5539, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 1.473922902494331e-05, | |
| "loss": 0.5657, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 21.97, | |
| "learning_rate": 1.455026455026455e-05, | |
| "loss": 0.5579, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "eval_accuracy": 0.7314484480913307, | |
| "eval_loss": 0.5537222623825073, | |
| "eval_runtime": 267.4411, | |
| "eval_samples_per_second": 41.923, | |
| "eval_steps_per_second": 0.165, | |
| "step": 2172 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.436130007558579e-05, | |
| "loss": 0.554, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 1.417233560090703e-05, | |
| "loss": 0.569, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 1.398337112622827e-05, | |
| "loss": 0.5528, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "learning_rate": 1.379440665154951e-05, | |
| "loss": 0.5649, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 22.48, | |
| "learning_rate": 1.360544217687075e-05, | |
| "loss": 0.5586, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 22.58, | |
| "learning_rate": 1.3416477702191987e-05, | |
| "loss": 0.5606, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 1.3227513227513228e-05, | |
| "loss": 0.5551, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 1.3038548752834468e-05, | |
| "loss": 0.5588, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 1.2849584278155707e-05, | |
| "loss": 0.5591, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "learning_rate": 1.2660619803476947e-05, | |
| "loss": 0.5604, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.72904031394934, | |
| "eval_loss": 0.5545207262039185, | |
| "eval_runtime": 270.2678, | |
| "eval_samples_per_second": 41.485, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2271 | |
| }, | |
| { | |
| "epoch": 23.09, | |
| "learning_rate": 1.2471655328798186e-05, | |
| "loss": 0.5588, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 1.2282690854119426e-05, | |
| "loss": 0.5499, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 23.29, | |
| "learning_rate": 1.2093726379440666e-05, | |
| "loss": 0.5495, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.5571, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 23.49, | |
| "learning_rate": 1.1715797430083145e-05, | |
| "loss": 0.5545, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 23.59, | |
| "learning_rate": 1.1526832955404384e-05, | |
| "loss": 0.5625, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 23.7, | |
| "learning_rate": 1.1337868480725626e-05, | |
| "loss": 0.5573, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 23.8, | |
| "learning_rate": 1.1148904006046863e-05, | |
| "loss": 0.5623, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 23.9, | |
| "learning_rate": 1.0959939531368103e-05, | |
| "loss": 0.5527, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0770975056689343e-05, | |
| "loss": 0.5563, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7287727434891188, | |
| "eval_loss": 0.5590741634368896, | |
| "eval_runtime": 269.4039, | |
| "eval_samples_per_second": 41.618, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 24.1, | |
| "learning_rate": 1.0582010582010582e-05, | |
| "loss": 0.5586, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 1.0393046107331822e-05, | |
| "loss": 0.5424, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 1.0204081632653061e-05, | |
| "loss": 0.5598, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "learning_rate": 1.0015117157974303e-05, | |
| "loss": 0.5528, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 24.51, | |
| "learning_rate": 9.82615268329554e-06, | |
| "loss": 0.5521, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 24.61, | |
| "learning_rate": 9.63718820861678e-06, | |
| "loss": 0.5524, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "learning_rate": 9.448223733938021e-06, | |
| "loss": 0.5602, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 24.81, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.5608, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 9.070294784580499e-06, | |
| "loss": 0.5634, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.7307349268640742, | |
| "eval_loss": 0.5545657277107239, | |
| "eval_runtime": 273.5576, | |
| "eval_samples_per_second": 40.986, | |
| "eval_steps_per_second": 0.161, | |
| "step": 2468 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 8.88133030990174e-06, | |
| "loss": 0.5516, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 8.692365835222978e-06, | |
| "loss": 0.5489, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 25.22, | |
| "learning_rate": 8.503401360544217e-06, | |
| "loss": 0.5562, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 8.314436885865457e-06, | |
| "loss": 0.5498, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 8.125472411186698e-06, | |
| "loss": 0.5578, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 25.52, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.551, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "learning_rate": 7.747543461829176e-06, | |
| "loss": 0.5572, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 25.72, | |
| "learning_rate": 7.558578987150416e-06, | |
| "loss": 0.5523, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 7.369614512471655e-06, | |
| "loss": 0.5525, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.180650037792895e-06, | |
| "loss": 0.5563, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "eval_accuracy": 0.7302889760970389, | |
| "eval_loss": 0.5556601285934448, | |
| "eval_runtime": 270.2761, | |
| "eval_samples_per_second": 41.484, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2567 | |
| }, | |
| { | |
| "epoch": 26.03, | |
| "learning_rate": 6.991685563114135e-06, | |
| "loss": 0.5607, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 26.13, | |
| "learning_rate": 6.802721088435375e-06, | |
| "loss": 0.5555, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 26.23, | |
| "learning_rate": 6.613756613756614e-06, | |
| "loss": 0.5527, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 26.33, | |
| "learning_rate": 6.424792139077854e-06, | |
| "loss": 0.5549, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 6.235827664399093e-06, | |
| "loss": 0.5435, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 6.046863189720333e-06, | |
| "loss": 0.5511, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 26.63, | |
| "learning_rate": 5.857898715041572e-06, | |
| "loss": 0.5629, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 26.73, | |
| "learning_rate": 5.668934240362813e-06, | |
| "loss": 0.5527, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "learning_rate": 5.4799697656840515e-06, | |
| "loss": 0.5541, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 5.291005291005291e-06, | |
| "loss": 0.5563, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.727613271494827, | |
| "eval_loss": 0.5571199655532837, | |
| "eval_runtime": 269.8955, | |
| "eval_samples_per_second": 41.542, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2666 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 5.102040816326531e-06, | |
| "loss": 0.553, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 4.91307634164777e-06, | |
| "loss": 0.5502, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 4.724111866969011e-06, | |
| "loss": 0.55, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 27.34, | |
| "learning_rate": 4.535147392290249e-06, | |
| "loss": 0.5527, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 27.44, | |
| "learning_rate": 4.346182917611489e-06, | |
| "loss": 0.5462, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 4.1572184429327285e-06, | |
| "loss": 0.5502, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 27.65, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.5533, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 3.779289493575208e-06, | |
| "loss": 0.5585, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 27.85, | |
| "learning_rate": 3.5903250188964477e-06, | |
| "loss": 0.556, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 3.4013605442176877e-06, | |
| "loss": 0.5544, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7298430253300036, | |
| "eval_loss": 0.5550753474235535, | |
| "eval_runtime": 273.4563, | |
| "eval_samples_per_second": 41.001, | |
| "eval_steps_per_second": 0.161, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 28.05, | |
| "learning_rate": 3.212396069538927e-06, | |
| "loss": 0.553, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 28.15, | |
| "learning_rate": 3.0234315948601664e-06, | |
| "loss": 0.5534, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 28.25, | |
| "learning_rate": 2.8344671201814064e-06, | |
| "loss": 0.5488, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 28.35, | |
| "learning_rate": 2.6455026455026455e-06, | |
| "loss": 0.5553, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 28.46, | |
| "learning_rate": 2.456538170823885e-06, | |
| "loss": 0.5503, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 28.56, | |
| "learning_rate": 2.2675736961451247e-06, | |
| "loss": 0.5493, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 2.0786092214663643e-06, | |
| "loss": 0.5474, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "learning_rate": 1.889644746787604e-06, | |
| "loss": 0.5477, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "learning_rate": 1.7006802721088438e-06, | |
| "loss": 0.5565, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.5117157974300832e-06, | |
| "loss": 0.5491, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.7282376025686764, | |
| "eval_loss": 0.5596103668212891, | |
| "eval_runtime": 270.7488, | |
| "eval_samples_per_second": 41.411, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2863 | |
| }, | |
| { | |
| "epoch": 29.06, | |
| "learning_rate": 1.3227513227513228e-06, | |
| "loss": 0.5508, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 29.16, | |
| "learning_rate": 1.1337868480725623e-06, | |
| "loss": 0.5513, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 29.27, | |
| "learning_rate": 9.44822373393802e-07, | |
| "loss": 0.5517, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 29.37, | |
| "learning_rate": 7.558578987150416e-07, | |
| "loss": 0.5575, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 29.47, | |
| "learning_rate": 5.668934240362812e-07, | |
| "loss": 0.5519, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 3.779289493575208e-07, | |
| "loss": 0.5549, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "learning_rate": 1.889644746787604e-07, | |
| "loss": 0.5478, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 29.77, | |
| "learning_rate": 0.0, | |
| "loss": 0.5461, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 29.77, | |
| "eval_accuracy": 0.7302889760970389, | |
| "eval_loss": 0.5574254989624023, | |
| "eval_runtime": 267.0764, | |
| "eval_samples_per_second": 41.98, | |
| "eval_steps_per_second": 0.165, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 29.77, | |
| "step": 2940, | |
| "total_flos": 7.46776315809736e+19, | |
| "train_loss": 0.5755378539870385, | |
| "train_runtime": 78104.0618, | |
| "train_samples_per_second": 38.759, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "max_steps": 2940, | |
| "num_train_epochs": 30, | |
| "total_flos": 7.46776315809736e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |