| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 396, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 1.0912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.1973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-06, | |
| "loss": 1.8214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.1457, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 2.2347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4613, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 1.9206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.7732, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.8977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.1657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.9736, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2143, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9999665339174013e-05, | |
| "loss": 0.9434, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9998661379095622e-05, | |
| "loss": 0.9365, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9996988186962044e-05, | |
| "loss": 1.0491, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9994645874763657e-05, | |
| "loss": 1.3624, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9991634599276488e-05, | |
| "loss": 0.9719, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9987954562051724e-05, | |
| "loss": 1.0088, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9983606009402224e-05, | |
| "loss": 0.8494, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9978589232386036e-05, | |
| "loss": 1.4835, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9972904566786903e-05, | |
| "loss": 0.4601, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.9966552393091804e-05, | |
| "loss": 1.2571, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.995953313646548e-05, | |
| "loss": 0.6248, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.995184726672197e-05, | |
| "loss": 0.4497, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.9943495298293182e-05, | |
| "loss": 0.7671, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.9934477790194445e-05, | |
| "loss": 0.8551, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.9924795345987103e-05, | |
| "loss": 0.9292, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9914448613738107e-05, | |
| "loss": 0.9321, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.990343828597665e-05, | |
| "loss": 0.9564, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.989176509964781e-05, | |
| "loss": 0.7888, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.9879429836063228e-05, | |
| "loss": 0.3541, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.9866433320848793e-05, | |
| "loss": 0.7242, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.9852776423889414e-05, | |
| "loss": 0.9379, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.9838460059270775e-05, | |
| "loss": 1.5263, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.982348518521816e-05, | |
| "loss": 1.241, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.9807852804032306e-05, | |
| "loss": 0.585, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.979156396202234e-05, | |
| "loss": 0.4718, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.977461974943572e-05, | |
| "loss": 0.8916, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.9757021300385288e-05, | |
| "loss": 0.7767, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.9738769792773338e-05, | |
| "loss": 0.7323, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.9719866448212794e-05, | |
| "loss": 0.8039, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.9700312531945444e-05, | |
| "loss": 0.9728, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.9680109352757228e-05, | |
| "loss": 1.4139, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.9659258262890683e-05, | |
| "loss": 0.5891, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.96377606579544e-05, | |
| "loss": 0.8547, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.9615617976829622e-05, | |
| "loss": 0.6453, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.959283170157394e-05, | |
| "loss": 0.9798, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.956940335732209e-05, | |
| "loss": 0.8966, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.9545334512183886e-05, | |
| "loss": 0.5067, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.9520626777139243e-05, | |
| "loss": 1.1425, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.949528180593037e-05, | |
| "loss": 1.3068, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.946930129495106e-05, | |
| "loss": 0.7687, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.944268698313317e-05, | |
| "loss": 0.9368, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.941544065183021e-05, | |
| "loss": 0.6697, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9387564124698133e-05, | |
| "loss": 0.6488, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.935905926757326e-05, | |
| "loss": 0.9918, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.932992798834739e-05, | |
| "loss": 0.7319, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.930017223684012e-05, | |
| "loss": 0.6621, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.926979400466833e-05, | |
| "loss": 0.6273, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.9238795325112867e-05, | |
| "loss": 0.8412, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.9207178272982477e-05, | |
| "loss": 0.7979, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.9174944964474914e-05, | |
| "loss": 1.0536, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.914209755703531e-05, | |
| "loss": 0.3799, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.910863824921176e-05, | |
| "loss": 1.4296, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.9074569280508188e-05, | |
| "loss": 0.637, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9039892931234434e-05, | |
| "loss": 1.3104, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.900461152235364e-05, | |
| "loss": 0.7303, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.8968727415326885e-05, | |
| "loss": 0.3171, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.8932243011955154e-05, | |
| "loss": 0.3529, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.8895160754218562e-05, | |
| "loss": 1.5304, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.885748312411291e-05, | |
| "loss": 1.1709, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.881921264348355e-05, | |
| "loss": 1.4026, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.8780351873856627e-05, | |
| "loss": 0.5411, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.874090341626759e-05, | |
| "loss": 0.3518, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.8700869911087115e-05, | |
| "loss": 1.2801, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 1.1898, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.8619058515047746e-05, | |
| "loss": 1.1509, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.8577286100002723e-05, | |
| "loss": 1.0352, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.8534939588627506e-05, | |
| "loss": 0.8594, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.849202181526579e-05, | |
| "loss": 0.4596, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.8448535652497073e-05, | |
| "loss": 0.7898, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.840448401094438e-05, | |
| "loss": 0.5138, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.835986983907947e-05, | |
| "loss": 1.443, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8314696123025456e-05, | |
| "loss": 0.321, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8268965886356965e-05, | |
| "loss": 0.4334, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.822268218989775e-05, | |
| "loss": 1.2314, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.817584813151584e-05, | |
| "loss": 0.667, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.8128466845916156e-05, | |
| "loss": 0.399, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.8080541504430732e-05, | |
| "loss": 1.1662, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.803207531480645e-05, | |
| "loss": 0.7352, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.7983071520990316e-05, | |
| "loss": 0.7251, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.7933533402912354e-05, | |
| "loss": 0.5131, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.7883464276266064e-05, | |
| "loss": 0.9221, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.7832867492286506e-05, | |
| "loss": 0.6758, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.778174643752598e-05, | |
| "loss": 0.6372, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.773010453362737e-05, | |
| "loss": 0.4088, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.7677945237095122e-05, | |
| "loss": 0.8338, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.7625272039063884e-05, | |
| "loss": 0.5329, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7572088465064847e-05, | |
| "loss": 0.7356, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.7518398074789776e-05, | |
| "loss": 0.5893, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.746420446185274e-05, | |
| "loss": 1.0192, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.7409511253549592e-05, | |
| "loss": 0.6132, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.735432211061519e-05, | |
| "loss": 0.5129, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.7298640726978357e-05, | |
| "loss": 1.3157, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.7242470829514674e-05, | |
| "loss": 1.1499, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.718581617779698e-05, | |
| "loss": 0.6059, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.71286805638438e-05, | |
| "loss": 0.7768, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.3944, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7012981778008245e-05, | |
| "loss": 0.4616, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.6954426350096118e-05, | |
| "loss": 0.392, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.689540544737067e-05, | |
| "loss": 0.4423, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.6835923020228714e-05, | |
| "loss": 0.5843, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.6775983049957888e-05, | |
| "loss": 0.4968, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.6715589548470187e-05, | |
| "loss": 0.6635, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.6654746558033424e-05, | |
| "loss": 0.5345, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.659345815100069e-05, | |
| "loss": 0.3274, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.6531728429537766e-05, | |
| "loss": 0.758, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.6469561525348576e-05, | |
| "loss": 0.6526, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.640696159939861e-05, | |
| "loss": 0.5578, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.6343932841636455e-05, | |
| "loss": 0.9087, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6280479470713343e-05, | |
| "loss": 0.3794, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6216605733700776e-05, | |
| "loss": 0.6467, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.615231590580627e-05, | |
| "loss": 0.5239, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.608761429008721e-05, | |
| "loss": 0.4212, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.6022505217162824e-05, | |
| "loss": 0.3344, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.5956993044924334e-05, | |
| "loss": 1.239, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.5891082158243283e-05, | |
| "loss": 0.8274, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.5824776968678024e-05, | |
| "loss": 0.5102, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5758081914178457e-05, | |
| "loss": 0.8099, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5691001458788984e-05, | |
| "loss": 0.9807, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.5623540092349735e-05, | |
| "loss": 0.6831, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5555702330196024e-05, | |
| "loss": 0.3847, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.548749271285616e-05, | |
| "loss": 0.9832, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.5418915805747518e-05, | |
| "loss": 0.4993, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.5349976198870974e-05, | |
| "loss": 0.2899, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.528067850650368e-05, | |
| "loss": 0.52, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.5211027366890237e-05, | |
| "loss": 0.6157, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.5141027441932217e-05, | |
| "loss": 0.2785, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.5070683416876172e-05, | |
| "loss": 0.4745, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.2615, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.4928981922297842e-05, | |
| "loss": 0.5145, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.4857633937163402e-05, | |
| "loss": 0.347, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.4785960820071812e-05, | |
| "loss": 0.2387, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.4713967368259981e-05, | |
| "loss": 0.7635, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.4641658400405516e-05, | |
| "loss": 0.3601, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.4569038756304209e-05, | |
| "loss": 0.3369, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.4496113296546068e-05, | |
| "loss": 0.3824, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.4422886902190014e-05, | |
| "loss": 0.287, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.4349364474437172e-05, | |
| "loss": 0.9414, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.4275550934302822e-05, | |
| "loss": 0.4918, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.4201451222287026e-05, | |
| "loss": 0.5476, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.4127070298043949e-05, | |
| "loss": 0.2683, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.4052413140049898e-05, | |
| "loss": 0.2498, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.3977484745270112e-05, | |
| "loss": 0.4185, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.3902290128824282e-05, | |
| "loss": 0.3995, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.3826834323650899e-05, | |
| "loss": 0.3908, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.375112238017038e-05, | |
| "loss": 0.2061, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.3675159365947038e-05, | |
| "loss": 0.3934, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.3598950365349884e-05, | |
| "loss": 0.3242, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.3522500479212337e-05, | |
| "loss": 0.4355, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.3445814824490806e-05, | |
| "loss": 0.4813, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.3368898533922202e-05, | |
| "loss": 0.4271, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.329175675568039e-05, | |
| "loss": 0.2628, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.3214394653031616e-05, | |
| "loss": 0.2714, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.3136817403988918e-05, | |
| "loss": 0.3173, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.3059030200965536e-05, | |
| "loss": 0.2928, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.2981038250427402e-05, | |
| "loss": 0.3756, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.2902846772544625e-05, | |
| "loss": 0.25, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.2824461000842126e-05, | |
| "loss": 0.389, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.2745886181849325e-05, | |
| "loss": 0.3511, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.2667127574748985e-05, | |
| "loss": 0.6542, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.2588190451025209e-05, | |
| "loss": 0.1331, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.2509080094110604e-05, | |
| "loss": 0.4515, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.242980179903264e-05, | |
| "loss": 0.4946, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.2350360872059268e-05, | |
| "loss": 0.453, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.2270762630343734e-05, | |
| "loss": 0.3207, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.2191012401568698e-05, | |
| "loss": 0.2817, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.2111115523589651e-05, | |
| "loss": 0.5249, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.203107734407763e-05, | |
| "loss": 0.616, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.1950903220161286e-05, | |
| "loss": 0.3736, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.1870598518068321e-05, | |
| "loss": 0.3653, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.1790168612766331e-05, | |
| "loss": 0.3652, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.1709618887603013e-05, | |
| "loss": 0.4013, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.162895473394589e-05, | |
| "loss": 0.3294, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.1548181550821411e-05, | |
| "loss": 0.6704, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.1467304744553618e-05, | |
| "loss": 0.3813, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.1386329728402269e-05, | |
| "loss": 0.3289, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.130526192220052e-05, | |
| "loss": 0.492, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.1224106751992164e-05, | |
| "loss": 0.6376, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.1142869649668467e-05, | |
| "loss": 0.4514, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.1061556052604579e-05, | |
| "loss": 0.1564, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.098017140329561e-05, | |
| "loss": 0.2852, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.089872114899235e-05, | |
| "loss": 0.3373, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.0817210741336684e-05, | |
| "loss": 0.2011, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.0735645635996676e-05, | |
| "loss": 0.6372, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.0654031292301432e-05, | |
| "loss": 0.1721, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.057237317287569e-05, | |
| "loss": 0.314, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0490676743274181e-05, | |
| "loss": 0.3923, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.0408947471615836e-05, | |
| "loss": 0.4527, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.0327190828217763e-05, | |
| "loss": 0.2541, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.0245412285229124e-05, | |
| "loss": 0.1693, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.0163617316264869e-05, | |
| "loss": 0.7895, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.0081811396039374e-05, | |
| "loss": 0.6897, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3858, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.918188603960632e-06, | |
| "loss": 0.495, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.836382683735133e-06, | |
| "loss": 0.2469, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.75458771477088e-06, | |
| "loss": 0.5765, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.67280917178224e-06, | |
| "loss": 0.4859, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.591052528384168e-06, | |
| "loss": 0.2056, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 9.50932325672582e-06, | |
| "loss": 0.5528, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.427626827124316e-06, | |
| "loss": 0.2854, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.34596870769857e-06, | |
| "loss": 0.2586, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.264354364003327e-06, | |
| "loss": 0.2958, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.182789258663321e-06, | |
| "loss": 0.2754, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.101278851007651e-06, | |
| "loss": 0.1672, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.019828596704394e-06, | |
| "loss": 0.474, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.938443947395428e-06, | |
| "loss": 0.7002, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.857130350331535e-06, | |
| "loss": 0.487, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.77589324800784e-06, | |
| "loss": 0.5058, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.694738077799487e-06, | |
| "loss": 0.3104, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.613670271597733e-06, | |
| "loss": 0.2636, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.532695255446384e-06, | |
| "loss": 0.2949, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.451818449178592e-06, | |
| "loss": 0.4606, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.371045266054114e-06, | |
| "loss": 0.2796, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.290381112396989e-06, | |
| "loss": 0.3996, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.209831387233675e-06, | |
| "loss": 0.7789, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.12940148193168e-06, | |
| "loss": 0.3954, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.04909677983872e-06, | |
| "loss": 0.293, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.968922655922375e-06, | |
| "loss": 0.2245, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 7.888884476410348e-06, | |
| "loss": 0.3602, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.808987598431303e-06, | |
| "loss": 0.1273, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 7.72923736965627e-06, | |
| "loss": 0.2048, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.649639127940734e-06, | |
| "loss": 0.4198, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.570198200967363e-06, | |
| "loss": 0.536, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.490919905889403e-06, | |
| "loss": 0.6785, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.411809548974792e-06, | |
| "loss": 0.5334, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.332872425251017e-06, | |
| "loss": 0.6093, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.25411381815068e-06, | |
| "loss": 0.2398, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.175538999157876e-06, | |
| "loss": 0.2231, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.097153227455379e-06, | |
| "loss": 0.2658, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.018961749572604e-06, | |
| "loss": 0.3377, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 6.940969799034465e-06, | |
| "loss": 0.2729, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 6.8631825960110866e-06, | |
| "loss": 0.2559, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 6.785605346968387e-06, | |
| "loss": 0.5784, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.708243244319611e-06, | |
| "loss": 0.2154, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.631101466077801e-06, | |
| "loss": 0.3358, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 6.554185175509196e-06, | |
| "loss": 0.8953, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.4774995207876654e-06, | |
| "loss": 0.3955, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.401049634650119e-06, | |
| "loss": 0.554, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.3248406340529665e-06, | |
| "loss": 0.2883, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.2488776198296195e-06, | |
| "loss": 0.21, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.173165676349103e-06, | |
| "loss": 0.4709, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.097709871175723e-06, | |
| "loss": 0.4529, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.02251525472989e-06, | |
| "loss": 0.7958, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 5.947586859950103e-06, | |
| "loss": 0.5224, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 5.872929701956054e-06, | |
| "loss": 0.4974, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 5.798548777712977e-06, | |
| "loss": 0.3196, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 5.724449065697182e-06, | |
| "loss": 0.2064, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 5.650635525562829e-06, | |
| "loss": 0.6573, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.5771130978099896e-06, | |
| "loss": 0.308, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 5.503886703453933e-06, | |
| "loss": 0.4254, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 5.430961243695794e-06, | |
| "loss": 0.2067, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 5.358341599594483e-06, | |
| "loss": 0.2164, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.286032631740023e-06, | |
| "loss": 0.71, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.214039179928194e-06, | |
| "loss": 0.4526, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5.142366062836599e-06, | |
| "loss": 0.2104, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5.071018077702161e-06, | |
| "loss": 0.2086, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.1537, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.9293165831238295e-06, | |
| "loss": 0.0942, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.858972558067784e-06, | |
| "loss": 0.1073, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.788972633109768e-06, | |
| "loss": 0.2291, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.7193214934963204e-06, | |
| "loss": 0.0834, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.65002380112903e-06, | |
| "loss": 0.1469, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.581084194252486e-06, | |
| "loss": 0.2772, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.5125072871438426e-06, | |
| "loss": 0.1829, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.444297669803981e-06, | |
| "loss": 0.1034, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.3764599076502705e-06, | |
| "loss": 0.1104, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.308998541211016e-06, | |
| "loss": 0.1409, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.241918085821547e-06, | |
| "loss": 0.1215, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.17522303132198e-06, | |
| "loss": 0.1462, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.108917841756717e-06, | |
| "loss": 0.2358, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.043006955075667e-06, | |
| "loss": 0.2254, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.977494782837182e-06, | |
| "loss": 0.1637, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.912385709912794e-06, | |
| "loss": 0.1373, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.847684094193733e-06, | |
| "loss": 0.2059, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 3.7833942662992286e-06, | |
| "loss": 0.1392, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 3.7195205292866588e-06, | |
| "loss": 0.1367, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.6560671583635467e-06, | |
| "loss": 0.1172, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.593038400601395e-06, | |
| "loss": 0.0897, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.5304384746514273e-06, | |
| "loss": 0.2328, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.468271570462235e-06, | |
| "loss": 0.2492, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.4065418489993118e-06, | |
| "loss": 0.1344, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.3452534419665793e-06, | |
| "loss": 0.1469, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.284410451529816e-06, | |
| "loss": 0.1339, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.224016950042114e-06, | |
| "loss": 0.0994, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.1640769797712865e-06, | |
| "loss": 0.2619, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.1045945526293307e-06, | |
| "loss": 0.0797, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.0455736499038847e-06, | |
| "loss": 0.181, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.9870182219917564e-06, | |
| "loss": 0.2399, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 0.1349, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.8713194361562036e-06, | |
| "loss": 0.1067, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2.8141838222030195e-06, | |
| "loss": 0.1468, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.7575291704853325e-06, | |
| "loss": 0.1159, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.7013592730216464e-06, | |
| "loss": 0.1167, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.6456778893848144e-06, | |
| "loss": 0.2314, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.5904887464504115e-06, | |
| "loss": 0.2353, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.5357955381472622e-06, | |
| "loss": 0.1086, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.4816019252102274e-06, | |
| "loss": 0.352, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.4279115349351546e-06, | |
| "loss": 0.2142, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.3747279609361197e-06, | |
| "loss": 0.1142, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.3220547629048796e-06, | |
| "loss": 0.1481, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.26989546637263e-06, | |
| "loss": 0.0982, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.2182535624740233e-06, | |
| "loss": 0.149, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.1671325077134963e-06, | |
| "loss": 0.1391, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.116535723733938e-06, | |
| "loss": 0.1366, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.0664665970876496e-06, | |
| "loss": 0.1159, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.0169284790096856e-06, | |
| "loss": 0.161, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.967924685193552e-06, | |
| "loss": 0.1869, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.919458495569271e-06, | |
| "loss": 0.2142, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.8715331540838488e-06, | |
| "loss": 0.4326, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.8241518684841642e-06, | |
| "loss": 0.1299, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.7773178101022514e-06, | |
| "loss": 0.1008, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.7310341136430386e-06, | |
| "loss": 0.1049, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.6853038769745466e-06, | |
| "loss": 0.205, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.6401301609205333e-06, | |
| "loss": 0.2219, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.5955159890556182e-06, | |
| "loss": 0.1405, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.551464347502929e-06, | |
| "loss": 0.1053, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.5079781847342122e-06, | |
| "loss": 0.1873, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1.4650604113724953e-06, | |
| "loss": 0.26, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.4227138999972801e-06, | |
| "loss": 0.1335, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.3809414849522585e-06, | |
| "loss": 0.1168, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.1731, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.2991300889128867e-06, | |
| "loss": 0.2434, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.2590965837324132e-06, | |
| "loss": 0.1344, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.2196481261433735e-06, | |
| "loss": 0.1206, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.1807873565164507e-06, | |
| "loss": 0.1283, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.1425168758870963e-06, | |
| "loss": 0.1008, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.1048392457814406e-06, | |
| "loss": 0.1143, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.0677569880448479e-06, | |
| "loss": 0.1137, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.0312725846731174e-06, | |
| "loss": 0.137, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.953884776463652e-07, | |
| "loss": 0.0847, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.601070687655667e-07, | |
| "loss": 0.1254, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.254307194918144e-07, | |
| "loss": 0.1035, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.91361750788241e-07, | |
| "loss": 0.126, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.579024429646932e-07, | |
| "loss": 0.1385, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 8.250550355250875e-07, | |
| "loss": 0.3491, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.928217270175231e-07, | |
| "loss": 0.1928, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.612046748871327e-07, | |
| "loss": 0.121, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.30205995331672e-07, | |
| "loss": 0.0909, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.998277631598793e-07, | |
| "loss": 0.1568, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.700720116526116e-07, | |
| "loss": 0.1316, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.409407324267448e-07, | |
| "loss": 0.3285, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.124358753018688e-07, | |
| "loss": 0.1659, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.845593481697931e-07, | |
| "loss": 0.1013, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.57313016866835e-07, | |
| "loss": 0.2537, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.306987050489442e-07, | |
| "loss": 0.1518, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.047181940696333e-07, | |
| "loss": 0.0987, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.793732228607573e-07, | |
| "loss": 0.2286, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.54665487816115e-07, | |
| "loss": 0.1637, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.305966426779118e-07, | |
| "loss": 0.1226, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.0716829842606385e-07, | |
| "loss": 0.1352, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 3.8438202317037987e-07, | |
| "loss": 0.1597, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.6223934204560165e-07, | |
| "loss": 0.2184, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.4074173710931804e-07, | |
| "loss": 0.174, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.198906472427732e-07, | |
| "loss": 0.1711, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.996874680545603e-07, | |
| "loss": 0.2215, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.8013355178720613e-07, | |
| "loss": 0.1262, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.612302072266637e-07, | |
| "loss": 0.1392, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.4297869961471544e-07, | |
| "loss": 0.1611, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.2538025056428216e-07, | |
| "loss": 0.1515, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 2.0843603797766287e-07, | |
| "loss": 0.1478, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.921471959676957e-07, | |
| "loss": 0.1685, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.7651481478184297e-07, | |
| "loss": 0.1206, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.615399407292251e-07, | |
| "loss": 0.0952, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.472235761105878e-07, | |
| "loss": 0.1378, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.3356667915121025e-07, | |
| "loss": 0.1138, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.2057016393677623e-07, | |
| "loss": 0.0912, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.0823490035218986e-07, | |
| "loss": 0.1429, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 9.656171402335213e-08, | |
| "loss": 0.1181, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.555138626189619e-08, | |
| "loss": 0.1142, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.520465401290033e-08, | |
| "loss": 0.2712, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 6.552220980555635e-08, | |
| "loss": 0.1408, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 5.650470170681876e-08, | |
| "loss": 0.1736, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.815273327803183e-08, | |
| "loss": 0.1527, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 4.0466863534522895e-08, | |
| "loss": 0.1103, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.3447606908196815e-08, | |
| "loss": 0.1522, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2.7095433213097933e-08, | |
| "loss": 0.1824, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.1410767613965212e-08, | |
| "loss": 0.1105, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.639399059777502e-08, | |
| "loss": 0.0768, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.2045437948275952e-08, | |
| "loss": 0.0796, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 8.365400723512329e-09, | |
| "loss": 0.0868, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.354125236343155e-09, | |
| "loss": 0.1575, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.0118130379575005e-09, | |
| "loss": 0.1257, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.3386209043819708e-09, | |
| "loss": 0.1137, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.346608259890971e-10, | |
| "loss": 0.1299, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1945, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 396, | |
| "total_flos": 4.02857154245034e+17, | |
| "train_loss": 0.47617627023672215, | |
| "train_runtime": 8141.7482, | |
| "train_samples_per_second": 0.776, | |
| "train_steps_per_second": 0.049 | |
| } | |
| ], | |
| "max_steps": 396, | |
| "num_train_epochs": 3, | |
| "total_flos": 4.02857154245034e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |