| { | |
| "best_metric": 0.9977298524404086, | |
| "best_model_checkpoint": "convnext-large-224-22k-1k-bottomCleanedData/checkpoint-1410", | |
| "epoch": 9.959636730575177, | |
| "global_step": 1410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2719, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.982078853046595e-05, | |
| "loss": 0.6765, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.9462365591397855e-05, | |
| "loss": 0.3213, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.910394265232976e-05, | |
| "loss": 0.3087, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.874551971326165e-05, | |
| "loss": 0.2588, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.2356, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.802867383512545e-05, | |
| "loss": 0.1907, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.767025089605735e-05, | |
| "loss": 0.1983, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.731182795698925e-05, | |
| "loss": 0.2132, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.695340501792115e-05, | |
| "loss": 0.2153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.1866, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.6236559139784944e-05, | |
| "loss": 0.2212, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.5878136200716846e-05, | |
| "loss": 0.1742, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.551971326164875e-05, | |
| "loss": 0.2003, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9807037457434733, | |
| "eval_loss": 0.06275633722543716, | |
| "eval_runtime": 223.5329, | |
| "eval_samples_per_second": 3.941, | |
| "eval_steps_per_second": 0.497, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.516129032258064e-05, | |
| "loss": 0.1657, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.1503, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1132, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.408602150537635e-05, | |
| "loss": 0.2287, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.372759856630825e-05, | |
| "loss": 0.1989, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.3369175627240145e-05, | |
| "loss": 0.1187, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.1305, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.265232974910394e-05, | |
| "loss": 0.1266, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.2293906810035844e-05, | |
| "loss": 0.135, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.1935483870967746e-05, | |
| "loss": 0.0955, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 4.157706093189964e-05, | |
| "loss": 0.1104, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.1446, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.0860215053763444e-05, | |
| "loss": 0.1684, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 4.050179211469534e-05, | |
| "loss": 0.1568, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9943246311010215, | |
| "eval_loss": 0.017290491610765457, | |
| "eval_runtime": 25.8711, | |
| "eval_samples_per_second": 34.053, | |
| "eval_steps_per_second": 4.291, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.014336917562724e-05, | |
| "loss": 0.1317, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.978494623655914e-05, | |
| "loss": 0.1638, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.1481, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.906810035842295e-05, | |
| "loss": 0.1343, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 3.870967741935484e-05, | |
| "loss": 0.1474, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3.8351254480286743e-05, | |
| "loss": 0.1385, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.799283154121864e-05, | |
| "loss": 0.1427, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.1364, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.727598566308244e-05, | |
| "loss": 0.1234, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.691756272401434e-05, | |
| "loss": 0.1629, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.655913978494624e-05, | |
| "loss": 0.1361, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.6200716845878134e-05, | |
| "loss": 0.1209, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.099, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.548387096774194e-05, | |
| "loss": 0.1499, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9897843359818388, | |
| "eval_loss": 0.02106553688645363, | |
| "eval_runtime": 26.0936, | |
| "eval_samples_per_second": 33.763, | |
| "eval_steps_per_second": 4.254, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.512544802867383e-05, | |
| "loss": 0.1292, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.4767025089605734e-05, | |
| "loss": 0.1215, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.4408602150537636e-05, | |
| "loss": 0.0976, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.1018, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.369175627240144e-05, | |
| "loss": 0.099, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1296, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 3.297491039426524e-05, | |
| "loss": 0.0928, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.261648745519714e-05, | |
| "loss": 0.1145, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.0758, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3.1899641577060935e-05, | |
| "loss": 0.1415, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.154121863799283e-05, | |
| "loss": 0.1325, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.118279569892473e-05, | |
| "loss": 0.0911, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.0824372759856634e-05, | |
| "loss": 0.1137, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.1189, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9954597048808173, | |
| "eval_loss": 0.014032257720828056, | |
| "eval_runtime": 26.0944, | |
| "eval_samples_per_second": 33.762, | |
| "eval_steps_per_second": 4.254, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.010752688172043e-05, | |
| "loss": 0.1333, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.974910394265233e-05, | |
| "loss": 0.117, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 2.939068100358423e-05, | |
| "loss": 0.0785, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 2.9032258064516133e-05, | |
| "loss": 0.1046, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.1224, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.831541218637993e-05, | |
| "loss": 0.0919, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.7956989247311828e-05, | |
| "loss": 0.1267, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 2.759856630824373e-05, | |
| "loss": 0.1165, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.7240143369175632e-05, | |
| "loss": 0.097, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.1161, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.652329749103943e-05, | |
| "loss": 0.0893, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.616487455197133e-05, | |
| "loss": 0.0914, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.5806451612903226e-05, | |
| "loss": 0.1219, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.5448028673835127e-05, | |
| "loss": 0.084, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9954597048808173, | |
| "eval_loss": 0.010512987151741982, | |
| "eval_runtime": 26.0838, | |
| "eval_samples_per_second": 33.776, | |
| "eval_steps_per_second": 4.256, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.0815, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.4731182795698928e-05, | |
| "loss": 0.1426, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.4372759856630826e-05, | |
| "loss": 0.0623, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 2.4014336917562724e-05, | |
| "loss": 0.092, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.3655913978494626e-05, | |
| "loss": 0.0939, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.0912, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 2.2939068100358423e-05, | |
| "loss": 0.1064, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 2.258064516129032e-05, | |
| "loss": 0.0856, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0998, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 2.1863799283154125e-05, | |
| "loss": 0.0651, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.0907, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.1146953405017922e-05, | |
| "loss": 0.0752, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 2.078853046594982e-05, | |
| "loss": 0.0567, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.0430107526881722e-05, | |
| "loss": 0.0797, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.996594778660613, | |
| "eval_loss": 0.009303615428507328, | |
| "eval_runtime": 26.0264, | |
| "eval_samples_per_second": 33.85, | |
| "eval_steps_per_second": 4.265, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 2.007168458781362e-05, | |
| "loss": 0.0576, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.0882, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 0.0673, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.899641577060932e-05, | |
| "loss": 0.0407, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 1.863799283154122e-05, | |
| "loss": 0.08, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 1.827956989247312e-05, | |
| "loss": 0.0476, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.0762, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.7562724014336916e-05, | |
| "loss": 0.0813, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.7204301075268818e-05, | |
| "loss": 0.0619, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.684587813620072e-05, | |
| "loss": 0.07, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 1.648745519713262e-05, | |
| "loss": 0.0903, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.0852, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.5770609318996415e-05, | |
| "loss": 0.0944, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.5412186379928317e-05, | |
| "loss": 0.0597, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.5053763440860215e-05, | |
| "loss": 0.0781, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9920544835414302, | |
| "eval_loss": 0.015680786222219467, | |
| "eval_runtime": 25.9238, | |
| "eval_samples_per_second": 33.984, | |
| "eval_steps_per_second": 4.282, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.4695340501792116e-05, | |
| "loss": 0.0906, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.0787, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.3978494623655914e-05, | |
| "loss": 0.082, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1.3620071684587816e-05, | |
| "loss": 0.0526, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.3261648745519714e-05, | |
| "loss": 0.0686, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 1.2903225806451613e-05, | |
| "loss": 0.0532, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.0541, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 1.2186379928315413e-05, | |
| "loss": 0.0397, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.1827956989247313e-05, | |
| "loss": 0.0428, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 1.1469534050179212e-05, | |
| "loss": 0.0597, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0498, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.102, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 1.039426523297491e-05, | |
| "loss": 0.0565, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 1.003584229390681e-05, | |
| "loss": 0.1075, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9943246311010215, | |
| "eval_loss": 0.00790259800851345, | |
| "eval_runtime": 26.0939, | |
| "eval_samples_per_second": 33.763, | |
| "eval_steps_per_second": 4.254, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.0333, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.31899641577061e-06, | |
| "loss": 0.073, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.0607, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 8.602150537634409e-06, | |
| "loss": 0.0766, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.24372759856631e-06, | |
| "loss": 0.0863, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 7.885304659498208e-06, | |
| "loss": 0.069, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.526881720430108e-06, | |
| "loss": 0.0837, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.0548, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 6.810035842293908e-06, | |
| "loss": 0.0849, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 6.451612903225806e-06, | |
| "loss": 0.0676, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 6.0931899641577065e-06, | |
| "loss": 0.0602, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 5.734767025089606e-06, | |
| "loss": 0.0803, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.0511, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 5.017921146953405e-06, | |
| "loss": 0.0718, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.996594778660613, | |
| "eval_loss": 0.007493594661355019, | |
| "eval_runtime": 25.9593, | |
| "eval_samples_per_second": 33.938, | |
| "eval_steps_per_second": 4.276, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.659498207885305e-06, | |
| "loss": 0.0675, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 4.3010752688172045e-06, | |
| "loss": 0.0691, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.942652329749104e-06, | |
| "loss": 0.0726, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.0384, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.225806451612903e-06, | |
| "loss": 0.0626, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 2.867383512544803e-06, | |
| "loss": 0.0397, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.5089605734767026e-06, | |
| "loss": 0.0666, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 2.1505376344086023e-06, | |
| "loss": 0.0613, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.0648, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.4336917562724014e-06, | |
| "loss": 0.0604, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.0752688172043011e-06, | |
| "loss": 0.0841, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 7.168458781362007e-07, | |
| "loss": 0.0581, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 3.5842293906810036e-07, | |
| "loss": 0.051, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 0.0, | |
| "loss": 0.0592, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "eval_accuracy": 0.9977298524404086, | |
| "eval_loss": 0.006742474623024464, | |
| "eval_runtime": 26.0288, | |
| "eval_samples_per_second": 33.847, | |
| "eval_steps_per_second": 4.265, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "step": 1410, | |
| "total_flos": 1.3986461576137236e+19, | |
| "train_loss": 0.1187829462983084, | |
| "train_runtime": 9114.264, | |
| "train_samples_per_second": 8.693, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "max_steps": 1410, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.3986461576137236e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |