| { | |
| "best_metric": 0.7115384615384616, | |
| "best_model_checkpoint": "videomae-large-finetuned-kinetics-mopping/checkpoint-1672", | |
| "epoch": 3.25, | |
| "global_step": 1672, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.9761904761904763e-06, | |
| "loss": 0.7257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.7446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.7318, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.6849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.4880952380952381e-05, | |
| "loss": 0.66, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.5942, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.0265, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.6231, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 0.6112, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 0.7304, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.273809523809524e-05, | |
| "loss": 0.5416, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.6291, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.8690476190476195e-05, | |
| "loss": 0.6386, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5992, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 0.7842, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.6465, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.993351063829788e-05, | |
| "loss": 1.8611, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.9601063829787235e-05, | |
| "loss": 0.8756, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.92686170212766e-05, | |
| "loss": 0.6679, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.893617021276596e-05, | |
| "loss": 0.6566, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.860372340425532e-05, | |
| "loss": 0.543, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.8271276595744686e-05, | |
| "loss": 0.547, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.793882978723405e-05, | |
| "loss": 0.6893, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7606382978723405e-05, | |
| "loss": 0.9666, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.727393617021277e-05, | |
| "loss": 0.7574, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.694148936170213e-05, | |
| "loss": 0.6599, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.660904255319149e-05, | |
| "loss": 0.682, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.627659574468085e-05, | |
| "loss": 0.6714, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.594414893617022e-05, | |
| "loss": 0.7409, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.5611702127659576e-05, | |
| "loss": 0.5337, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.527925531914894e-05, | |
| "loss": 0.9172, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.49468085106383e-05, | |
| "loss": 0.6787, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.461436170212766e-05, | |
| "loss": 0.6626, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.428191489361702e-05, | |
| "loss": 0.6113, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.394946808510639e-05, | |
| "loss": 0.703, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.3617021276595746e-05, | |
| "loss": 0.6532, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.328457446808511e-05, | |
| "loss": 0.8501, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.295212765957447e-05, | |
| "loss": 0.5234, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.2619680851063835e-05, | |
| "loss": 0.8803, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.228723404255319e-05, | |
| "loss": 0.6746, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.1954787234042554e-05, | |
| "loss": 0.6868, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.21153846153846154, | |
| "eval_loss": 0.7473957538604736, | |
| "eval_runtime": 184.1286, | |
| "eval_samples_per_second": 1.694, | |
| "eval_steps_per_second": 0.847, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.1622340425531916e-05, | |
| "loss": 0.6966, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.128989361702128e-05, | |
| "loss": 0.615, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.095744680851064e-05, | |
| "loss": 0.6828, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 0.627, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.029255319148936e-05, | |
| "loss": 0.6394, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.9960106382978724e-05, | |
| "loss": 0.4705, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.962765957446809e-05, | |
| "loss": 0.8386, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.929521276595745e-05, | |
| "loss": 0.6489, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.896276595744681e-05, | |
| "loss": 0.4634, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.8630319148936175e-05, | |
| "loss": 0.4205, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.829787234042553e-05, | |
| "loss": 1.1553, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.7965425531914894e-05, | |
| "loss": 0.968, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.763297872340426e-05, | |
| "loss": 0.662, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.730053191489361e-05, | |
| "loss": 0.8165, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.696808510638298e-05, | |
| "loss": 0.8334, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.6635638297872346e-05, | |
| "loss": 0.592, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.63031914893617e-05, | |
| "loss": 0.6842, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.5970744680851064e-05, | |
| "loss": 0.692, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.563829787234043e-05, | |
| "loss": 0.7469, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.530585106382979e-05, | |
| "loss": 0.7048, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.497340425531915e-05, | |
| "loss": 0.7271, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.4640957446808516e-05, | |
| "loss": 0.4924, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.430851063829787e-05, | |
| "loss": 0.6303, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.3976063829787235e-05, | |
| "loss": 0.8736, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.36436170212766e-05, | |
| "loss": 0.5803, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.331117021276596e-05, | |
| "loss": 0.7117, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.2978723404255317e-05, | |
| "loss": 0.7229, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.2646276595744686e-05, | |
| "loss": 0.5549, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.231382978723405e-05, | |
| "loss": 0.596, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.1981382978723405e-05, | |
| "loss": 0.6088, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.164893617021277e-05, | |
| "loss": 1.2256, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.131648936170213e-05, | |
| "loss": 0.9902, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.098404255319149e-05, | |
| "loss": 0.4703, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.065159574468085e-05, | |
| "loss": 0.7934, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.0319148936170216e-05, | |
| "loss": 0.6965, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.998670212765958e-05, | |
| "loss": 0.5744, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9654255319148938e-05, | |
| "loss": 0.4907, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9321808510638298e-05, | |
| "loss": 1.0854, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.898936170212766e-05, | |
| "loss": 0.7813, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.865691489361702e-05, | |
| "loss": 0.6902, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.8324468085106386e-05, | |
| "loss": 0.8116, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.799202127659575e-05, | |
| "loss": 0.7265, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.6025641025641025, | |
| "eval_loss": 0.6471951007843018, | |
| "eval_runtime": 175.8702, | |
| "eval_samples_per_second": 1.774, | |
| "eval_steps_per_second": 0.887, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.765957446808511e-05, | |
| "loss": 0.6714, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.7327127659574468e-05, | |
| "loss": 0.7021, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.699468085106383e-05, | |
| "loss": 0.5664, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.666223404255319e-05, | |
| "loss": 0.6453, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.6329787234042553e-05, | |
| "loss": 0.6841, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.599734042553192e-05, | |
| "loss": 0.3523, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.566489361702128e-05, | |
| "loss": 0.5916, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.5332446808510642e-05, | |
| "loss": 0.6005, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9208, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.466755319148936e-05, | |
| "loss": 1.1425, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.4335106382978727e-05, | |
| "loss": 0.6431, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.4002659574468086e-05, | |
| "loss": 0.843, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.3670212765957446e-05, | |
| "loss": 0.6568, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.333776595744681e-05, | |
| "loss": 0.5618, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.300531914893617e-05, | |
| "loss": 0.4693, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.2672872340425534e-05, | |
| "loss": 0.9186, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.2340425531914894e-05, | |
| "loss": 0.6835, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.2007978723404257e-05, | |
| "loss": 0.6809, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.167553191489362e-05, | |
| "loss": 0.607, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.134308510638298e-05, | |
| "loss": 0.6872, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.1010638297872342e-05, | |
| "loss": 0.6011, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.0678191489361705e-05, | |
| "loss": 0.6885, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.0345744680851064e-05, | |
| "loss": 0.5925, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.0013297872340424e-05, | |
| "loss": 0.5091, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.968085106382979e-05, | |
| "loss": 0.4648, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.934840425531915e-05, | |
| "loss": 0.7222, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.9015957446808512e-05, | |
| "loss": 0.4034, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8683510638297875e-05, | |
| "loss": 0.5973, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8351063829787234e-05, | |
| "loss": 1.1715, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.8018617021276597e-05, | |
| "loss": 0.9911, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.768617021276596e-05, | |
| "loss": 0.4329, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.735372340425532e-05, | |
| "loss": 0.7458, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.7021276595744682e-05, | |
| "loss": 1.1755, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6688829787234042e-05, | |
| "loss": 0.6074, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6356382978723405e-05, | |
| "loss": 0.8051, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6023936170212768e-05, | |
| "loss": 0.6331, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.5691489361702127e-05, | |
| "loss": 0.6292, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.535904255319149e-05, | |
| "loss": 0.6519, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.5026595744680853e-05, | |
| "loss": 0.6466, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4694148936170212e-05, | |
| "loss": 0.6337, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4361702127659577e-05, | |
| "loss": 0.6831, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.4029255319148938e-05, | |
| "loss": 0.6854, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.6346153846153846, | |
| "eval_loss": 0.621135950088501, | |
| "eval_runtime": 177.1967, | |
| "eval_samples_per_second": 1.761, | |
| "eval_steps_per_second": 0.88, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.3696808510638297e-05, | |
| "loss": 0.4754, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1.3364361702127659e-05, | |
| "loss": 0.6731, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.3031914893617023e-05, | |
| "loss": 0.5832, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.2699468085106384e-05, | |
| "loss": 0.6755, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.2367021276595745e-05, | |
| "loss": 0.7011, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.2034574468085107e-05, | |
| "loss": 0.5694, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.170212765957447e-05, | |
| "loss": 0.6381, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.136968085106383e-05, | |
| "loss": 0.6598, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.1037234042553192e-05, | |
| "loss": 0.6255, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.0704787234042555e-05, | |
| "loss": 0.5323, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.0372340425531916e-05, | |
| "loss": 0.4125, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.0039893617021277e-05, | |
| "loss": 0.7932, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.707446808510638e-06, | |
| "loss": 0.5528, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.6247, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 9.042553191489362e-06, | |
| "loss": 0.5198, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 8.710106382978723e-06, | |
| "loss": 0.6433, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 8.377659574468086e-06, | |
| "loss": 0.5981, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 8.045212765957447e-06, | |
| "loss": 0.7204, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.712765957446808e-06, | |
| "loss": 0.7437, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.380319148936171e-06, | |
| "loss": 0.6888, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.047872340425532e-06, | |
| "loss": 0.6113, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 6.715425531914894e-06, | |
| "loss": 0.6399, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 6.3829787234042555e-06, | |
| "loss": 0.5685, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 6.0505319148936175e-06, | |
| "loss": 0.7251, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.718085106382979e-06, | |
| "loss": 0.629, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.385638297872341e-06, | |
| "loss": 0.5404, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 5.053191489361702e-06, | |
| "loss": 0.6974, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.720744680851065e-06, | |
| "loss": 0.7332, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.388297872340426e-06, | |
| "loss": 0.6905, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.055851063829787e-06, | |
| "loss": 0.6313, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.723404255319149e-06, | |
| "loss": 0.6934, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.3909574468085105e-06, | |
| "loss": 0.6479, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.0585106382978726e-06, | |
| "loss": 0.6756, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.726063829787234e-06, | |
| "loss": 0.7393, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.3936170212765957e-06, | |
| "loss": 0.5521, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.0611702127659573e-06, | |
| "loss": 0.5931, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.7287234042553193e-06, | |
| "loss": 0.5324, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.3962765957446809e-06, | |
| "loss": 0.6355, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.0638297872340427e-06, | |
| "loss": 0.9237, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.313829787234043e-07, | |
| "loss": 0.8162, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.9893617021276597e-07, | |
| "loss": 0.6747, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 6.648936170212767e-08, | |
| "loss": 0.7829, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.5958611965179443, | |
| "eval_runtime": 177.9778, | |
| "eval_samples_per_second": 1.753, | |
| "eval_steps_per_second": 0.877, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "step": 1672, | |
| "total_flos": 1.4683591998352392e+19, | |
| "train_loss": 0.6908089216958964, | |
| "train_runtime": 3902.1292, | |
| "train_samples_per_second": 0.857, | |
| "train_steps_per_second": 0.428 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.7368421052631579, | |
| "eval_loss": 0.4468162953853607, | |
| "eval_runtime": 90.4466, | |
| "eval_samples_per_second": 1.05, | |
| "eval_steps_per_second": 0.531, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.7368421052631579, | |
| "eval_loss": 0.4468163251876831, | |
| "eval_runtime": 87.805, | |
| "eval_samples_per_second": 1.082, | |
| "eval_steps_per_second": 0.547, | |
| "step": 1672 | |
| } | |
| ], | |
| "max_steps": 1672, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.4683591998352392e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |