| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.955555555555556, |
| "eval_steps": 500, |
| "global_step": 280, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "learning_rate": 1.111111111111111e-06, |
| "loss": 10.1618, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 2.222222222222222e-06, |
| "loss": 10.1939, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 9.4951, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 4.444444444444444e-06, |
| "loss": 8.6598, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 5.555555555555557e-06, |
| "loss": 7.2393, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 3.9581, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 7.77777777777778e-06, |
| "loss": 2.0577, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 0.8907, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1e-05, |
| "loss": 0.3646, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 9.999664033241933e-06, |
| "loss": 0.3316, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 9.998656178117193e-06, |
| "loss": 0.29, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 9.99697657006811e-06, |
| "loss": 0.3072, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 9.99462543481167e-06, |
| "loss": 0.2946, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 9.991603088309195e-06, |
| "loss": 0.2903, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 9.98790993672386e-06, |
| "loss": 0.2589, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 9.983546476366133e-06, |
| "loss": 0.2576, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 9.978513293627068e-06, |
| "loss": 0.2416, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 9.9728110648995e-06, |
| "loss": 0.271, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 9.966440556487149e-06, |
| "loss": 0.2381, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 9.959402624501636e-06, |
| "loss": 0.236, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 9.951698214747441e-06, |
| "loss": 0.251, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 9.943328362594788e-06, |
| "loss": 0.2417, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 9.934294192840518e-06, |
| "loss": 0.225, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 9.924596919556917e-06, |
| "loss": 0.191, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 9.914237845928574e-06, |
| "loss": 0.1782, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 9.903218364077242e-06, |
| "loss": 0.1757, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 9.891539954874758e-06, |
| "loss": 0.1771, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 9.879204187744036e-06, |
| "loss": 0.2267, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 9.866212720448149e-06, |
| "loss": 0.1946, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 9.852567298867557e-06, |
| "loss": 0.1474, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 9.838269756765483e-06, |
| "loss": 0.2083, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 9.823322015541474e-06, |
| "loss": 0.1316, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 9.807726083973192e-06, |
| "loss": 0.17, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 9.791484057946465e-06, |
| "loss": 0.1188, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 9.774598120173625e-06, |
| "loss": 0.1894, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 9.75707053990018e-06, |
| "loss": 0.1519, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 9.738903672599858e-06, |
| "loss": 0.131, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 9.720099959658062e-06, |
| "loss": 0.1622, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 9.700661928043787e-06, |
| "loss": 0.1607, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 9.680592189970015e-06, |
| "loss": 0.149, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 9.659893442542683e-06, |
| "loss": 0.1657, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 9.638568467398215e-06, |
| "loss": 0.1577, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 9.61662013032972e-06, |
| "loss": 0.1561, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 9.59405138090186e-06, |
| "loss": 0.1406, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 9.570865252054462e-06, |
| "loss": 0.1226, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 9.547064859694943e-06, |
| "loss": 0.1818, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 9.52265340227957e-06, |
| "loss": 0.1775, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 9.497634160383627e-06, |
| "loss": 0.1414, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 9.472010496260545e-06, |
| "loss": 0.131, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 9.445785853390074e-06, |
| "loss": 0.1127, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 9.418963756015511e-06, |
| "loss": 0.1325, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 9.391547808670097e-06, |
| "loss": 0.0949, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 9.36354169569261e-06, |
| "loss": 0.1333, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 9.334949180732245e-06, |
| "loss": 0.1793, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 9.305774106242825e-06, |
| "loss": 0.1489, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 9.276020392966423e-06, |
| "loss": 0.1751, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 9.24569203940648e-06, |
| "loss": 0.1151, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 9.214793121290442e-06, |
| "loss": 0.0944, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 9.183327791022048e-06, |
| "loss": 0.1047, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 9.1513002771233e-06, |
| "loss": 0.083, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 9.118714883666204e-06, |
| "loss": 0.1001, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 9.085575989694358e-06, |
| "loss": 0.0604, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 9.051888048634471e-06, |
| "loss": 0.1303, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 9.017655587697885e-06, |
| "loss": 0.1208, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 8.982883207272164e-06, |
| "loss": 0.1053, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 8.947575580302879e-06, |
| "loss": 0.1324, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 8.911737451665616e-06, |
| "loss": 0.0858, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 8.875373637528336e-06, |
| "loss": 0.0868, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 8.838489024704131e-06, |
| "loss": 0.1172, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 8.801088569994523e-06, |
| "loss": 0.0814, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 8.763177299523318e-06, |
| "loss": 0.0874, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 8.724760308061172e-06, |
| "loss": 0.0579, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 8.685842758340912e-06, |
| "loss": 0.1138, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 8.646429880363746e-06, |
| "loss": 0.0584, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 8.60652697069641e-06, |
| "loss": 0.1309, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 8.566139391759378e-06, |
| "loss": 0.1021, |
| "step": 76 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 8.525272571106242e-06, |
| "loss": 0.1037, |
| "step": 77 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 8.483932000694295e-06, |
| "loss": 0.1086, |
| "step": 78 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 8.442123236146509e-06, |
| "loss": 0.1019, |
| "step": 79 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 8.399851896004914e-06, |
| "loss": 0.0721, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 8.357123660975553e-06, |
| "loss": 0.1472, |
| "step": 81 |
| }, |
| { |
| "epoch": 2.92, |
| "learning_rate": 8.313944273165068e-06, |
| "loss": 0.0891, |
| "step": 82 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 8.270319535309035e-06, |
| "loss": 0.1329, |
| "step": 83 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 8.22625530999215e-06, |
| "loss": 0.0898, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 8.181757518860387e-06, |
| "loss": 0.0509, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 8.136832141825197e-06, |
| "loss": 0.0711, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 8.091485216259886e-06, |
| "loss": 0.1521, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.13, |
| "learning_rate": 8.04572283618829e-06, |
| "loss": 0.1137, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 7.999551151465793e-06, |
| "loss": 0.1022, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 7.952976366952888e-06, |
| "loss": 0.0479, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 7.906004741681321e-06, |
| "loss": 0.0639, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 7.858642588012957e-06, |
| "loss": 0.0604, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 7.810896270791484e-06, |
| "loss": 0.0461, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 7.762772206487066e-06, |
| "loss": 0.0758, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 7.714276862334051e-06, |
| "loss": 0.0912, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.41, |
| "learning_rate": 7.66541675546186e-06, |
| "loss": 0.0638, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 7.616198452019176e-06, |
| "loss": 0.0333, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 7.566628566291537e-06, |
| "loss": 0.1232, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 7.516713759812465e-06, |
| "loss": 0.0526, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 7.466460740468246e-06, |
| "loss": 0.0772, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.59, |
| "learning_rate": 7.4158762615964744e-06, |
| "loss": 0.0282, |
| "step": 101 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 7.3649671210785024e-06, |
| "loss": 0.0691, |
| "step": 102 |
| }, |
| { |
| "epoch": 3.66, |
| "learning_rate": 7.313740160425887e-06, |
| "loss": 0.0929, |
| "step": 103 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 7.262202263860989e-06, |
| "loss": 0.064, |
| "step": 104 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 7.210360357391818e-06, |
| "loss": 0.0312, |
| "step": 105 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 7.1582214078812715e-06, |
| "loss": 0.1029, |
| "step": 106 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 7.1057924221108856e-06, |
| "loss": 0.1044, |
| "step": 107 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 7.053080445839211e-06, |
| "loss": 0.0535, |
| "step": 108 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 7.0000925628549595e-06, |
| "loss": 0.0562, |
| "step": 109 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 6.946835894025037e-06, |
| "loss": 0.101, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.95, |
| "learning_rate": 6.893317596337592e-06, |
| "loss": 0.0882, |
| "step": 111 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 6.839544861940214e-06, |
| "loss": 0.0468, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.02, |
| "learning_rate": 6.7855249171734e-06, |
| "loss": 0.076, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.05, |
| "learning_rate": 6.731265021599437e-06, |
| "loss": 0.0579, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.09, |
| "learning_rate": 6.676772467026809e-06, |
| "loss": 0.0441, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 6.622054576530275e-06, |
| "loss": 0.0615, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.16, |
| "learning_rate": 6.5671187034667465e-06, |
| "loss": 0.1432, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.2, |
| "learning_rate": 6.511972230487091e-06, |
| "loss": 0.0455, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.23, |
| "learning_rate": 6.456622568544012e-06, |
| "loss": 0.0569, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.27, |
| "learning_rate": 6.401077155896098e-06, |
| "loss": 0.0484, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.3, |
| "learning_rate": 6.345343457108238e-06, |
| "loss": 0.0493, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.34, |
| "learning_rate": 6.289428962048467e-06, |
| "loss": 0.0627, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.37, |
| "learning_rate": 6.2333411848814415e-06, |
| "loss": 0.0393, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 6.177087663058626e-06, |
| "loss": 0.0403, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.44, |
| "learning_rate": 6.120675956305363e-06, |
| "loss": 0.0705, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.48, |
| "learning_rate": 6.064113645604945e-06, |
| "loss": 0.0325, |
| "step": 126 |
| }, |
| { |
| "epoch": 4.52, |
| "learning_rate": 6.007408332179836e-06, |
| "loss": 0.0549, |
| "step": 127 |
| }, |
| { |
| "epoch": 4.55, |
| "learning_rate": 5.95056763647016e-06, |
| "loss": 0.0532, |
| "step": 128 |
| }, |
| { |
| "epoch": 4.59, |
| "learning_rate": 5.893599197109625e-06, |
| "loss": 0.0659, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.62, |
| "learning_rate": 5.836510669898984e-06, |
| "loss": 0.0271, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.66, |
| "learning_rate": 5.7793097267772e-06, |
| "loss": 0.0657, |
| "step": 131 |
| }, |
| { |
| "epoch": 4.69, |
| "learning_rate": 5.722004054790442e-06, |
| "loss": 0.0663, |
| "step": 132 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 5.664601355059044e-06, |
| "loss": 0.0398, |
| "step": 133 |
| }, |
| { |
| "epoch": 4.76, |
| "learning_rate": 5.607109341742579e-06, |
| "loss": 0.0443, |
| "step": 134 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 5.5495357410031805e-06, |
| "loss": 0.0351, |
| "step": 135 |
| }, |
| { |
| "epoch": 4.84, |
| "learning_rate": 5.491888289967241e-06, |
| "loss": 0.0328, |
| "step": 136 |
| }, |
| { |
| "epoch": 4.87, |
| "learning_rate": 5.434174735685658e-06, |
| "loss": 0.0611, |
| "step": 137 |
| }, |
| { |
| "epoch": 4.91, |
| "learning_rate": 5.376402834092721e-06, |
| "loss": 0.0557, |
| "step": 138 |
| }, |
| { |
| "epoch": 4.94, |
| "learning_rate": 5.318580348963826e-06, |
| "loss": 0.0547, |
| "step": 139 |
| }, |
| { |
| "epoch": 4.98, |
| "learning_rate": 5.260715050872119e-06, |
| "loss": 0.0421, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.01, |
| "learning_rate": 5.202814716144245e-06, |
| "loss": 0.083, |
| "step": 141 |
| }, |
| { |
| "epoch": 5.05, |
| "learning_rate": 5.144887125815301e-06, |
| "loss": 0.0348, |
| "step": 142 |
| }, |
| { |
| "epoch": 5.08, |
| "learning_rate": 5.086940064583179e-06, |
| "loss": 0.0231, |
| "step": 143 |
| }, |
| { |
| "epoch": 5.12, |
| "learning_rate": 5.028981319762399e-06, |
| "loss": 0.0217, |
| "step": 144 |
| }, |
| { |
| "epoch": 5.16, |
| "learning_rate": 4.971018680237602e-06, |
| "loss": 0.0149, |
| "step": 145 |
| }, |
| { |
| "epoch": 5.19, |
| "learning_rate": 4.913059935416822e-06, |
| "loss": 0.0315, |
| "step": 146 |
| }, |
| { |
| "epoch": 5.23, |
| "learning_rate": 4.855112874184701e-06, |
| "loss": 0.0287, |
| "step": 147 |
| }, |
| { |
| "epoch": 5.26, |
| "learning_rate": 4.797185283855756e-06, |
| "loss": 0.042, |
| "step": 148 |
| }, |
| { |
| "epoch": 5.3, |
| "learning_rate": 4.7392849491278825e-06, |
| "loss": 0.0369, |
| "step": 149 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 4.681419651036177e-06, |
| "loss": 0.0249, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.37, |
| "learning_rate": 4.6235971659072806e-06, |
| "loss": 0.0515, |
| "step": 151 |
| }, |
| { |
| "epoch": 5.4, |
| "learning_rate": 4.565825264314344e-06, |
| "loss": 0.0617, |
| "step": 152 |
| }, |
| { |
| "epoch": 5.44, |
| "learning_rate": 4.5081117100327594e-06, |
| "loss": 0.0519, |
| "step": 153 |
| }, |
| { |
| "epoch": 5.48, |
| "learning_rate": 4.450464258996822e-06, |
| "loss": 0.0411, |
| "step": 154 |
| }, |
| { |
| "epoch": 5.51, |
| "learning_rate": 4.392890658257421e-06, |
| "loss": 0.0644, |
| "step": 155 |
| }, |
| { |
| "epoch": 5.55, |
| "learning_rate": 4.335398644940958e-06, |
| "loss": 0.0709, |
| "step": 156 |
| }, |
| { |
| "epoch": 5.58, |
| "learning_rate": 4.277995945209558e-06, |
| "loss": 0.0558, |
| "step": 157 |
| }, |
| { |
| "epoch": 5.62, |
| "learning_rate": 4.220690273222802e-06, |
| "loss": 0.0335, |
| "step": 158 |
| }, |
| { |
| "epoch": 5.65, |
| "learning_rate": 4.163489330101017e-06, |
| "loss": 0.0496, |
| "step": 159 |
| }, |
| { |
| "epoch": 5.69, |
| "learning_rate": 4.106400802890377e-06, |
| "loss": 0.0252, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.72, |
| "learning_rate": 4.049432363529842e-06, |
| "loss": 0.0379, |
| "step": 161 |
| }, |
| { |
| "epoch": 5.76, |
| "learning_rate": 3.992591667820166e-06, |
| "loss": 0.0435, |
| "step": 162 |
| }, |
| { |
| "epoch": 5.8, |
| "learning_rate": 3.935886354395057e-06, |
| "loss": 0.0253, |
| "step": 163 |
| }, |
| { |
| "epoch": 5.83, |
| "learning_rate": 3.8793240436946385e-06, |
| "loss": 0.0348, |
| "step": 164 |
| }, |
| { |
| "epoch": 5.87, |
| "learning_rate": 3.822912336941375e-06, |
| "loss": 0.0742, |
| "step": 165 |
| }, |
| { |
| "epoch": 5.9, |
| "learning_rate": 3.7666588151185584e-06, |
| "loss": 0.0388, |
| "step": 166 |
| }, |
| { |
| "epoch": 5.94, |
| "learning_rate": 3.7105710379515335e-06, |
| "loss": 0.045, |
| "step": 167 |
| }, |
| { |
| "epoch": 5.97, |
| "learning_rate": 3.6546565428917623e-06, |
| "loss": 0.0836, |
| "step": 168 |
| }, |
| { |
| "epoch": 6.01, |
| "learning_rate": 3.5989228441039024e-06, |
| "loss": 0.0301, |
| "step": 169 |
| }, |
| { |
| "epoch": 6.04, |
| "learning_rate": 3.543377431455991e-06, |
| "loss": 0.0243, |
| "step": 170 |
| }, |
| { |
| "epoch": 6.08, |
| "learning_rate": 3.4880277695129095e-06, |
| "loss": 0.0473, |
| "step": 171 |
| }, |
| { |
| "epoch": 6.12, |
| "learning_rate": 3.432881296533257e-06, |
| "loss": 0.0413, |
| "step": 172 |
| }, |
| { |
| "epoch": 6.15, |
| "learning_rate": 3.377945423469727e-06, |
| "loss": 0.0394, |
| "step": 173 |
| }, |
| { |
| "epoch": 6.19, |
| "learning_rate": 3.323227532973193e-06, |
| "loss": 0.043, |
| "step": 174 |
| }, |
| { |
| "epoch": 6.22, |
| "learning_rate": 3.268734978400564e-06, |
| "loss": 0.053, |
| "step": 175 |
| }, |
| { |
| "epoch": 6.26, |
| "learning_rate": 3.214475082826602e-06, |
| "loss": 0.0172, |
| "step": 176 |
| }, |
| { |
| "epoch": 6.29, |
| "learning_rate": 3.160455138059788e-06, |
| "loss": 0.0445, |
| "step": 177 |
| }, |
| { |
| "epoch": 6.33, |
| "learning_rate": 3.1066824036624086e-06, |
| "loss": 0.0601, |
| "step": 178 |
| }, |
| { |
| "epoch": 6.36, |
| "learning_rate": 3.053164105974964e-06, |
| "loss": 0.0182, |
| "step": 179 |
| }, |
| { |
| "epoch": 6.4, |
| "learning_rate": 2.999907437145042e-06, |
| "loss": 0.0437, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.44, |
| "learning_rate": 2.946919554160792e-06, |
| "loss": 0.0159, |
| "step": 181 |
| }, |
| { |
| "epoch": 6.47, |
| "learning_rate": 2.8942075778891153e-06, |
| "loss": 0.0147, |
| "step": 182 |
| }, |
| { |
| "epoch": 6.51, |
| "learning_rate": 2.84177859211873e-06, |
| "loss": 0.0345, |
| "step": 183 |
| }, |
| { |
| "epoch": 6.54, |
| "learning_rate": 2.7896396426081844e-06, |
| "loss": 0.0125, |
| "step": 184 |
| }, |
| { |
| "epoch": 6.58, |
| "learning_rate": 2.7377977361390118e-06, |
| "loss": 0.0198, |
| "step": 185 |
| }, |
| { |
| "epoch": 6.61, |
| "learning_rate": 2.6862598395741136e-06, |
| "loss": 0.0363, |
| "step": 186 |
| }, |
| { |
| "epoch": 6.65, |
| "learning_rate": 2.6350328789215e-06, |
| "loss": 0.0411, |
| "step": 187 |
| }, |
| { |
| "epoch": 6.68, |
| "learning_rate": 2.584123738403527e-06, |
| "loss": 0.0116, |
| "step": 188 |
| }, |
| { |
| "epoch": 6.72, |
| "learning_rate": 2.533539259531757e-06, |
| "loss": 0.032, |
| "step": 189 |
| }, |
| { |
| "epoch": 6.76, |
| "learning_rate": 2.483286240187538e-06, |
| "loss": 0.0145, |
| "step": 190 |
| }, |
| { |
| "epoch": 6.79, |
| "learning_rate": 2.433371433708465e-06, |
| "loss": 0.0464, |
| "step": 191 |
| }, |
| { |
| "epoch": 6.83, |
| "learning_rate": 2.383801547980826e-06, |
| "loss": 0.0168, |
| "step": 192 |
| }, |
| { |
| "epoch": 6.86, |
| "learning_rate": 2.3345832445381415e-06, |
| "loss": 0.0271, |
| "step": 193 |
| }, |
| { |
| "epoch": 6.9, |
| "learning_rate": 2.2857231376659517e-06, |
| "loss": 0.0575, |
| "step": 194 |
| }, |
| { |
| "epoch": 6.93, |
| "learning_rate": 2.237227793512935e-06, |
| "loss": 0.0713, |
| "step": 195 |
| }, |
| { |
| "epoch": 6.97, |
| "learning_rate": 2.1891037292085177e-06, |
| "loss": 0.036, |
| "step": 196 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 2.141357411987044e-06, |
| "loss": 0.0475, |
| "step": 197 |
| }, |
| { |
| "epoch": 7.04, |
| "learning_rate": 2.0939952583186806e-06, |
| "loss": 0.0223, |
| "step": 198 |
| }, |
| { |
| "epoch": 7.08, |
| "learning_rate": 2.0470236330471125e-06, |
| "loss": 0.0453, |
| "step": 199 |
| }, |
| { |
| "epoch": 7.11, |
| "learning_rate": 2.000448848534209e-06, |
| "loss": 0.0248, |
| "step": 200 |
| }, |
| { |
| "epoch": 7.15, |
| "learning_rate": 1.9542771638117124e-06, |
| "loss": 0.0239, |
| "step": 201 |
| }, |
| { |
| "epoch": 7.18, |
| "learning_rate": 1.908514783740114e-06, |
| "loss": 0.0474, |
| "step": 202 |
| }, |
| { |
| "epoch": 7.22, |
| "learning_rate": 1.8631678581748059e-06, |
| "loss": 0.0674, |
| "step": 203 |
| }, |
| { |
| "epoch": 7.25, |
| "learning_rate": 1.8182424811396131e-06, |
| "loss": 0.0091, |
| "step": 204 |
| }, |
| { |
| "epoch": 7.29, |
| "learning_rate": 1.7737446900078503e-06, |
| "loss": 0.0438, |
| "step": 205 |
| }, |
| { |
| "epoch": 7.32, |
| "learning_rate": 1.7296804646909654e-06, |
| "loss": 0.0415, |
| "step": 206 |
| }, |
| { |
| "epoch": 7.36, |
| "learning_rate": 1.686055726834932e-06, |
| "loss": 0.008, |
| "step": 207 |
| }, |
| { |
| "epoch": 7.4, |
| "learning_rate": 1.6428763390244462e-06, |
| "loss": 0.0612, |
| "step": 208 |
| }, |
| { |
| "epoch": 7.43, |
| "learning_rate": 1.6001481039950872e-06, |
| "loss": 0.0166, |
| "step": 209 |
| }, |
| { |
| "epoch": 7.47, |
| "learning_rate": 1.557876763853493e-06, |
| "loss": 0.0299, |
| "step": 210 |
| }, |
| { |
| "epoch": 7.5, |
| "learning_rate": 1.5160679993057048e-06, |
| "loss": 0.0218, |
| "step": 211 |
| }, |
| { |
| "epoch": 7.54, |
| "learning_rate": 1.4747274288937597e-06, |
| "loss": 0.0469, |
| "step": 212 |
| }, |
| { |
| "epoch": 7.57, |
| "learning_rate": 1.4338606082406232e-06, |
| "loss": 0.0185, |
| "step": 213 |
| }, |
| { |
| "epoch": 7.61, |
| "learning_rate": 1.3934730293035935e-06, |
| "loss": 0.0105, |
| "step": 214 |
| }, |
| { |
| "epoch": 7.64, |
| "learning_rate": 1.353570119636255e-06, |
| "loss": 0.0178, |
| "step": 215 |
| }, |
| { |
| "epoch": 7.68, |
| "learning_rate": 1.314157241659089e-06, |
| "loss": 0.0219, |
| "step": 216 |
| }, |
| { |
| "epoch": 7.72, |
| "learning_rate": 1.2752396919388293e-06, |
| "loss": 0.0536, |
| "step": 217 |
| }, |
| { |
| "epoch": 7.75, |
| "learning_rate": 1.236822700476683e-06, |
| "loss": 0.0254, |
| "step": 218 |
| }, |
| { |
| "epoch": 7.79, |
| "learning_rate": 1.1989114300054782e-06, |
| "loss": 0.012, |
| "step": 219 |
| }, |
| { |
| "epoch": 7.82, |
| "learning_rate": 1.1615109752958715e-06, |
| "loss": 0.0375, |
| "step": 220 |
| }, |
| { |
| "epoch": 7.86, |
| "learning_rate": 1.124626362471668e-06, |
| "loss": 0.0367, |
| "step": 221 |
| }, |
| { |
| "epoch": 7.89, |
| "learning_rate": 1.0882625483343846e-06, |
| "loss": 0.0383, |
| "step": 222 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 1.0524244196971228e-06, |
| "loss": 0.037, |
| "step": 223 |
| }, |
| { |
| "epoch": 7.96, |
| "learning_rate": 1.0171167927278369e-06, |
| "loss": 0.0348, |
| "step": 224 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 9.82344412302117e-07, |
| "loss": 0.0205, |
| "step": 225 |
| }, |
| { |
| "epoch": 8.04, |
| "learning_rate": 9.48111951365529e-07, |
| "loss": 0.047, |
| "step": 226 |
| }, |
| { |
| "epoch": 8.07, |
| "learning_rate": 9.144240103056439e-07, |
| "loss": 0.0519, |
| "step": 227 |
| }, |
| { |
| "epoch": 8.11, |
| "learning_rate": 8.812851163337976e-07, |
| "loss": 0.0138, |
| "step": 228 |
| }, |
| { |
| "epoch": 8.14, |
| "learning_rate": 8.486997228767013e-07, |
| "loss": 0.0184, |
| "step": 229 |
| }, |
| { |
| "epoch": 8.18, |
| "learning_rate": 8.166722089779539e-07, |
| "loss": 0.0108, |
| "step": 230 |
| }, |
| { |
| "epoch": 8.21, |
| "learning_rate": 7.852068787095601e-07, |
| "loss": 0.0372, |
| "step": 231 |
| }, |
| { |
| "epoch": 8.25, |
| "learning_rate": 7.543079605935222e-07, |
| "loss": 0.0203, |
| "step": 232 |
| }, |
| { |
| "epoch": 8.28, |
| "learning_rate": 7.239796070335775e-07, |
| "loss": 0.0109, |
| "step": 233 |
| }, |
| { |
| "epoch": 8.32, |
| "learning_rate": 6.942258937571772e-07, |
| "loss": 0.0257, |
| "step": 234 |
| }, |
| { |
| "epoch": 8.36, |
| "learning_rate": 6.650508192677546e-07, |
| "loss": 0.0596, |
| "step": 235 |
| }, |
| { |
| "epoch": 8.39, |
| "learning_rate": 6.364583043073902e-07, |
| "loss": 0.0165, |
| "step": 236 |
| }, |
| { |
| "epoch": 8.43, |
| "learning_rate": 6.08452191329903e-07, |
| "loss": 0.021, |
| "step": 237 |
| }, |
| { |
| "epoch": 8.46, |
| "learning_rate": 5.810362439844897e-07, |
| "loss": 0.0186, |
| "step": 238 |
| }, |
| { |
| "epoch": 8.5, |
| "learning_rate": 5.542141466099271e-07, |
| "loss": 0.0444, |
| "step": 239 |
| }, |
| { |
| "epoch": 8.53, |
| "learning_rate": 5.279895037394567e-07, |
| "loss": 0.0403, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.57, |
| "learning_rate": 5.02365839616375e-07, |
| "loss": 0.0164, |
| "step": 241 |
| }, |
| { |
| "epoch": 8.6, |
| "learning_rate": 4.773465977204311e-07, |
| "loss": 0.0173, |
| "step": 242 |
| }, |
| { |
| "epoch": 8.64, |
| "learning_rate": 4.529351403050586e-07, |
| "loss": 0.0195, |
| "step": 243 |
| }, |
| { |
| "epoch": 8.68, |
| "learning_rate": 4.2913474794554044e-07, |
| "loss": 0.0156, |
| "step": 244 |
| }, |
| { |
| "epoch": 8.71, |
| "learning_rate": 4.0594861909814266e-07, |
| "loss": 0.0299, |
| "step": 245 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 3.833798696702801e-07, |
| "loss": 0.0563, |
| "step": 246 |
| }, |
| { |
| "epoch": 8.78, |
| "learning_rate": 3.6143153260178586e-07, |
| "loss": 0.0224, |
| "step": 247 |
| }, |
| { |
| "epoch": 8.82, |
| "learning_rate": 3.401065574573187e-07, |
| "loss": 0.0621, |
| "step": 248 |
| }, |
| { |
| "epoch": 8.85, |
| "learning_rate": 3.194078100299863e-07, |
| "loss": 0.0432, |
| "step": 249 |
| }, |
| { |
| "epoch": 8.89, |
| "learning_rate": 2.9933807195621446e-07, |
| "loss": 0.0469, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.92, |
| "learning_rate": 2.799000403419383e-07, |
| "loss": 0.0176, |
| "step": 251 |
| }, |
| { |
| "epoch": 8.96, |
| "learning_rate": 2.610963274001438e-07, |
| "loss": 0.0515, |
| "step": 252 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 2.4292946009982163e-07, |
| "loss": 0.013, |
| "step": 253 |
| }, |
| { |
| "epoch": 9.03, |
| "learning_rate": 2.2540187982637628e-07, |
| "loss": 0.0077, |
| "step": 254 |
| }, |
| { |
| "epoch": 9.07, |
| "learning_rate": 2.0851594205353543e-07, |
| "loss": 0.0332, |
| "step": 255 |
| }, |
| { |
| "epoch": 9.1, |
| "learning_rate": 1.922739160268089e-07, |
| "loss": 0.0073, |
| "step": 256 |
| }, |
| { |
| "epoch": 9.14, |
| "learning_rate": 1.7667798445852703e-07, |
| "loss": 0.0232, |
| "step": 257 |
| }, |
| { |
| "epoch": 9.17, |
| "learning_rate": 1.6173024323451747e-07, |
| "loss": 0.0402, |
| "step": 258 |
| }, |
| { |
| "epoch": 9.21, |
| "learning_rate": 1.4743270113244278e-07, |
| "loss": 0.0296, |
| "step": 259 |
| }, |
| { |
| "epoch": 9.24, |
| "learning_rate": 1.3378727955185243e-07, |
| "loss": 0.0391, |
| "step": 260 |
| }, |
| { |
| "epoch": 9.28, |
| "learning_rate": 1.207958122559655e-07, |
| "loss": 0.0077, |
| "step": 261 |
| }, |
| { |
| "epoch": 9.32, |
| "learning_rate": 1.084600451252421e-07, |
| "loss": 0.0473, |
| "step": 262 |
| }, |
| { |
| "epoch": 9.35, |
| "learning_rate": 9.678163592275858e-08, |
| "loss": 0.0264, |
| "step": 263 |
| }, |
| { |
| "epoch": 9.39, |
| "learning_rate": 8.576215407142652e-08, |
| "loss": 0.0283, |
| "step": 264 |
| }, |
| { |
| "epoch": 9.42, |
| "learning_rate": 7.540308044308442e-08, |
| "loss": 0.0337, |
| "step": 265 |
| }, |
| { |
| "epoch": 9.46, |
| "learning_rate": 6.570580715948404e-08, |
| "loss": 0.0344, |
| "step": 266 |
| }, |
| { |
| "epoch": 9.49, |
| "learning_rate": 5.6671637405212865e-08, |
| "loss": 0.0269, |
| "step": 267 |
| }, |
| { |
| "epoch": 9.53, |
| "learning_rate": 4.830178525256079e-08, |
| "loss": 0.0306, |
| "step": 268 |
| }, |
| { |
| "epoch": 9.56, |
| "learning_rate": 4.0597375498365175e-08, |
| "loss": 0.016, |
| "step": 269 |
| }, |
| { |
| "epoch": 9.6, |
| "learning_rate": 3.355944351285278e-08, |
| "loss": 0.0409, |
| "step": 270 |
| }, |
| { |
| "epoch": 9.64, |
| "learning_rate": 2.718893510050058e-08, |
| "loss": 0.0232, |
| "step": 271 |
| }, |
| { |
| "epoch": 9.67, |
| "learning_rate": 2.1486706372932375e-08, |
| "loss": 0.0145, |
| "step": 272 |
| }, |
| { |
| "epoch": 9.71, |
| "learning_rate": 1.6453523633868096e-08, |
| "loss": 0.0374, |
| "step": 273 |
| }, |
| { |
| "epoch": 9.74, |
| "learning_rate": 1.2090063276142261e-08, |
| "loss": 0.0485, |
| "step": 274 |
| }, |
| { |
| "epoch": 9.78, |
| "learning_rate": 8.396911690807253e-09, |
| "loss": 0.0471, |
| "step": 275 |
| }, |
| { |
| "epoch": 9.81, |
| "learning_rate": 5.374565188329683e-09, |
| "loss": 0.0492, |
| "step": 276 |
| }, |
| { |
| "epoch": 9.85, |
| "learning_rate": 3.0234299318909755e-09, |
| "loss": 0.0523, |
| "step": 277 |
| }, |
| { |
| "epoch": 9.88, |
| "learning_rate": 1.3438218828076831e-09, |
| "loss": 0.0252, |
| "step": 278 |
| }, |
| { |
| "epoch": 9.92, |
| "learning_rate": 3.359667580682402e-10, |
| "loss": 0.0394, |
| "step": 279 |
| }, |
| { |
| "epoch": 9.96, |
| "learning_rate": 0.0, |
| "loss": 0.0269, |
| "step": 280 |
| }, |
| { |
| "epoch": 9.96, |
| "step": 280, |
| "total_flos": 1.0363597546666391e+21, |
| "train_loss": 0.2612905190725412, |
| "train_runtime": 5871.1818, |
| "train_samples_per_second": 6.132, |
| "train_steps_per_second": 0.048 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 280, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 200, |
| "total_flos": 1.0363597546666391e+21, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
