{ "best_global_step": 1460, "best_metric": 0.8658280922431866, "best_model_checkpoint": "./cysecbert-ttp-bert-75per_ood_data/checkpoint-1460", "epoch": 10.0, "eval_steps": 500, "global_step": 1460, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00684931506849315, "grad_norm": 40235.48046875, "learning_rate": 0.0, "loss": 0.6887, "step": 1 }, { "epoch": 0.0136986301369863, "grad_norm": 40833.5390625, "learning_rate": 5.000000000000001e-07, "loss": 0.6884, "step": 2 }, { "epoch": 0.02054794520547945, "grad_norm": 41377.40625, "learning_rate": 1.0000000000000002e-06, "loss": 0.6903, "step": 3 }, { "epoch": 0.0273972602739726, "grad_norm": 43284.0234375, "learning_rate": 1.5e-06, "loss": 0.6843, "step": 4 }, { "epoch": 0.03424657534246575, "grad_norm": 42114.75390625, "learning_rate": 2.0000000000000003e-06, "loss": 0.6853, "step": 5 }, { "epoch": 0.0410958904109589, "grad_norm": 40727.859375, "learning_rate": 2.5e-06, "loss": 0.6824, "step": 6 }, { "epoch": 0.04794520547945205, "grad_norm": 44728.51171875, "learning_rate": 3e-06, "loss": 0.6811, "step": 7 }, { "epoch": 0.0547945205479452, "grad_norm": 40711.49609375, "learning_rate": 3.5000000000000004e-06, "loss": 0.68, "step": 8 }, { "epoch": 0.06164383561643835, "grad_norm": 42349.7421875, "learning_rate": 4.000000000000001e-06, "loss": 0.6741, "step": 9 }, { "epoch": 0.0684931506849315, "grad_norm": 42834.99609375, "learning_rate": 4.5e-06, "loss": 0.6726, "step": 10 }, { "epoch": 0.07534246575342465, "grad_norm": 46013.91796875, "learning_rate": 5e-06, "loss": 0.6669, "step": 11 }, { "epoch": 0.0821917808219178, "grad_norm": 51480.80859375, "learning_rate": 5.500000000000001e-06, "loss": 0.6636, "step": 12 }, { "epoch": 0.08904109589041095, "grad_norm": 46873.71484375, "learning_rate": 6e-06, "loss": 0.6633, "step": 13 }, { "epoch": 0.0958904109589041, "grad_norm": 52108.734375, "learning_rate": 6.5000000000000004e-06, "loss": 0.6531, "step": 14 }, { "epoch": 0.10273972602739725, "grad_norm": 50014.2578125, "learning_rate": 7.000000000000001e-06, "loss": 0.6484, "step": 15 }, { "epoch": 0.1095890410958904, "grad_norm": 49517.47265625, "learning_rate": 7.5e-06, "loss": 0.6399, "step": 16 }, { "epoch": 0.11643835616438356, "grad_norm": 75202.9140625, "learning_rate": 8.000000000000001e-06, "loss": 0.6296, "step": 17 }, { "epoch": 0.1232876712328767, "grad_norm": 47799.85546875, "learning_rate": 8.500000000000002e-06, "loss": 0.6262, "step": 18 }, { "epoch": 0.13013698630136986, "grad_norm": 62351.71484375, "learning_rate": 9e-06, "loss": 0.6167, "step": 19 }, { "epoch": 0.136986301369863, "grad_norm": 55344.5859375, "learning_rate": 9.5e-06, "loss": 0.6075, "step": 20 }, { "epoch": 0.14383561643835616, "grad_norm": 51717.06640625, "learning_rate": 1e-05, "loss": 0.5974, "step": 21 }, { "epoch": 0.1506849315068493, "grad_norm": 52018.078125, "learning_rate": 1.05e-05, "loss": 0.5808, "step": 22 }, { "epoch": 0.15753424657534246, "grad_norm": 51652.50390625, "learning_rate": 1.1000000000000001e-05, "loss": 0.5751, "step": 23 }, { "epoch": 0.1643835616438356, "grad_norm": 53332.38671875, "learning_rate": 1.1500000000000002e-05, "loss": 0.5631, "step": 24 }, { "epoch": 0.17123287671232876, "grad_norm": 52499.24609375, "learning_rate": 1.2e-05, "loss": 0.5566, "step": 25 }, { "epoch": 0.1780821917808219, "grad_norm": 49486.08984375, "learning_rate": 1.25e-05, "loss": 0.545, "step": 26 }, { "epoch": 0.18493150684931506, "grad_norm": 51167.44140625, "learning_rate": 1.3000000000000001e-05, "loss": 0.5288, "step": 27 }, { "epoch": 0.1917808219178082, "grad_norm": 66664.09375, "learning_rate": 1.3500000000000001e-05, "loss": 0.5297, "step": 28 }, { "epoch": 0.19863013698630136, "grad_norm": 45469.953125, "learning_rate": 1.4000000000000001e-05, "loss": 0.5126, "step": 29 }, { "epoch": 0.2054794520547945, "grad_norm": 44199.90234375, "learning_rate": 1.45e-05, "loss": 0.5061, "step": 30 }, { "epoch": 0.21232876712328766, "grad_norm": 44457.09765625, "learning_rate": 1.5e-05, "loss": 0.4949, "step": 31 }, { "epoch": 0.2191780821917808, "grad_norm": 43740.30078125, "learning_rate": 1.55e-05, "loss": 0.4892, "step": 32 }, { "epoch": 0.22602739726027396, "grad_norm": 44430.03515625, "learning_rate": 1.6000000000000003e-05, "loss": 0.4758, "step": 33 }, { "epoch": 0.2328767123287671, "grad_norm": 43423.80078125, "learning_rate": 1.65e-05, "loss": 0.4728, "step": 34 }, { "epoch": 0.23972602739726026, "grad_norm": 42465.08203125, "learning_rate": 1.7000000000000003e-05, "loss": 0.4588, "step": 35 }, { "epoch": 0.2465753424657534, "grad_norm": 41459.41796875, "learning_rate": 1.75e-05, "loss": 0.4585, "step": 36 }, { "epoch": 0.2534246575342466, "grad_norm": 41684.81640625, "learning_rate": 1.8e-05, "loss": 0.4443, "step": 37 }, { "epoch": 0.2602739726027397, "grad_norm": 41280.94140625, "learning_rate": 1.85e-05, "loss": 0.4313, "step": 38 }, { "epoch": 0.2671232876712329, "grad_norm": 41269.48046875, "learning_rate": 1.9e-05, "loss": 0.4256, "step": 39 }, { "epoch": 0.273972602739726, "grad_norm": 40282.34765625, "learning_rate": 1.9500000000000003e-05, "loss": 0.4197, "step": 40 }, { "epoch": 0.2808219178082192, "grad_norm": 40001.88671875, "learning_rate": 2e-05, "loss": 0.4159, "step": 41 }, { "epoch": 0.2876712328767123, "grad_norm": 39656.03125, "learning_rate": 2.05e-05, "loss": 0.409, "step": 42 }, { "epoch": 0.2945205479452055, "grad_norm": 39420.35546875, "learning_rate": 2.1e-05, "loss": 0.3979, "step": 43 }, { "epoch": 0.3013698630136986, "grad_norm": 38680.59765625, "learning_rate": 2.15e-05, "loss": 0.3973, "step": 44 }, { "epoch": 0.3082191780821918, "grad_norm": 38872.77734375, "learning_rate": 2.2000000000000003e-05, "loss": 0.3861, "step": 45 }, { "epoch": 0.3150684931506849, "grad_norm": 38217.92578125, "learning_rate": 2.25e-05, "loss": 0.377, "step": 46 }, { "epoch": 0.3219178082191781, "grad_norm": 37789.0625, "learning_rate": 2.3000000000000003e-05, "loss": 0.3683, "step": 47 }, { "epoch": 0.3287671232876712, "grad_norm": 37014.44140625, "learning_rate": 2.35e-05, "loss": 0.3702, "step": 48 }, { "epoch": 0.3356164383561644, "grad_norm": 37085.09765625, "learning_rate": 2.4e-05, "loss": 0.3611, "step": 49 }, { "epoch": 0.3424657534246575, "grad_norm": 36909.046875, "learning_rate": 2.45e-05, "loss": 0.3487, "step": 50 }, { "epoch": 0.3493150684931507, "grad_norm": 36649.34765625, "learning_rate": 2.5e-05, "loss": 0.3439, "step": 51 }, { "epoch": 0.3561643835616438, "grad_norm": 35952.72265625, "learning_rate": 2.5500000000000003e-05, "loss": 0.339, "step": 52 }, { "epoch": 0.363013698630137, "grad_norm": 35468.87109375, "learning_rate": 2.6000000000000002e-05, "loss": 0.3379, "step": 53 }, { "epoch": 0.3698630136986301, "grad_norm": 35107.97265625, "learning_rate": 2.6500000000000004e-05, "loss": 0.3246, "step": 54 }, { "epoch": 0.3767123287671233, "grad_norm": 34695.078125, "learning_rate": 2.7000000000000002e-05, "loss": 0.3125, "step": 55 }, { "epoch": 0.3835616438356164, "grad_norm": 33767.9765625, "learning_rate": 2.7500000000000004e-05, "loss": 0.3108, "step": 56 }, { "epoch": 0.3904109589041096, "grad_norm": 34098.65234375, "learning_rate": 2.8000000000000003e-05, "loss": 0.303, "step": 57 }, { "epoch": 0.3972602739726027, "grad_norm": 33558.62890625, "learning_rate": 2.8499999999999998e-05, "loss": 0.3023, "step": 58 }, { "epoch": 0.4041095890410959, "grad_norm": 32385.314453125, "learning_rate": 2.9e-05, "loss": 0.2909, "step": 59 }, { "epoch": 0.410958904109589, "grad_norm": 32493.962890625, "learning_rate": 2.95e-05, "loss": 0.2853, "step": 60 }, { "epoch": 0.4178082191780822, "grad_norm": 31880.669921875, "learning_rate": 3e-05, "loss": 0.2871, "step": 61 }, { "epoch": 0.4246575342465753, "grad_norm": 31619.47265625, "learning_rate": 3.05e-05, "loss": 0.2716, "step": 62 }, { "epoch": 0.4315068493150685, "grad_norm": 31282.384765625, "learning_rate": 3.1e-05, "loss": 0.2642, "step": 63 }, { "epoch": 0.4383561643835616, "grad_norm": 30239.6953125, "learning_rate": 3.15e-05, "loss": 0.2614, "step": 64 }, { "epoch": 0.4452054794520548, "grad_norm": 29724.130859375, "learning_rate": 3.2000000000000005e-05, "loss": 0.2477, "step": 65 }, { "epoch": 0.4520547945205479, "grad_norm": 29504.95703125, "learning_rate": 3.2500000000000004e-05, "loss": 0.2496, "step": 66 }, { "epoch": 0.4589041095890411, "grad_norm": 29248.1953125, "learning_rate": 3.3e-05, "loss": 0.2421, "step": 67 }, { "epoch": 0.4657534246575342, "grad_norm": 28177.767578125, "learning_rate": 3.35e-05, "loss": 0.2381, "step": 68 }, { "epoch": 0.4726027397260274, "grad_norm": 27021.123046875, "learning_rate": 3.4000000000000007e-05, "loss": 0.2373, "step": 69 }, { "epoch": 0.4794520547945205, "grad_norm": 26797.484375, "learning_rate": 3.45e-05, "loss": 0.2221, "step": 70 }, { "epoch": 0.4863013698630137, "grad_norm": 26093.4609375, "learning_rate": 3.5e-05, "loss": 0.2209, "step": 71 }, { "epoch": 0.4931506849315068, "grad_norm": 25555.8828125, "learning_rate": 3.55e-05, "loss": 0.2183, "step": 72 }, { "epoch": 0.5, "grad_norm": 24861.978515625, "learning_rate": 3.6e-05, "loss": 0.2178, "step": 73 }, { "epoch": 0.5068493150684932, "grad_norm": 24384.646484375, "learning_rate": 3.65e-05, "loss": 0.2132, "step": 74 }, { "epoch": 0.5136986301369864, "grad_norm": 23557.564453125, "learning_rate": 3.7e-05, "loss": 0.2068, "step": 75 }, { "epoch": 0.5205479452054794, "grad_norm": 22570.8046875, "learning_rate": 3.7500000000000003e-05, "loss": 0.2033, "step": 76 }, { "epoch": 0.5273972602739726, "grad_norm": 22542.50390625, "learning_rate": 3.8e-05, "loss": 0.1917, "step": 77 }, { "epoch": 0.5342465753424658, "grad_norm": 20321.337890625, "learning_rate": 3.85e-05, "loss": 0.2014, "step": 78 }, { "epoch": 0.541095890410959, "grad_norm": 20167.287109375, "learning_rate": 3.9000000000000006e-05, "loss": 0.1951, "step": 79 }, { "epoch": 0.547945205479452, "grad_norm": 20679.982421875, "learning_rate": 3.9500000000000005e-05, "loss": 0.1781, "step": 80 }, { "epoch": 0.5547945205479452, "grad_norm": 19417.52734375, "learning_rate": 4e-05, "loss": 0.1811, "step": 81 }, { "epoch": 0.5616438356164384, "grad_norm": 19473.375, "learning_rate": 4.05e-05, "loss": 0.1643, "step": 82 }, { "epoch": 0.5684931506849316, "grad_norm": 18340.1015625, "learning_rate": 4.1e-05, "loss": 0.1764, "step": 83 }, { "epoch": 0.5753424657534246, "grad_norm": 16642.7890625, "learning_rate": 4.15e-05, "loss": 0.1771, "step": 84 }, { "epoch": 0.5821917808219178, "grad_norm": 17052.697265625, "learning_rate": 4.2e-05, "loss": 0.1659, "step": 85 }, { "epoch": 0.589041095890411, "grad_norm": 16948.982421875, "learning_rate": 4.25e-05, "loss": 0.152, "step": 86 }, { "epoch": 0.5958904109589042, "grad_norm": 17601.1171875, "learning_rate": 4.3e-05, "loss": 0.1473, "step": 87 }, { "epoch": 0.6027397260273972, "grad_norm": 16111.666015625, "learning_rate": 4.35e-05, "loss": 0.1403, "step": 88 }, { "epoch": 0.6095890410958904, "grad_norm": 15580.625, "learning_rate": 4.4000000000000006e-05, "loss": 0.1427, "step": 89 }, { "epoch": 0.6164383561643836, "grad_norm": 14311.80859375, "learning_rate": 4.4500000000000004e-05, "loss": 0.1466, "step": 90 }, { "epoch": 0.6232876712328768, "grad_norm": 13912.0703125, "learning_rate": 4.5e-05, "loss": 0.1454, "step": 91 }, { "epoch": 0.6301369863013698, "grad_norm": 13390.2021484375, "learning_rate": 4.55e-05, "loss": 0.1307, "step": 92 }, { "epoch": 0.636986301369863, "grad_norm": 12240.388671875, "learning_rate": 4.600000000000001e-05, "loss": 0.138, "step": 93 }, { "epoch": 0.6438356164383562, "grad_norm": 12777.0703125, "learning_rate": 4.6500000000000005e-05, "loss": 0.1376, "step": 94 }, { "epoch": 0.6506849315068494, "grad_norm": 12149.126953125, "learning_rate": 4.7e-05, "loss": 0.1309, "step": 95 }, { "epoch": 0.6575342465753424, "grad_norm": 12086.5283203125, "learning_rate": 4.75e-05, "loss": 0.1229, "step": 96 }, { "epoch": 0.6643835616438356, "grad_norm": 11085.8681640625, "learning_rate": 4.8e-05, "loss": 0.1417, "step": 97 }, { "epoch": 0.6712328767123288, "grad_norm": 10390.2392578125, "learning_rate": 4.85e-05, "loss": 0.1259, "step": 98 }, { "epoch": 0.678082191780822, "grad_norm": 11204.9091796875, "learning_rate": 4.9e-05, "loss": 0.1292, "step": 99 }, { "epoch": 0.684931506849315, "grad_norm": 11244.5625, "learning_rate": 4.9500000000000004e-05, "loss": 0.1233, "step": 100 }, { "epoch": 0.6917808219178082, "grad_norm": 9874.2109375, "learning_rate": 5e-05, "loss": 0.114, "step": 101 }, { "epoch": 0.6986301369863014, "grad_norm": 9110.65625, "learning_rate": 4.996323529411765e-05, "loss": 0.1212, "step": 102 }, { "epoch": 0.7054794520547946, "grad_norm": 9141.6650390625, "learning_rate": 4.99264705882353e-05, "loss": 0.1122, "step": 103 }, { "epoch": 0.7123287671232876, "grad_norm": 8792.66796875, "learning_rate": 4.9889705882352945e-05, "loss": 0.1103, "step": 104 }, { "epoch": 0.7191780821917808, "grad_norm": 8324.197265625, "learning_rate": 4.985294117647059e-05, "loss": 0.1201, "step": 105 }, { "epoch": 0.726027397260274, "grad_norm": 9198.9814453125, "learning_rate": 4.9816176470588236e-05, "loss": 0.1196, "step": 106 }, { "epoch": 0.7328767123287672, "grad_norm": 9103.576171875, "learning_rate": 4.977941176470589e-05, "loss": 0.1098, "step": 107 }, { "epoch": 0.7397260273972602, "grad_norm": 8073.556640625, "learning_rate": 4.9742647058823534e-05, "loss": 0.1216, "step": 108 }, { "epoch": 0.7465753424657534, "grad_norm": 7941.67431640625, "learning_rate": 4.970588235294118e-05, "loss": 0.1095, "step": 109 }, { "epoch": 0.7534246575342466, "grad_norm": 9013.251953125, "learning_rate": 4.9669117647058824e-05, "loss": 0.1157, "step": 110 }, { "epoch": 0.7602739726027398, "grad_norm": 9189.2509765625, "learning_rate": 4.9632352941176476e-05, "loss": 0.0989, "step": 111 }, { "epoch": 0.7671232876712328, "grad_norm": 7528.97412109375, "learning_rate": 4.959558823529412e-05, "loss": 0.0984, "step": 112 }, { "epoch": 0.773972602739726, "grad_norm": 9241.4521484375, "learning_rate": 4.955882352941177e-05, "loss": 0.1007, "step": 113 }, { "epoch": 0.7808219178082192, "grad_norm": 8411.1435546875, "learning_rate": 4.952205882352941e-05, "loss": 0.1065, "step": 114 }, { "epoch": 0.7876712328767124, "grad_norm": 10099.728515625, "learning_rate": 4.9485294117647065e-05, "loss": 0.0938, "step": 115 }, { "epoch": 0.7945205479452054, "grad_norm": 8326.3583984375, "learning_rate": 4.944852941176471e-05, "loss": 0.1136, "step": 116 }, { "epoch": 0.8013698630136986, "grad_norm": 7931.55908203125, "learning_rate": 4.9411764705882355e-05, "loss": 0.1106, "step": 117 }, { "epoch": 0.8082191780821918, "grad_norm": 7750.83251953125, "learning_rate": 4.937500000000001e-05, "loss": 0.1087, "step": 118 }, { "epoch": 0.815068493150685, "grad_norm": 7448.69482421875, "learning_rate": 4.933823529411765e-05, "loss": 0.1148, "step": 119 }, { "epoch": 0.821917808219178, "grad_norm": 7205.22802734375, "learning_rate": 4.93014705882353e-05, "loss": 0.1079, "step": 120 }, { "epoch": 0.8287671232876712, "grad_norm": 7149.3701171875, "learning_rate": 4.9264705882352944e-05, "loss": 0.1168, "step": 121 }, { "epoch": 0.8356164383561644, "grad_norm": 7850.7734375, "learning_rate": 4.9227941176470596e-05, "loss": 0.13, "step": 122 }, { "epoch": 0.8424657534246576, "grad_norm": 7431.83349609375, "learning_rate": 4.9191176470588234e-05, "loss": 0.1048, "step": 123 }, { "epoch": 0.8493150684931506, "grad_norm": 8571.9541015625, "learning_rate": 4.915441176470588e-05, "loss": 0.1214, "step": 124 }, { "epoch": 0.8561643835616438, "grad_norm": 6354.39453125, "learning_rate": 4.911764705882353e-05, "loss": 0.1036, "step": 125 }, { "epoch": 0.863013698630137, "grad_norm": 9486.8916015625, "learning_rate": 4.908088235294118e-05, "loss": 0.1188, "step": 126 }, { "epoch": 0.8698630136986302, "grad_norm": 7285.9189453125, "learning_rate": 4.904411764705882e-05, "loss": 0.1113, "step": 127 }, { "epoch": 0.8767123287671232, "grad_norm": 8400.583984375, "learning_rate": 4.900735294117647e-05, "loss": 0.1033, "step": 128 }, { "epoch": 0.8835616438356164, "grad_norm": 7335.37158203125, "learning_rate": 4.897058823529412e-05, "loss": 0.1136, "step": 129 }, { "epoch": 0.8904109589041096, "grad_norm": 7330.98388671875, "learning_rate": 4.8933823529411766e-05, "loss": 0.1156, "step": 130 }, { "epoch": 0.8972602739726028, "grad_norm": 7794.04736328125, "learning_rate": 4.889705882352941e-05, "loss": 0.1045, "step": 131 }, { "epoch": 0.9041095890410958, "grad_norm": 7455.669921875, "learning_rate": 4.886029411764706e-05, "loss": 0.1107, "step": 132 }, { "epoch": 0.910958904109589, "grad_norm": 8304.4736328125, "learning_rate": 4.882352941176471e-05, "loss": 0.107, "step": 133 }, { "epoch": 0.9178082191780822, "grad_norm": 7252.26953125, "learning_rate": 4.8786764705882354e-05, "loss": 0.1054, "step": 134 }, { "epoch": 0.9246575342465754, "grad_norm": 7084.47412109375, "learning_rate": 4.875e-05, "loss": 0.1083, "step": 135 }, { "epoch": 0.9315068493150684, "grad_norm": 6766.45068359375, "learning_rate": 4.871323529411765e-05, "loss": 0.1044, "step": 136 }, { "epoch": 0.9383561643835616, "grad_norm": 7519.54052734375, "learning_rate": 4.86764705882353e-05, "loss": 0.1064, "step": 137 }, { "epoch": 0.9452054794520548, "grad_norm": 10277.6962890625, "learning_rate": 4.863970588235294e-05, "loss": 0.1313, "step": 138 }, { "epoch": 0.952054794520548, "grad_norm": 7649.0849609375, "learning_rate": 4.860294117647059e-05, "loss": 0.0958, "step": 139 }, { "epoch": 0.958904109589041, "grad_norm": 8338.7470703125, "learning_rate": 4.856617647058824e-05, "loss": 0.1083, "step": 140 }, { "epoch": 0.9657534246575342, "grad_norm": 7829.50830078125, "learning_rate": 4.8529411764705885e-05, "loss": 0.1226, "step": 141 }, { "epoch": 0.9726027397260274, "grad_norm": 7447.2080078125, "learning_rate": 4.849264705882353e-05, "loss": 0.1025, "step": 142 }, { "epoch": 0.9794520547945206, "grad_norm": 8027.55810546875, "learning_rate": 4.8455882352941176e-05, "loss": 0.1128, "step": 143 }, { "epoch": 0.9863013698630136, "grad_norm": 7852.28955078125, "learning_rate": 4.841911764705883e-05, "loss": 0.1182, "step": 144 }, { "epoch": 0.9931506849315068, "grad_norm": 8110.33984375, "learning_rate": 4.838235294117647e-05, "loss": 0.1089, "step": 145 }, { "epoch": 1.0, "grad_norm": 9531.46875, "learning_rate": 4.834558823529412e-05, "loss": 0.1045, "step": 146 }, { "epoch": 1.0, "eval_f1_macro": 0.0, "eval_f1_micro": 0.0, "eval_loss": 0.10734307020902634, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 1.0888, "eval_samples_per_second": 357.264, "eval_steps_per_second": 15.613, "step": 146 }, { "epoch": 1.0068493150684932, "grad_norm": 7844.3857421875, "learning_rate": 4.830882352941177e-05, "loss": 0.1155, "step": 147 }, { "epoch": 1.0136986301369864, "grad_norm": 7834.66650390625, "learning_rate": 4.8272058823529416e-05, "loss": 0.1133, "step": 148 }, { "epoch": 1.0205479452054795, "grad_norm": 9270.6435546875, "learning_rate": 4.823529411764706e-05, "loss": 0.0962, "step": 149 }, { "epoch": 1.0273972602739727, "grad_norm": 5747.0166015625, "learning_rate": 4.819852941176471e-05, "loss": 0.1051, "step": 150 }, { "epoch": 1.0342465753424657, "grad_norm": 7144.046875, "learning_rate": 4.816176470588236e-05, "loss": 0.0923, "step": 151 }, { "epoch": 1.0410958904109588, "grad_norm": 6622.763671875, "learning_rate": 4.8125000000000004e-05, "loss": 0.0964, "step": 152 }, { "epoch": 1.047945205479452, "grad_norm": 6455.65185546875, "learning_rate": 4.808823529411765e-05, "loss": 0.1068, "step": 153 }, { "epoch": 1.0547945205479452, "grad_norm": 7207.41748046875, "learning_rate": 4.8051470588235295e-05, "loss": 0.1011, "step": 154 }, { "epoch": 1.0616438356164384, "grad_norm": 6697.1240234375, "learning_rate": 4.801470588235295e-05, "loss": 0.1053, "step": 155 }, { "epoch": 1.0684931506849316, "grad_norm": 9128.0439453125, "learning_rate": 4.797794117647059e-05, "loss": 0.1062, "step": 156 }, { "epoch": 1.0753424657534247, "grad_norm": 6570.29052734375, "learning_rate": 4.794117647058824e-05, "loss": 0.1018, "step": 157 }, { "epoch": 1.0821917808219177, "grad_norm": 7567.10107421875, "learning_rate": 4.790441176470588e-05, "loss": 0.1333, "step": 158 }, { "epoch": 1.0890410958904109, "grad_norm": 8185.25732421875, "learning_rate": 4.7867647058823535e-05, "loss": 0.1079, "step": 159 }, { "epoch": 1.095890410958904, "grad_norm": 7491.5166015625, "learning_rate": 4.783088235294118e-05, "loss": 0.1058, "step": 160 }, { "epoch": 1.1027397260273972, "grad_norm": 6058.0859375, "learning_rate": 4.7794117647058826e-05, "loss": 0.0968, "step": 161 }, { "epoch": 1.1095890410958904, "grad_norm": 7416.90576171875, "learning_rate": 4.775735294117648e-05, "loss": 0.0956, "step": 162 }, { "epoch": 1.1164383561643836, "grad_norm": 7249.77099609375, "learning_rate": 4.7720588235294124e-05, "loss": 0.097, "step": 163 }, { "epoch": 1.1232876712328768, "grad_norm": 7413.4677734375, "learning_rate": 4.768382352941177e-05, "loss": 0.097, "step": 164 }, { "epoch": 1.13013698630137, "grad_norm": 6435.68408203125, "learning_rate": 4.7647058823529414e-05, "loss": 0.1007, "step": 165 }, { "epoch": 1.1369863013698631, "grad_norm": 8137.607421875, "learning_rate": 4.761029411764706e-05, "loss": 0.1002, "step": 166 }, { "epoch": 1.143835616438356, "grad_norm": 7903.47705078125, "learning_rate": 4.7573529411764705e-05, "loss": 0.0975, "step": 167 }, { "epoch": 1.1506849315068493, "grad_norm": 7501.56982421875, "learning_rate": 4.753676470588235e-05, "loss": 0.1103, "step": 168 }, { "epoch": 1.1575342465753424, "grad_norm": 8079.19140625, "learning_rate": 4.75e-05, "loss": 0.1057, "step": 169 }, { "epoch": 1.1643835616438356, "grad_norm": 6607.068359375, "learning_rate": 4.746323529411765e-05, "loss": 0.0966, "step": 170 }, { "epoch": 1.1712328767123288, "grad_norm": 7972.5283203125, "learning_rate": 4.742647058823529e-05, "loss": 0.1025, "step": 171 }, { "epoch": 1.178082191780822, "grad_norm": 6533.47705078125, "learning_rate": 4.738970588235294e-05, "loss": 0.1107, "step": 172 }, { "epoch": 1.1849315068493151, "grad_norm": 7033.37060546875, "learning_rate": 4.735294117647059e-05, "loss": 0.1181, "step": 173 }, { "epoch": 1.191780821917808, "grad_norm": 7818.30419921875, "learning_rate": 4.7316176470588236e-05, "loss": 0.1072, "step": 174 }, { "epoch": 1.1986301369863013, "grad_norm": 6882.0087890625, "learning_rate": 4.727941176470588e-05, "loss": 0.0962, "step": 175 }, { "epoch": 1.2054794520547945, "grad_norm": 8742.55078125, "learning_rate": 4.7242647058823534e-05, "loss": 0.1165, "step": 176 }, { "epoch": 1.2123287671232876, "grad_norm": 6775.27392578125, "learning_rate": 4.720588235294118e-05, "loss": 0.1092, "step": 177 }, { "epoch": 1.2191780821917808, "grad_norm": 7078.43505859375, "learning_rate": 4.7169117647058824e-05, "loss": 0.1065, "step": 178 }, { "epoch": 1.226027397260274, "grad_norm": 7678.19873046875, "learning_rate": 4.713235294117647e-05, "loss": 0.1085, "step": 179 }, { "epoch": 1.2328767123287672, "grad_norm": 7301.466796875, "learning_rate": 4.709558823529412e-05, "loss": 0.1107, "step": 180 }, { "epoch": 1.2397260273972603, "grad_norm": 8494.6337890625, "learning_rate": 4.705882352941177e-05, "loss": 0.1118, "step": 181 }, { "epoch": 1.2465753424657535, "grad_norm": 10682.3720703125, "learning_rate": 4.702205882352941e-05, "loss": 0.1495, "step": 182 }, { "epoch": 1.2534246575342465, "grad_norm": 6462.31396484375, "learning_rate": 4.698529411764706e-05, "loss": 0.103, "step": 183 }, { "epoch": 1.2602739726027397, "grad_norm": 6301.04443359375, "learning_rate": 4.694852941176471e-05, "loss": 0.0994, "step": 184 }, { "epoch": 1.2671232876712328, "grad_norm": 6932.416015625, "learning_rate": 4.6911764705882356e-05, "loss": 0.101, "step": 185 }, { "epoch": 1.273972602739726, "grad_norm": 7733.24853515625, "learning_rate": 4.6875e-05, "loss": 0.1184, "step": 186 }, { "epoch": 1.2808219178082192, "grad_norm": 9721.1484375, "learning_rate": 4.6838235294117646e-05, "loss": 0.1258, "step": 187 }, { "epoch": 1.2876712328767124, "grad_norm": 7505.13037109375, "learning_rate": 4.68014705882353e-05, "loss": 0.1038, "step": 188 }, { "epoch": 1.2945205479452055, "grad_norm": 7543.56298828125, "learning_rate": 4.6764705882352944e-05, "loss": 0.0956, "step": 189 }, { "epoch": 1.3013698630136985, "grad_norm": 8164.38623046875, "learning_rate": 4.672794117647059e-05, "loss": 0.1214, "step": 190 }, { "epoch": 1.308219178082192, "grad_norm": 6560.83203125, "learning_rate": 4.669117647058824e-05, "loss": 0.097, "step": 191 }, { "epoch": 1.3150684931506849, "grad_norm": 7678.19140625, "learning_rate": 4.665441176470589e-05, "loss": 0.0965, "step": 192 }, { "epoch": 1.321917808219178, "grad_norm": 7035.8173828125, "learning_rate": 4.661764705882353e-05, "loss": 0.0997, "step": 193 }, { "epoch": 1.3287671232876712, "grad_norm": 6044.10546875, "learning_rate": 4.658088235294118e-05, "loss": 0.1293, "step": 194 }, { "epoch": 1.3356164383561644, "grad_norm": 8358.5283203125, "learning_rate": 4.654411764705883e-05, "loss": 0.1172, "step": 195 }, { "epoch": 1.3424657534246576, "grad_norm": 7993.4306640625, "learning_rate": 4.6507352941176475e-05, "loss": 0.103, "step": 196 }, { "epoch": 1.3493150684931507, "grad_norm": 7649.63818359375, "learning_rate": 4.647058823529412e-05, "loss": 0.1095, "step": 197 }, { "epoch": 1.356164383561644, "grad_norm": 6661.931640625, "learning_rate": 4.6433823529411766e-05, "loss": 0.1123, "step": 198 }, { "epoch": 1.3630136986301369, "grad_norm": 8118.16796875, "learning_rate": 4.639705882352942e-05, "loss": 0.1241, "step": 199 }, { "epoch": 1.36986301369863, "grad_norm": 7540.71142578125, "learning_rate": 4.636029411764706e-05, "loss": 0.1072, "step": 200 }, { "epoch": 1.3767123287671232, "grad_norm": 7699.181640625, "learning_rate": 4.632352941176471e-05, "loss": 0.1097, "step": 201 }, { "epoch": 1.3835616438356164, "grad_norm": 8992.42578125, "learning_rate": 4.6286764705882354e-05, "loss": 0.1097, "step": 202 }, { "epoch": 1.3904109589041096, "grad_norm": 8244.7421875, "learning_rate": 4.6250000000000006e-05, "loss": 0.1232, "step": 203 }, { "epoch": 1.3972602739726028, "grad_norm": 6626.13818359375, "learning_rate": 4.621323529411765e-05, "loss": 0.104, "step": 204 }, { "epoch": 1.404109589041096, "grad_norm": 7067.0263671875, "learning_rate": 4.61764705882353e-05, "loss": 0.1001, "step": 205 }, { "epoch": 1.410958904109589, "grad_norm": 7676.96875, "learning_rate": 4.613970588235295e-05, "loss": 0.1112, "step": 206 }, { "epoch": 1.4178082191780823, "grad_norm": 7285.85595703125, "learning_rate": 4.6102941176470594e-05, "loss": 0.1113, "step": 207 }, { "epoch": 1.4246575342465753, "grad_norm": 8258.4580078125, "learning_rate": 4.606617647058823e-05, "loss": 0.1203, "step": 208 }, { "epoch": 1.4315068493150684, "grad_norm": 7589.36279296875, "learning_rate": 4.6029411764705885e-05, "loss": 0.1005, "step": 209 }, { "epoch": 1.4383561643835616, "grad_norm": 7342.3876953125, "learning_rate": 4.599264705882353e-05, "loss": 0.1019, "step": 210 }, { "epoch": 1.4452054794520548, "grad_norm": 9245.3056640625, "learning_rate": 4.5955882352941176e-05, "loss": 0.1212, "step": 211 }, { "epoch": 1.452054794520548, "grad_norm": 7459.8623046875, "learning_rate": 4.591911764705882e-05, "loss": 0.0993, "step": 212 }, { "epoch": 1.4589041095890412, "grad_norm": 5807.0439453125, "learning_rate": 4.588235294117647e-05, "loss": 0.0978, "step": 213 }, { "epoch": 1.4657534246575343, "grad_norm": 6110.4345703125, "learning_rate": 4.584558823529412e-05, "loss": 0.1048, "step": 214 }, { "epoch": 1.4726027397260273, "grad_norm": 8390.87109375, "learning_rate": 4.5808823529411764e-05, "loss": 0.0952, "step": 215 }, { "epoch": 1.4794520547945205, "grad_norm": 8570.6171875, "learning_rate": 4.577205882352941e-05, "loss": 0.1126, "step": 216 }, { "epoch": 1.4863013698630136, "grad_norm": 8216.21875, "learning_rate": 4.573529411764706e-05, "loss": 0.1215, "step": 217 }, { "epoch": 1.4931506849315068, "grad_norm": 7293.83447265625, "learning_rate": 4.569852941176471e-05, "loss": 0.1032, "step": 218 }, { "epoch": 1.5, "grad_norm": 7831.90234375, "learning_rate": 4.566176470588235e-05, "loss": 0.1127, "step": 219 }, { "epoch": 1.5068493150684932, "grad_norm": 7085.89599609375, "learning_rate": 4.5625e-05, "loss": 0.108, "step": 220 }, { "epoch": 1.5136986301369864, "grad_norm": 6184.080078125, "learning_rate": 4.558823529411765e-05, "loss": 0.1042, "step": 221 }, { "epoch": 1.5205479452054793, "grad_norm": 9069.4853515625, "learning_rate": 4.5551470588235295e-05, "loss": 0.1197, "step": 222 }, { "epoch": 1.5273972602739727, "grad_norm": 5565.07861328125, "learning_rate": 4.551470588235294e-05, "loss": 0.0859, "step": 223 }, { "epoch": 1.5342465753424657, "grad_norm": 8995.748046875, "learning_rate": 4.547794117647059e-05, "loss": 0.1346, "step": 224 }, { "epoch": 1.541095890410959, "grad_norm": 9742.046875, "learning_rate": 4.544117647058824e-05, "loss": 0.1201, "step": 225 }, { "epoch": 1.547945205479452, "grad_norm": 9440.0703125, "learning_rate": 4.5404411764705883e-05, "loss": 0.1029, "step": 226 }, { "epoch": 1.5547945205479452, "grad_norm": 11334.765625, "learning_rate": 4.536764705882353e-05, "loss": 0.0984, "step": 227 }, { "epoch": 1.5616438356164384, "grad_norm": 8359.0068359375, "learning_rate": 4.533088235294118e-05, "loss": 0.1023, "step": 228 }, { "epoch": 1.5684931506849316, "grad_norm": 8090.54150390625, "learning_rate": 4.5294117647058826e-05, "loss": 0.1232, "step": 229 }, { "epoch": 1.5753424657534247, "grad_norm": 7711.95556640625, "learning_rate": 4.525735294117647e-05, "loss": 0.0973, "step": 230 }, { "epoch": 1.5821917808219177, "grad_norm": 6313.77783203125, "learning_rate": 4.522058823529412e-05, "loss": 0.1045, "step": 231 }, { "epoch": 1.589041095890411, "grad_norm": 6809.267578125, "learning_rate": 4.518382352941177e-05, "loss": 0.106, "step": 232 }, { "epoch": 1.595890410958904, "grad_norm": 6950.990234375, "learning_rate": 4.5147058823529415e-05, "loss": 0.0918, "step": 233 }, { "epoch": 1.6027397260273972, "grad_norm": 8488.9462890625, "learning_rate": 4.511029411764706e-05, "loss": 0.1249, "step": 234 }, { "epoch": 1.6095890410958904, "grad_norm": 6941.8408203125, "learning_rate": 4.507352941176471e-05, "loss": 0.1157, "step": 235 }, { "epoch": 1.6164383561643836, "grad_norm": 7106.1103515625, "learning_rate": 4.503676470588236e-05, "loss": 0.1065, "step": 236 }, { "epoch": 1.6232876712328768, "grad_norm": 10947.8837890625, "learning_rate": 4.5e-05, "loss": 0.0931, "step": 237 }, { "epoch": 1.6301369863013697, "grad_norm": 8602.11328125, "learning_rate": 4.496323529411765e-05, "loss": 0.1011, "step": 238 }, { "epoch": 1.6369863013698631, "grad_norm": 6389.4345703125, "learning_rate": 4.49264705882353e-05, "loss": 0.0922, "step": 239 }, { "epoch": 1.643835616438356, "grad_norm": 6915.12451171875, "learning_rate": 4.4889705882352946e-05, "loss": 0.1049, "step": 240 }, { "epoch": 1.6506849315068495, "grad_norm": 6776.38525390625, "learning_rate": 4.485294117647059e-05, "loss": 0.0968, "step": 241 }, { "epoch": 1.6575342465753424, "grad_norm": 8686.3349609375, "learning_rate": 4.4816176470588236e-05, "loss": 0.0923, "step": 242 }, { "epoch": 1.6643835616438356, "grad_norm": 12123.1650390625, "learning_rate": 4.477941176470589e-05, "loss": 0.1324, "step": 243 }, { "epoch": 1.6712328767123288, "grad_norm": 7402.97314453125, "learning_rate": 4.4742647058823534e-05, "loss": 0.0952, "step": 244 }, { "epoch": 1.678082191780822, "grad_norm": 9577.775390625, "learning_rate": 4.470588235294118e-05, "loss": 0.0978, "step": 245 }, { "epoch": 1.6849315068493151, "grad_norm": 7227.2509765625, "learning_rate": 4.4669117647058825e-05, "loss": 0.1066, "step": 246 }, { "epoch": 1.691780821917808, "grad_norm": 11711.3359375, "learning_rate": 4.463235294117648e-05, "loss": 0.1064, "step": 247 }, { "epoch": 1.6986301369863015, "grad_norm": 14257.646484375, "learning_rate": 4.459558823529412e-05, "loss": 0.0922, "step": 248 }, { "epoch": 1.7054794520547945, "grad_norm": 7509.47119140625, "learning_rate": 4.455882352941177e-05, "loss": 0.097, "step": 249 }, { "epoch": 1.7123287671232876, "grad_norm": 6169.5751953125, "learning_rate": 4.452205882352941e-05, "loss": 0.0935, "step": 250 }, { "epoch": 1.7191780821917808, "grad_norm": 6637.474609375, "learning_rate": 4.448529411764706e-05, "loss": 0.1045, "step": 251 }, { "epoch": 1.726027397260274, "grad_norm": 8777.0068359375, "learning_rate": 4.4448529411764704e-05, "loss": 0.1095, "step": 252 }, { "epoch": 1.7328767123287672, "grad_norm": 7759.5595703125, "learning_rate": 4.4411764705882356e-05, "loss": 0.0893, "step": 253 }, { "epoch": 1.7397260273972601, "grad_norm": 6482.70556640625, "learning_rate": 4.4375e-05, "loss": 0.09, "step": 254 }, { "epoch": 1.7465753424657535, "grad_norm": 6385.28857421875, "learning_rate": 4.4338235294117647e-05, "loss": 0.0959, "step": 255 }, { "epoch": 1.7534246575342465, "grad_norm": 7996.22021484375, "learning_rate": 4.430147058823529e-05, "loss": 0.116, "step": 256 }, { "epoch": 1.7602739726027399, "grad_norm": 8335.6025390625, "learning_rate": 4.4264705882352944e-05, "loss": 0.0959, "step": 257 }, { "epoch": 1.7671232876712328, "grad_norm": 7788.5498046875, "learning_rate": 4.422794117647059e-05, "loss": 0.1102, "step": 258 }, { "epoch": 1.773972602739726, "grad_norm": 7955.65478515625, "learning_rate": 4.4191176470588235e-05, "loss": 0.0947, "step": 259 }, { "epoch": 1.7808219178082192, "grad_norm": 7436.2783203125, "learning_rate": 4.415441176470588e-05, "loss": 0.1056, "step": 260 }, { "epoch": 1.7876712328767124, "grad_norm": 7510.03662109375, "learning_rate": 4.411764705882353e-05, "loss": 0.0944, "step": 261 }, { "epoch": 1.7945205479452055, "grad_norm": 7410.8427734375, "learning_rate": 4.408088235294118e-05, "loss": 0.0973, "step": 262 }, { "epoch": 1.8013698630136985, "grad_norm": 7405.92822265625, "learning_rate": 4.404411764705882e-05, "loss": 0.0939, "step": 263 }, { "epoch": 1.808219178082192, "grad_norm": 6860.1044921875, "learning_rate": 4.400735294117647e-05, "loss": 0.0899, "step": 264 }, { "epoch": 1.8150684931506849, "grad_norm": 7136.47509765625, "learning_rate": 4.397058823529412e-05, "loss": 0.0915, "step": 265 }, { "epoch": 1.821917808219178, "grad_norm": 6130.75732421875, "learning_rate": 4.3933823529411766e-05, "loss": 0.0979, "step": 266 }, { "epoch": 1.8287671232876712, "grad_norm": 8399.8779296875, "learning_rate": 4.389705882352941e-05, "loss": 0.0849, "step": 267 }, { "epoch": 1.8356164383561644, "grad_norm": 7727.62060546875, "learning_rate": 4.3860294117647063e-05, "loss": 0.0934, "step": 268 }, { "epoch": 1.8424657534246576, "grad_norm": 7186.12060546875, "learning_rate": 4.382352941176471e-05, "loss": 0.0915, "step": 269 }, { "epoch": 1.8493150684931505, "grad_norm": 6508.896484375, "learning_rate": 4.3786764705882354e-05, "loss": 0.0903, "step": 270 }, { "epoch": 1.856164383561644, "grad_norm": 8441.95703125, "learning_rate": 4.375e-05, "loss": 0.0772, "step": 271 }, { "epoch": 1.8630136986301369, "grad_norm": 7860.8740234375, "learning_rate": 4.371323529411765e-05, "loss": 0.1041, "step": 272 }, { "epoch": 1.8698630136986303, "grad_norm": 7112.07177734375, "learning_rate": 4.36764705882353e-05, "loss": 0.1001, "step": 273 }, { "epoch": 1.8767123287671232, "grad_norm": 7572.97607421875, "learning_rate": 4.363970588235294e-05, "loss": 0.0908, "step": 274 }, { "epoch": 1.8835616438356164, "grad_norm": 8511.6474609375, "learning_rate": 4.360294117647059e-05, "loss": 0.0984, "step": 275 }, { "epoch": 1.8904109589041096, "grad_norm": 7513.7568359375, "learning_rate": 4.356617647058824e-05, "loss": 0.0925, "step": 276 }, { "epoch": 1.8972602739726028, "grad_norm": 7293.30615234375, "learning_rate": 4.3529411764705885e-05, "loss": 0.0794, "step": 277 }, { "epoch": 1.904109589041096, "grad_norm": 7897.21923828125, "learning_rate": 4.349264705882353e-05, "loss": 0.0999, "step": 278 }, { "epoch": 1.910958904109589, "grad_norm": 7267.3037109375, "learning_rate": 4.345588235294118e-05, "loss": 0.0884, "step": 279 }, { "epoch": 1.9178082191780823, "grad_norm": 7964.326171875, "learning_rate": 4.341911764705883e-05, "loss": 0.105, "step": 280 }, { "epoch": 1.9246575342465753, "grad_norm": 7533.4462890625, "learning_rate": 4.3382352941176474e-05, "loss": 0.0834, "step": 281 }, { "epoch": 1.9315068493150684, "grad_norm": 7497.66845703125, "learning_rate": 4.334558823529412e-05, "loss": 0.0989, "step": 282 }, { "epoch": 1.9383561643835616, "grad_norm": 8227.22265625, "learning_rate": 4.330882352941177e-05, "loss": 0.0986, "step": 283 }, { "epoch": 1.9452054794520548, "grad_norm": 8094.78857421875, "learning_rate": 4.3272058823529416e-05, "loss": 0.1029, "step": 284 }, { "epoch": 1.952054794520548, "grad_norm": 8206.1396484375, "learning_rate": 4.323529411764706e-05, "loss": 0.0942, "step": 285 }, { "epoch": 1.958904109589041, "grad_norm": 8282.9609375, "learning_rate": 4.319852941176471e-05, "loss": 0.0921, "step": 286 }, { "epoch": 1.9657534246575343, "grad_norm": 7492.50634765625, "learning_rate": 4.316176470588236e-05, "loss": 0.0847, "step": 287 }, { "epoch": 1.9726027397260273, "grad_norm": 7649.80029296875, "learning_rate": 4.3125000000000005e-05, "loss": 0.083, "step": 288 }, { "epoch": 1.9794520547945207, "grad_norm": 7907.5927734375, "learning_rate": 4.308823529411765e-05, "loss": 0.0881, "step": 289 }, { "epoch": 1.9863013698630136, "grad_norm": 7580.23095703125, "learning_rate": 4.3051470588235295e-05, "loss": 0.1038, "step": 290 }, { "epoch": 1.9931506849315068, "grad_norm": 7234.494140625, "learning_rate": 4.301470588235295e-05, "loss": 0.0916, "step": 291 }, { "epoch": 2.0, "grad_norm": 9618.341796875, "learning_rate": 4.297794117647059e-05, "loss": 0.0844, "step": 292 }, { "epoch": 2.0, "eval_f1_macro": 0.04840095083997523, "eval_f1_micro": 0.3659305993690852, "eval_loss": 0.08943719416856766, "eval_precision": 0.8226950354609929, "eval_recall": 0.23529411764705882, "eval_runtime": 1.0899, "eval_samples_per_second": 356.9, "eval_steps_per_second": 15.597, "step": 292 }, { "epoch": 2.006849315068493, "grad_norm": 9403.65234375, "learning_rate": 4.294117647058823e-05, "loss": 0.08, "step": 293 }, { "epoch": 2.0136986301369864, "grad_norm": 6781.734375, "learning_rate": 4.2904411764705884e-05, "loss": 0.0753, "step": 294 }, { "epoch": 2.0205479452054793, "grad_norm": 8872.84765625, "learning_rate": 4.286764705882353e-05, "loss": 0.0979, "step": 295 }, { "epoch": 2.0273972602739727, "grad_norm": 7737.91845703125, "learning_rate": 4.2830882352941174e-05, "loss": 0.0931, "step": 296 }, { "epoch": 2.0342465753424657, "grad_norm": 7718.1337890625, "learning_rate": 4.2794117647058827e-05, "loss": 0.0856, "step": 297 }, { "epoch": 2.041095890410959, "grad_norm": 8382.8125, "learning_rate": 4.275735294117647e-05, "loss": 0.0828, "step": 298 }, { "epoch": 2.047945205479452, "grad_norm": 10513.3935546875, "learning_rate": 4.272058823529412e-05, "loss": 0.1035, "step": 299 }, { "epoch": 2.0547945205479454, "grad_norm": 7395.0673828125, "learning_rate": 4.268382352941176e-05, "loss": 0.1012, "step": 300 }, { "epoch": 2.0616438356164384, "grad_norm": 7629.2255859375, "learning_rate": 4.2647058823529415e-05, "loss": 0.0959, "step": 301 }, { "epoch": 2.0684931506849313, "grad_norm": 9145.5947265625, "learning_rate": 4.261029411764706e-05, "loss": 0.0793, "step": 302 }, { "epoch": 2.0753424657534247, "grad_norm": 7487.2109375, "learning_rate": 4.2573529411764706e-05, "loss": 0.0869, "step": 303 }, { "epoch": 2.0821917808219177, "grad_norm": 6452.27392578125, "learning_rate": 4.253676470588235e-05, "loss": 0.0853, "step": 304 }, { "epoch": 2.089041095890411, "grad_norm": 6600.908203125, "learning_rate": 4.25e-05, "loss": 0.0748, "step": 305 }, { "epoch": 2.095890410958904, "grad_norm": 8203.083984375, "learning_rate": 4.246323529411765e-05, "loss": 0.0932, "step": 306 }, { "epoch": 2.1027397260273974, "grad_norm": 7487.896484375, "learning_rate": 4.2426470588235294e-05, "loss": 0.0913, "step": 307 }, { "epoch": 2.1095890410958904, "grad_norm": 7736.96728515625, "learning_rate": 4.238970588235294e-05, "loss": 0.0959, "step": 308 }, { "epoch": 2.1164383561643834, "grad_norm": 8469.23046875, "learning_rate": 4.235294117647059e-05, "loss": 0.0868, "step": 309 }, { "epoch": 2.1232876712328768, "grad_norm": 7852.525390625, "learning_rate": 4.231617647058824e-05, "loss": 0.0831, "step": 310 }, { "epoch": 2.1301369863013697, "grad_norm": 7601.58203125, "learning_rate": 4.227941176470588e-05, "loss": 0.0855, "step": 311 }, { "epoch": 2.136986301369863, "grad_norm": 6888.62646484375, "learning_rate": 4.2242647058823534e-05, "loss": 0.0848, "step": 312 }, { "epoch": 2.143835616438356, "grad_norm": 6197.84619140625, "learning_rate": 4.220588235294118e-05, "loss": 0.082, "step": 313 }, { "epoch": 2.1506849315068495, "grad_norm": 7650.23583984375, "learning_rate": 4.2169117647058825e-05, "loss": 0.0908, "step": 314 }, { "epoch": 2.1575342465753424, "grad_norm": 7945.35107421875, "learning_rate": 4.213235294117647e-05, "loss": 0.0909, "step": 315 }, { "epoch": 2.1643835616438354, "grad_norm": 8849.48828125, "learning_rate": 4.209558823529412e-05, "loss": 0.0908, "step": 316 }, { "epoch": 2.171232876712329, "grad_norm": 6683.9560546875, "learning_rate": 4.205882352941177e-05, "loss": 0.085, "step": 317 }, { "epoch": 2.1780821917808217, "grad_norm": 9759.4287109375, "learning_rate": 4.202205882352941e-05, "loss": 0.0817, "step": 318 }, { "epoch": 2.184931506849315, "grad_norm": 9102.291015625, "learning_rate": 4.198529411764706e-05, "loss": 0.0972, "step": 319 }, { "epoch": 2.191780821917808, "grad_norm": 7668.04833984375, "learning_rate": 4.194852941176471e-05, "loss": 0.0827, "step": 320 }, { "epoch": 2.1986301369863015, "grad_norm": 6085.779296875, "learning_rate": 4.1911764705882356e-05, "loss": 0.0736, "step": 321 }, { "epoch": 2.2054794520547945, "grad_norm": 7270.31201171875, "learning_rate": 4.1875e-05, "loss": 0.0912, "step": 322 }, { "epoch": 2.212328767123288, "grad_norm": 7695.744140625, "learning_rate": 4.1838235294117654e-05, "loss": 0.073, "step": 323 }, { "epoch": 2.219178082191781, "grad_norm": 7369.44189453125, "learning_rate": 4.18014705882353e-05, "loss": 0.085, "step": 324 }, { "epoch": 2.2260273972602738, "grad_norm": 14132.6318359375, "learning_rate": 4.1764705882352944e-05, "loss": 0.0923, "step": 325 }, { "epoch": 2.232876712328767, "grad_norm": 7908.48974609375, "learning_rate": 4.172794117647059e-05, "loss": 0.0834, "step": 326 }, { "epoch": 2.23972602739726, "grad_norm": 7263.966796875, "learning_rate": 4.169117647058824e-05, "loss": 0.0859, "step": 327 }, { "epoch": 2.2465753424657535, "grad_norm": 12272.375, "learning_rate": 4.165441176470589e-05, "loss": 0.088, "step": 328 }, { "epoch": 2.2534246575342465, "grad_norm": 6609.49853515625, "learning_rate": 4.161764705882353e-05, "loss": 0.0788, "step": 329 }, { "epoch": 2.26027397260274, "grad_norm": 7770.97021484375, "learning_rate": 4.158088235294118e-05, "loss": 0.0898, "step": 330 }, { "epoch": 2.267123287671233, "grad_norm": 8534.4541015625, "learning_rate": 4.154411764705883e-05, "loss": 0.0849, "step": 331 }, { "epoch": 2.2739726027397262, "grad_norm": 7029.560546875, "learning_rate": 4.1507352941176475e-05, "loss": 0.073, "step": 332 }, { "epoch": 2.280821917808219, "grad_norm": 7754.3388671875, "learning_rate": 4.147058823529412e-05, "loss": 0.0766, "step": 333 }, { "epoch": 2.287671232876712, "grad_norm": 8097.3037109375, "learning_rate": 4.1433823529411766e-05, "loss": 0.0808, "step": 334 }, { "epoch": 2.2945205479452055, "grad_norm": 7905.76318359375, "learning_rate": 4.139705882352941e-05, "loss": 0.0787, "step": 335 }, { "epoch": 2.3013698630136985, "grad_norm": 8071.15478515625, "learning_rate": 4.136029411764706e-05, "loss": 0.0848, "step": 336 }, { "epoch": 2.308219178082192, "grad_norm": 6366.6357421875, "learning_rate": 4.13235294117647e-05, "loss": 0.074, "step": 337 }, { "epoch": 2.315068493150685, "grad_norm": 6685.9775390625, "learning_rate": 4.1286764705882354e-05, "loss": 0.0929, "step": 338 }, { "epoch": 2.3219178082191783, "grad_norm": 7068.87255859375, "learning_rate": 4.125e-05, "loss": 0.0762, "step": 339 }, { "epoch": 2.328767123287671, "grad_norm": 7607.4091796875, "learning_rate": 4.1213235294117645e-05, "loss": 0.0831, "step": 340 }, { "epoch": 2.3356164383561646, "grad_norm": 6388.318359375, "learning_rate": 4.11764705882353e-05, "loss": 0.0763, "step": 341 }, { "epoch": 2.3424657534246576, "grad_norm": 7107.830078125, "learning_rate": 4.113970588235294e-05, "loss": 0.0704, "step": 342 }, { "epoch": 2.3493150684931505, "grad_norm": 6302.0693359375, "learning_rate": 4.110294117647059e-05, "loss": 0.0671, "step": 343 }, { "epoch": 2.356164383561644, "grad_norm": 6883.36083984375, "learning_rate": 4.1066176470588233e-05, "loss": 0.0682, "step": 344 }, { "epoch": 2.363013698630137, "grad_norm": 6963.70166015625, "learning_rate": 4.1029411764705886e-05, "loss": 0.0723, "step": 345 }, { "epoch": 2.3698630136986303, "grad_norm": 7682.451171875, "learning_rate": 4.099264705882353e-05, "loss": 0.0891, "step": 346 }, { "epoch": 2.3767123287671232, "grad_norm": 8395.9443359375, "learning_rate": 4.0955882352941176e-05, "loss": 0.079, "step": 347 }, { "epoch": 2.383561643835616, "grad_norm": 9870.103515625, "learning_rate": 4.091911764705882e-05, "loss": 0.0811, "step": 348 }, { "epoch": 2.3904109589041096, "grad_norm": 6436.81298828125, "learning_rate": 4.0882352941176474e-05, "loss": 0.0745, "step": 349 }, { "epoch": 2.3972602739726026, "grad_norm": 6816.47509765625, "learning_rate": 4.084558823529412e-05, "loss": 0.0725, "step": 350 }, { "epoch": 2.404109589041096, "grad_norm": 7977.06298828125, "learning_rate": 4.0808823529411765e-05, "loss": 0.066, "step": 351 }, { "epoch": 2.410958904109589, "grad_norm": 7857.92578125, "learning_rate": 4.077205882352941e-05, "loss": 0.0783, "step": 352 }, { "epoch": 2.4178082191780823, "grad_norm": 7024.62744140625, "learning_rate": 4.073529411764706e-05, "loss": 0.0745, "step": 353 }, { "epoch": 2.4246575342465753, "grad_norm": 9508.865234375, "learning_rate": 4.069852941176471e-05, "loss": 0.0917, "step": 354 }, { "epoch": 2.4315068493150687, "grad_norm": 7849.15478515625, "learning_rate": 4.066176470588235e-05, "loss": 0.0813, "step": 355 }, { "epoch": 2.4383561643835616, "grad_norm": 8311.88671875, "learning_rate": 4.0625000000000005e-05, "loss": 0.0762, "step": 356 }, { "epoch": 2.4452054794520546, "grad_norm": 10212.1337890625, "learning_rate": 4.058823529411765e-05, "loss": 0.0882, "step": 357 }, { "epoch": 2.452054794520548, "grad_norm": 12522.037109375, "learning_rate": 4.0551470588235296e-05, "loss": 0.0679, "step": 358 }, { "epoch": 2.458904109589041, "grad_norm": 7783.009765625, "learning_rate": 4.051470588235294e-05, "loss": 0.0831, "step": 359 }, { "epoch": 2.4657534246575343, "grad_norm": 7538.6298828125, "learning_rate": 4.047794117647059e-05, "loss": 0.0731, "step": 360 }, { "epoch": 2.4726027397260273, "grad_norm": 7176.2021484375, "learning_rate": 4.044117647058824e-05, "loss": 0.0657, "step": 361 }, { "epoch": 2.4794520547945207, "grad_norm": 8570.9140625, "learning_rate": 4.0404411764705884e-05, "loss": 0.0754, "step": 362 }, { "epoch": 2.4863013698630136, "grad_norm": 8446.9755859375, "learning_rate": 4.036764705882353e-05, "loss": 0.0741, "step": 363 }, { "epoch": 2.493150684931507, "grad_norm": 8465.7919921875, "learning_rate": 4.033088235294118e-05, "loss": 0.0723, "step": 364 }, { "epoch": 2.5, "grad_norm": 7987.8369140625, "learning_rate": 4.029411764705883e-05, "loss": 0.0766, "step": 365 }, { "epoch": 2.506849315068493, "grad_norm": 9649.9150390625, "learning_rate": 4.025735294117647e-05, "loss": 0.1033, "step": 366 }, { "epoch": 2.5136986301369864, "grad_norm": 10749.3037109375, "learning_rate": 4.0220588235294124e-05, "loss": 0.0803, "step": 367 }, { "epoch": 2.5205479452054793, "grad_norm": 7179.810546875, "learning_rate": 4.018382352941177e-05, "loss": 0.0838, "step": 368 }, { "epoch": 2.5273972602739727, "grad_norm": 11326.7919921875, "learning_rate": 4.0147058823529415e-05, "loss": 0.0895, "step": 369 }, { "epoch": 2.5342465753424657, "grad_norm": 9264.5908203125, "learning_rate": 4.011029411764706e-05, "loss": 0.0817, "step": 370 }, { "epoch": 2.541095890410959, "grad_norm": 12358.748046875, "learning_rate": 4.007352941176471e-05, "loss": 0.0919, "step": 371 }, { "epoch": 2.547945205479452, "grad_norm": 6950.76806640625, "learning_rate": 4.003676470588236e-05, "loss": 0.075, "step": 372 }, { "epoch": 2.5547945205479454, "grad_norm": 7461.916015625, "learning_rate": 4e-05, "loss": 0.0715, "step": 373 }, { "epoch": 2.5616438356164384, "grad_norm": 8036.46728515625, "learning_rate": 3.996323529411765e-05, "loss": 0.0848, "step": 374 }, { "epoch": 2.5684931506849313, "grad_norm": 6753.29296875, "learning_rate": 3.99264705882353e-05, "loss": 0.0704, "step": 375 }, { "epoch": 2.5753424657534247, "grad_norm": 6928.373046875, "learning_rate": 3.9889705882352946e-05, "loss": 0.0626, "step": 376 }, { "epoch": 2.5821917808219177, "grad_norm": 7438.43017578125, "learning_rate": 3.985294117647059e-05, "loss": 0.0738, "step": 377 }, { "epoch": 2.589041095890411, "grad_norm": 6948.525390625, "learning_rate": 3.981617647058824e-05, "loss": 0.0625, "step": 378 }, { "epoch": 2.595890410958904, "grad_norm": 9865.8359375, "learning_rate": 3.977941176470588e-05, "loss": 0.087, "step": 379 }, { "epoch": 2.602739726027397, "grad_norm": 8448.2587890625, "learning_rate": 3.974264705882353e-05, "loss": 0.0772, "step": 380 }, { "epoch": 2.6095890410958904, "grad_norm": 9079.615234375, "learning_rate": 3.970588235294117e-05, "loss": 0.0673, "step": 381 }, { "epoch": 2.616438356164384, "grad_norm": 11972.0771484375, "learning_rate": 3.9669117647058825e-05, "loss": 0.0697, "step": 382 }, { "epoch": 2.6232876712328768, "grad_norm": 9496.873046875, "learning_rate": 3.963235294117647e-05, "loss": 0.0712, "step": 383 }, { "epoch": 2.6301369863013697, "grad_norm": 7563.94287109375, "learning_rate": 3.9595588235294116e-05, "loss": 0.0578, "step": 384 }, { "epoch": 2.636986301369863, "grad_norm": 9942.9794921875, "learning_rate": 3.955882352941177e-05, "loss": 0.0705, "step": 385 }, { "epoch": 2.643835616438356, "grad_norm": 7392.53466796875, "learning_rate": 3.952205882352941e-05, "loss": 0.0643, "step": 386 }, { "epoch": 2.6506849315068495, "grad_norm": 11520.888671875, "learning_rate": 3.948529411764706e-05, "loss": 0.1091, "step": 387 }, { "epoch": 2.6575342465753424, "grad_norm": 6539.70947265625, "learning_rate": 3.9448529411764704e-05, "loss": 0.0639, "step": 388 }, { "epoch": 2.6643835616438354, "grad_norm": 11622.4482421875, "learning_rate": 3.9411764705882356e-05, "loss": 0.0793, "step": 389 }, { "epoch": 2.671232876712329, "grad_norm": 9539.5302734375, "learning_rate": 3.9375e-05, "loss": 0.063, "step": 390 }, { "epoch": 2.678082191780822, "grad_norm": 10741.65234375, "learning_rate": 3.933823529411765e-05, "loss": 0.0599, "step": 391 }, { "epoch": 2.684931506849315, "grad_norm": 13216.44140625, "learning_rate": 3.930147058823529e-05, "loss": 0.0731, "step": 392 }, { "epoch": 2.691780821917808, "grad_norm": 10555.3974609375, "learning_rate": 3.9264705882352945e-05, "loss": 0.0841, "step": 393 }, { "epoch": 2.6986301369863015, "grad_norm": 8293.837890625, "learning_rate": 3.922794117647059e-05, "loss": 0.0657, "step": 394 }, { "epoch": 2.7054794520547945, "grad_norm": 9788.69921875, "learning_rate": 3.9191176470588235e-05, "loss": 0.0829, "step": 395 }, { "epoch": 2.712328767123288, "grad_norm": 9236.0634765625, "learning_rate": 3.915441176470588e-05, "loss": 0.0731, "step": 396 }, { "epoch": 2.719178082191781, "grad_norm": 13464.94140625, "learning_rate": 3.911764705882353e-05, "loss": 0.078, "step": 397 }, { "epoch": 2.7260273972602738, "grad_norm": 7960.7314453125, "learning_rate": 3.908088235294118e-05, "loss": 0.0627, "step": 398 }, { "epoch": 2.732876712328767, "grad_norm": 8860.734375, "learning_rate": 3.9044117647058823e-05, "loss": 0.0658, "step": 399 }, { "epoch": 2.73972602739726, "grad_norm": 8913.1884765625, "learning_rate": 3.9007352941176476e-05, "loss": 0.0683, "step": 400 }, { "epoch": 2.7465753424657535, "grad_norm": 8187.23388671875, "learning_rate": 3.897058823529412e-05, "loss": 0.0765, "step": 401 }, { "epoch": 2.7534246575342465, "grad_norm": 7800.19482421875, "learning_rate": 3.8933823529411766e-05, "loss": 0.0821, "step": 402 }, { "epoch": 2.76027397260274, "grad_norm": 9376.4443359375, "learning_rate": 3.889705882352941e-05, "loss": 0.0591, "step": 403 }, { "epoch": 2.767123287671233, "grad_norm": 19803.41015625, "learning_rate": 3.8860294117647064e-05, "loss": 0.1026, "step": 404 }, { "epoch": 2.7739726027397262, "grad_norm": 10698.9384765625, "learning_rate": 3.882352941176471e-05, "loss": 0.0683, "step": 405 }, { "epoch": 2.780821917808219, "grad_norm": 7618.62939453125, "learning_rate": 3.8786764705882355e-05, "loss": 0.0741, "step": 406 }, { "epoch": 2.787671232876712, "grad_norm": 6664.30859375, "learning_rate": 3.875e-05, "loss": 0.074, "step": 407 }, { "epoch": 2.7945205479452055, "grad_norm": 7914.8125, "learning_rate": 3.871323529411765e-05, "loss": 0.0695, "step": 408 }, { "epoch": 2.8013698630136985, "grad_norm": 6096.96337890625, "learning_rate": 3.86764705882353e-05, "loss": 0.0698, "step": 409 }, { "epoch": 2.808219178082192, "grad_norm": 7265.603515625, "learning_rate": 3.863970588235294e-05, "loss": 0.0657, "step": 410 }, { "epoch": 2.815068493150685, "grad_norm": 9744.8466796875, "learning_rate": 3.8602941176470595e-05, "loss": 0.0865, "step": 411 }, { "epoch": 2.821917808219178, "grad_norm": 8634.9326171875, "learning_rate": 3.856617647058824e-05, "loss": 0.0669, "step": 412 }, { "epoch": 2.828767123287671, "grad_norm": 9899.671875, "learning_rate": 3.8529411764705886e-05, "loss": 0.0658, "step": 413 }, { "epoch": 2.8356164383561646, "grad_norm": 8723.8583984375, "learning_rate": 3.849264705882353e-05, "loss": 0.0631, "step": 414 }, { "epoch": 2.8424657534246576, "grad_norm": 10427.3671875, "learning_rate": 3.845588235294118e-05, "loss": 0.063, "step": 415 }, { "epoch": 2.8493150684931505, "grad_norm": 11623.6123046875, "learning_rate": 3.841911764705883e-05, "loss": 0.0686, "step": 416 }, { "epoch": 2.856164383561644, "grad_norm": 8653.7939453125, "learning_rate": 3.8382352941176474e-05, "loss": 0.0815, "step": 417 }, { "epoch": 2.863013698630137, "grad_norm": 7602.724609375, "learning_rate": 3.834558823529412e-05, "loss": 0.0697, "step": 418 }, { "epoch": 2.8698630136986303, "grad_norm": 7877.53466796875, "learning_rate": 3.830882352941177e-05, "loss": 0.0677, "step": 419 }, { "epoch": 2.8767123287671232, "grad_norm": 9370.23046875, "learning_rate": 3.827205882352941e-05, "loss": 0.0628, "step": 420 }, { "epoch": 2.883561643835616, "grad_norm": 8625.6865234375, "learning_rate": 3.8235294117647055e-05, "loss": 0.0699, "step": 421 }, { "epoch": 2.8904109589041096, "grad_norm": 7611.470703125, "learning_rate": 3.819852941176471e-05, "loss": 0.0786, "step": 422 }, { "epoch": 2.897260273972603, "grad_norm": 9584.7412109375, "learning_rate": 3.816176470588235e-05, "loss": 0.0828, "step": 423 }, { "epoch": 2.904109589041096, "grad_norm": 9874.900390625, "learning_rate": 3.8125e-05, "loss": 0.0735, "step": 424 }, { "epoch": 2.910958904109589, "grad_norm": 8986.53125, "learning_rate": 3.8088235294117644e-05, "loss": 0.0767, "step": 425 }, { "epoch": 2.9178082191780823, "grad_norm": 9692.7919921875, "learning_rate": 3.8051470588235296e-05, "loss": 0.0756, "step": 426 }, { "epoch": 2.9246575342465753, "grad_norm": 9400.916015625, "learning_rate": 3.801470588235294e-05, "loss": 0.0708, "step": 427 }, { "epoch": 2.9315068493150687, "grad_norm": 7663.86572265625, "learning_rate": 3.7977941176470587e-05, "loss": 0.0667, "step": 428 }, { "epoch": 2.9383561643835616, "grad_norm": 8155.3193359375, "learning_rate": 3.794117647058824e-05, "loss": 0.0584, "step": 429 }, { "epoch": 2.9452054794520546, "grad_norm": 7708.685546875, "learning_rate": 3.7904411764705884e-05, "loss": 0.081, "step": 430 }, { "epoch": 2.952054794520548, "grad_norm": 9798.2255859375, "learning_rate": 3.786764705882353e-05, "loss": 0.0782, "step": 431 }, { "epoch": 2.958904109589041, "grad_norm": 7708.298828125, "learning_rate": 3.7830882352941175e-05, "loss": 0.0691, "step": 432 }, { "epoch": 2.9657534246575343, "grad_norm": 8793.36328125, "learning_rate": 3.779411764705883e-05, "loss": 0.059, "step": 433 }, { "epoch": 2.9726027397260273, "grad_norm": 7797.23486328125, "learning_rate": 3.775735294117647e-05, "loss": 0.0751, "step": 434 }, { "epoch": 2.9794520547945207, "grad_norm": 11875.5400390625, "learning_rate": 3.772058823529412e-05, "loss": 0.0542, "step": 435 }, { "epoch": 2.9863013698630136, "grad_norm": 8204.65625, "learning_rate": 3.768382352941176e-05, "loss": 0.0566, "step": 436 }, { "epoch": 2.993150684931507, "grad_norm": 7569.85205078125, "learning_rate": 3.7647058823529415e-05, "loss": 0.0804, "step": 437 }, { "epoch": 3.0, "grad_norm": 10447.3017578125, "learning_rate": 3.761029411764706e-05, "loss": 0.0536, "step": 438 }, { "epoch": 3.0, "eval_f1_macro": 0.29090020092033053, "eval_f1_micro": 0.6608040201005025, "eval_loss": 0.06574681401252747, "eval_precision": 0.8679867986798679, "eval_recall": 0.5334685598377282, "eval_runtime": 1.0883, "eval_samples_per_second": 357.453, "eval_steps_per_second": 15.621, "step": 438 }, { "epoch": 3.006849315068493, "grad_norm": 7769.32861328125, "learning_rate": 3.7573529411764706e-05, "loss": 0.0675, "step": 439 }, { "epoch": 3.0136986301369864, "grad_norm": 7002.2197265625, "learning_rate": 3.753676470588235e-05, "loss": 0.0527, "step": 440 }, { "epoch": 3.0205479452054793, "grad_norm": 8344.6181640625, "learning_rate": 3.7500000000000003e-05, "loss": 0.0665, "step": 441 }, { "epoch": 3.0273972602739727, "grad_norm": 7639.59228515625, "learning_rate": 3.746323529411765e-05, "loss": 0.0594, "step": 442 }, { "epoch": 3.0342465753424657, "grad_norm": 6662.47412109375, "learning_rate": 3.7426470588235294e-05, "loss": 0.0576, "step": 443 }, { "epoch": 3.041095890410959, "grad_norm": 8681.5185546875, "learning_rate": 3.7389705882352946e-05, "loss": 0.0678, "step": 444 }, { "epoch": 3.047945205479452, "grad_norm": 6818.10986328125, "learning_rate": 3.735294117647059e-05, "loss": 0.0673, "step": 445 }, { "epoch": 3.0547945205479454, "grad_norm": 7014.423828125, "learning_rate": 3.731617647058824e-05, "loss": 0.0681, "step": 446 }, { "epoch": 3.0616438356164384, "grad_norm": 6639.5673828125, "learning_rate": 3.727941176470588e-05, "loss": 0.0579, "step": 447 }, { "epoch": 3.0684931506849313, "grad_norm": 8156.24755859375, "learning_rate": 3.7242647058823535e-05, "loss": 0.066, "step": 448 }, { "epoch": 3.0753424657534247, "grad_norm": 10190.4921875, "learning_rate": 3.720588235294118e-05, "loss": 0.0825, "step": 449 }, { "epoch": 3.0821917808219177, "grad_norm": 8291.2978515625, "learning_rate": 3.7169117647058825e-05, "loss": 0.0603, "step": 450 }, { "epoch": 3.089041095890411, "grad_norm": 8056.96728515625, "learning_rate": 3.713235294117647e-05, "loss": 0.0787, "step": 451 }, { "epoch": 3.095890410958904, "grad_norm": 6453.16845703125, "learning_rate": 3.709558823529412e-05, "loss": 0.0523, "step": 452 }, { "epoch": 3.1027397260273974, "grad_norm": 7565.87109375, "learning_rate": 3.705882352941177e-05, "loss": 0.0621, "step": 453 }, { "epoch": 3.1095890410958904, "grad_norm": 6165.97705078125, "learning_rate": 3.7022058823529414e-05, "loss": 0.0472, "step": 454 }, { "epoch": 3.1164383561643834, "grad_norm": 5584.9091796875, "learning_rate": 3.6985294117647066e-05, "loss": 0.0476, "step": 455 }, { "epoch": 3.1232876712328768, "grad_norm": 8257.4814453125, "learning_rate": 3.694852941176471e-05, "loss": 0.0761, "step": 456 }, { "epoch": 3.1301369863013697, "grad_norm": 8592.46875, "learning_rate": 3.6911764705882356e-05, "loss": 0.0771, "step": 457 }, { "epoch": 3.136986301369863, "grad_norm": 7445.4091796875, "learning_rate": 3.6875e-05, "loss": 0.0613, "step": 458 }, { "epoch": 3.143835616438356, "grad_norm": 10099.1103515625, "learning_rate": 3.6838235294117654e-05, "loss": 0.071, "step": 459 }, { "epoch": 3.1506849315068495, "grad_norm": 7846.50341796875, "learning_rate": 3.68014705882353e-05, "loss": 0.0616, "step": 460 }, { "epoch": 3.1575342465753424, "grad_norm": 6569.95751953125, "learning_rate": 3.6764705882352945e-05, "loss": 0.0581, "step": 461 }, { "epoch": 3.1643835616438354, "grad_norm": 7518.82861328125, "learning_rate": 3.672794117647059e-05, "loss": 0.0561, "step": 462 }, { "epoch": 3.171232876712329, "grad_norm": 7350.41015625, "learning_rate": 3.6691176470588235e-05, "loss": 0.0559, "step": 463 }, { "epoch": 3.1780821917808217, "grad_norm": 6280.77783203125, "learning_rate": 3.665441176470588e-05, "loss": 0.0489, "step": 464 }, { "epoch": 3.184931506849315, "grad_norm": 7729.423828125, "learning_rate": 3.6617647058823526e-05, "loss": 0.06, "step": 465 }, { "epoch": 3.191780821917808, "grad_norm": 6472.66552734375, "learning_rate": 3.658088235294118e-05, "loss": 0.0549, "step": 466 }, { "epoch": 3.1986301369863015, "grad_norm": 7257.470703125, "learning_rate": 3.6544117647058824e-05, "loss": 0.0558, "step": 467 }, { "epoch": 3.2054794520547945, "grad_norm": 10437.4931640625, "learning_rate": 3.650735294117647e-05, "loss": 0.0643, "step": 468 }, { "epoch": 3.212328767123288, "grad_norm": 8019.48974609375, "learning_rate": 3.6470588235294114e-05, "loss": 0.061, "step": 469 }, { "epoch": 3.219178082191781, "grad_norm": 6578.49609375, "learning_rate": 3.6433823529411767e-05, "loss": 0.0498, "step": 470 }, { "epoch": 3.2260273972602738, "grad_norm": 8208.3271484375, "learning_rate": 3.639705882352941e-05, "loss": 0.049, "step": 471 }, { "epoch": 3.232876712328767, "grad_norm": 6771.33935546875, "learning_rate": 3.636029411764706e-05, "loss": 0.0617, "step": 472 }, { "epoch": 3.23972602739726, "grad_norm": 7089.5048828125, "learning_rate": 3.632352941176471e-05, "loss": 0.0486, "step": 473 }, { "epoch": 3.2465753424657535, "grad_norm": 7658.41259765625, "learning_rate": 3.6286764705882355e-05, "loss": 0.0658, "step": 474 }, { "epoch": 3.2534246575342465, "grad_norm": 7309.439453125, "learning_rate": 3.625e-05, "loss": 0.05, "step": 475 }, { "epoch": 3.26027397260274, "grad_norm": 7310.05419921875, "learning_rate": 3.6213235294117646e-05, "loss": 0.0584, "step": 476 }, { "epoch": 3.267123287671233, "grad_norm": 8330.5419921875, "learning_rate": 3.61764705882353e-05, "loss": 0.0605, "step": 477 }, { "epoch": 3.2739726027397262, "grad_norm": 8102.61279296875, "learning_rate": 3.613970588235294e-05, "loss": 0.0703, "step": 478 }, { "epoch": 3.280821917808219, "grad_norm": 8840.4716796875, "learning_rate": 3.610294117647059e-05, "loss": 0.05, "step": 479 }, { "epoch": 3.287671232876712, "grad_norm": 6995.53076171875, "learning_rate": 3.6066176470588234e-05, "loss": 0.0576, "step": 480 }, { "epoch": 3.2945205479452055, "grad_norm": 5832.85400390625, "learning_rate": 3.6029411764705886e-05, "loss": 0.0512, "step": 481 }, { "epoch": 3.3013698630136985, "grad_norm": 8592.9697265625, "learning_rate": 3.599264705882353e-05, "loss": 0.0562, "step": 482 }, { "epoch": 3.308219178082192, "grad_norm": 9499.1865234375, "learning_rate": 3.595588235294118e-05, "loss": 0.0624, "step": 483 }, { "epoch": 3.315068493150685, "grad_norm": 8452.1162109375, "learning_rate": 3.591911764705882e-05, "loss": 0.0476, "step": 484 }, { "epoch": 3.3219178082191783, "grad_norm": 8527.08203125, "learning_rate": 3.5882352941176474e-05, "loss": 0.0607, "step": 485 }, { "epoch": 3.328767123287671, "grad_norm": 6453.51611328125, "learning_rate": 3.584558823529412e-05, "loss": 0.0397, "step": 486 }, { "epoch": 3.3356164383561646, "grad_norm": 9219.9453125, "learning_rate": 3.5808823529411765e-05, "loss": 0.0603, "step": 487 }, { "epoch": 3.3424657534246576, "grad_norm": 10501.3359375, "learning_rate": 3.577205882352942e-05, "loss": 0.0624, "step": 488 }, { "epoch": 3.3493150684931505, "grad_norm": 7475.38525390625, "learning_rate": 3.573529411764706e-05, "loss": 0.0547, "step": 489 }, { "epoch": 3.356164383561644, "grad_norm": 6072.75146484375, "learning_rate": 3.569852941176471e-05, "loss": 0.0633, "step": 490 }, { "epoch": 3.363013698630137, "grad_norm": 7023.109375, "learning_rate": 3.566176470588235e-05, "loss": 0.0554, "step": 491 }, { "epoch": 3.3698630136986303, "grad_norm": 9332.962890625, "learning_rate": 3.5625000000000005e-05, "loss": 0.0666, "step": 492 }, { "epoch": 3.3767123287671232, "grad_norm": 7166.3525390625, "learning_rate": 3.558823529411765e-05, "loss": 0.0552, "step": 493 }, { "epoch": 3.383561643835616, "grad_norm": 7592.74267578125, "learning_rate": 3.5551470588235296e-05, "loss": 0.0646, "step": 494 }, { "epoch": 3.3904109589041096, "grad_norm": 12950.736328125, "learning_rate": 3.551470588235294e-05, "loss": 0.0637, "step": 495 }, { "epoch": 3.3972602739726026, "grad_norm": 8627.017578125, "learning_rate": 3.5477941176470594e-05, "loss": 0.0622, "step": 496 }, { "epoch": 3.404109589041096, "grad_norm": 7502.42138671875, "learning_rate": 3.544117647058824e-05, "loss": 0.0644, "step": 497 }, { "epoch": 3.410958904109589, "grad_norm": 6842.67236328125, "learning_rate": 3.5404411764705884e-05, "loss": 0.0547, "step": 498 }, { "epoch": 3.4178082191780823, "grad_norm": 8876.109375, "learning_rate": 3.5367647058823536e-05, "loss": 0.0481, "step": 499 }, { "epoch": 3.4246575342465753, "grad_norm": 9320.849609375, "learning_rate": 3.533088235294118e-05, "loss": 0.0568, "step": 500 }, { "epoch": 3.4315068493150687, "grad_norm": 7541.18212890625, "learning_rate": 3.529411764705883e-05, "loss": 0.0531, "step": 501 }, { "epoch": 3.4383561643835616, "grad_norm": 5524.39892578125, "learning_rate": 3.525735294117647e-05, "loss": 0.0553, "step": 502 }, { "epoch": 3.4452054794520546, "grad_norm": 8874.314453125, "learning_rate": 3.5220588235294125e-05, "loss": 0.0579, "step": 503 }, { "epoch": 3.452054794520548, "grad_norm": 8268.9990234375, "learning_rate": 3.518382352941177e-05, "loss": 0.072, "step": 504 }, { "epoch": 3.458904109589041, "grad_norm": 7838.9912109375, "learning_rate": 3.514705882352941e-05, "loss": 0.0534, "step": 505 }, { "epoch": 3.4657534246575343, "grad_norm": 7353.318359375, "learning_rate": 3.511029411764706e-05, "loss": 0.0457, "step": 506 }, { "epoch": 3.4726027397260273, "grad_norm": 7510.8583984375, "learning_rate": 3.5073529411764706e-05, "loss": 0.0484, "step": 507 }, { "epoch": 3.4794520547945207, "grad_norm": 7922.5576171875, "learning_rate": 3.503676470588235e-05, "loss": 0.0597, "step": 508 }, { "epoch": 3.4863013698630136, "grad_norm": 11668.9423828125, "learning_rate": 3.5e-05, "loss": 0.0568, "step": 509 }, { "epoch": 3.493150684931507, "grad_norm": 8005.99267578125, "learning_rate": 3.496323529411765e-05, "loss": 0.0557, "step": 510 }, { "epoch": 3.5, "grad_norm": 6909.181640625, "learning_rate": 3.4926470588235294e-05, "loss": 0.0485, "step": 511 }, { "epoch": 3.506849315068493, "grad_norm": 7131.68798828125, "learning_rate": 3.488970588235294e-05, "loss": 0.0558, "step": 512 }, { "epoch": 3.5136986301369864, "grad_norm": 9390.01953125, "learning_rate": 3.4852941176470585e-05, "loss": 0.0431, "step": 513 }, { "epoch": 3.5205479452054793, "grad_norm": 8094.267578125, "learning_rate": 3.481617647058824e-05, "loss": 0.0607, "step": 514 }, { "epoch": 3.5273972602739727, "grad_norm": 8131.076171875, "learning_rate": 3.477941176470588e-05, "loss": 0.0661, "step": 515 }, { "epoch": 3.5342465753424657, "grad_norm": 8918.828125, "learning_rate": 3.474264705882353e-05, "loss": 0.0743, "step": 516 }, { "epoch": 3.541095890410959, "grad_norm": 12419.119140625, "learning_rate": 3.470588235294118e-05, "loss": 0.0556, "step": 517 }, { "epoch": 3.547945205479452, "grad_norm": 8592.2568359375, "learning_rate": 3.4669117647058826e-05, "loss": 0.065, "step": 518 }, { "epoch": 3.5547945205479454, "grad_norm": 10854.0458984375, "learning_rate": 3.463235294117647e-05, "loss": 0.0695, "step": 519 }, { "epoch": 3.5616438356164384, "grad_norm": 8249.2958984375, "learning_rate": 3.4595588235294116e-05, "loss": 0.0529, "step": 520 }, { "epoch": 3.5684931506849313, "grad_norm": 6600.89990234375, "learning_rate": 3.455882352941177e-05, "loss": 0.0428, "step": 521 }, { "epoch": 3.5753424657534247, "grad_norm": 8044.10009765625, "learning_rate": 3.4522058823529414e-05, "loss": 0.0488, "step": 522 }, { "epoch": 3.5821917808219177, "grad_norm": 8204.88671875, "learning_rate": 3.448529411764706e-05, "loss": 0.0567, "step": 523 }, { "epoch": 3.589041095890411, "grad_norm": 8697.1982421875, "learning_rate": 3.4448529411764705e-05, "loss": 0.0378, "step": 524 }, { "epoch": 3.595890410958904, "grad_norm": 7744.65576171875, "learning_rate": 3.441176470588236e-05, "loss": 0.0525, "step": 525 }, { "epoch": 3.602739726027397, "grad_norm": 8071.533203125, "learning_rate": 3.4375e-05, "loss": 0.0496, "step": 526 }, { "epoch": 3.6095890410958904, "grad_norm": 9372.33203125, "learning_rate": 3.433823529411765e-05, "loss": 0.0665, "step": 527 }, { "epoch": 3.616438356164384, "grad_norm": 7980.86865234375, "learning_rate": 3.430147058823529e-05, "loss": 0.0507, "step": 528 }, { "epoch": 3.6232876712328768, "grad_norm": 8569.208984375, "learning_rate": 3.4264705882352945e-05, "loss": 0.0463, "step": 529 }, { "epoch": 3.6301369863013697, "grad_norm": 7336.71044921875, "learning_rate": 3.422794117647059e-05, "loss": 0.0525, "step": 530 }, { "epoch": 3.636986301369863, "grad_norm": 9621.5400390625, "learning_rate": 3.4191176470588236e-05, "loss": 0.0487, "step": 531 }, { "epoch": 3.643835616438356, "grad_norm": 10704.29296875, "learning_rate": 3.415441176470589e-05, "loss": 0.0548, "step": 532 }, { "epoch": 3.6506849315068495, "grad_norm": 12987.4765625, "learning_rate": 3.411764705882353e-05, "loss": 0.0652, "step": 533 }, { "epoch": 3.6575342465753424, "grad_norm": 8471.498046875, "learning_rate": 3.408088235294118e-05, "loss": 0.0496, "step": 534 }, { "epoch": 3.6643835616438354, "grad_norm": 7624.5771484375, "learning_rate": 3.4044117647058824e-05, "loss": 0.0657, "step": 535 }, { "epoch": 3.671232876712329, "grad_norm": 12547.953125, "learning_rate": 3.4007352941176476e-05, "loss": 0.0664, "step": 536 }, { "epoch": 3.678082191780822, "grad_norm": 10399.5107421875, "learning_rate": 3.397058823529412e-05, "loss": 0.0665, "step": 537 }, { "epoch": 3.684931506849315, "grad_norm": 11536.00390625, "learning_rate": 3.393382352941177e-05, "loss": 0.0635, "step": 538 }, { "epoch": 3.691780821917808, "grad_norm": 8126.89501953125, "learning_rate": 3.389705882352941e-05, "loss": 0.0649, "step": 539 }, { "epoch": 3.6986301369863015, "grad_norm": 7991.2568359375, "learning_rate": 3.3860294117647064e-05, "loss": 0.0533, "step": 540 }, { "epoch": 3.7054794520547945, "grad_norm": 10519.0234375, "learning_rate": 3.382352941176471e-05, "loss": 0.0535, "step": 541 }, { "epoch": 3.712328767123288, "grad_norm": 9458.84765625, "learning_rate": 3.3786764705882355e-05, "loss": 0.0624, "step": 542 }, { "epoch": 3.719178082191781, "grad_norm": 6431.52685546875, "learning_rate": 3.375000000000001e-05, "loss": 0.0471, "step": 543 }, { "epoch": 3.7260273972602738, "grad_norm": 8409.9208984375, "learning_rate": 3.371323529411765e-05, "loss": 0.0432, "step": 544 }, { "epoch": 3.732876712328767, "grad_norm": 8495.9189453125, "learning_rate": 3.36764705882353e-05, "loss": 0.0599, "step": 545 }, { "epoch": 3.73972602739726, "grad_norm": 6869.9716796875, "learning_rate": 3.363970588235294e-05, "loss": 0.0454, "step": 546 }, { "epoch": 3.7465753424657535, "grad_norm": 6748.28271484375, "learning_rate": 3.3602941176470595e-05, "loss": 0.0495, "step": 547 }, { "epoch": 3.7534246575342465, "grad_norm": 8204.3798828125, "learning_rate": 3.3566176470588234e-05, "loss": 0.0564, "step": 548 }, { "epoch": 3.76027397260274, "grad_norm": 9735.1005859375, "learning_rate": 3.352941176470588e-05, "loss": 0.057, "step": 549 }, { "epoch": 3.767123287671233, "grad_norm": 8163.7431640625, "learning_rate": 3.349264705882353e-05, "loss": 0.053, "step": 550 }, { "epoch": 3.7739726027397262, "grad_norm": 7988.24365234375, "learning_rate": 3.345588235294118e-05, "loss": 0.0506, "step": 551 }, { "epoch": 3.780821917808219, "grad_norm": 7283.5400390625, "learning_rate": 3.341911764705882e-05, "loss": 0.0555, "step": 552 }, { "epoch": 3.787671232876712, "grad_norm": 16856.40625, "learning_rate": 3.338235294117647e-05, "loss": 0.0822, "step": 553 }, { "epoch": 3.7945205479452055, "grad_norm": 7805.17041015625, "learning_rate": 3.334558823529412e-05, "loss": 0.05, "step": 554 }, { "epoch": 3.8013698630136985, "grad_norm": 7236.83447265625, "learning_rate": 3.3308823529411765e-05, "loss": 0.052, "step": 555 }, { "epoch": 3.808219178082192, "grad_norm": 10421.140625, "learning_rate": 3.327205882352941e-05, "loss": 0.0433, "step": 556 }, { "epoch": 3.815068493150685, "grad_norm": 6914.5869140625, "learning_rate": 3.3235294117647056e-05, "loss": 0.0541, "step": 557 }, { "epoch": 3.821917808219178, "grad_norm": 7851.66552734375, "learning_rate": 3.319852941176471e-05, "loss": 0.0496, "step": 558 }, { "epoch": 3.828767123287671, "grad_norm": 6859.70947265625, "learning_rate": 3.3161764705882353e-05, "loss": 0.0576, "step": 559 }, { "epoch": 3.8356164383561646, "grad_norm": 7605.7080078125, "learning_rate": 3.3125e-05, "loss": 0.063, "step": 560 }, { "epoch": 3.8424657534246576, "grad_norm": 8587.0869140625, "learning_rate": 3.308823529411765e-05, "loss": 0.0572, "step": 561 }, { "epoch": 3.8493150684931505, "grad_norm": 8056.33154296875, "learning_rate": 3.3051470588235296e-05, "loss": 0.0565, "step": 562 }, { "epoch": 3.856164383561644, "grad_norm": 8331.8603515625, "learning_rate": 3.301470588235294e-05, "loss": 0.0543, "step": 563 }, { "epoch": 3.863013698630137, "grad_norm": 7523.591796875, "learning_rate": 3.297794117647059e-05, "loss": 0.0485, "step": 564 }, { "epoch": 3.8698630136986303, "grad_norm": 8504.3583984375, "learning_rate": 3.294117647058824e-05, "loss": 0.0474, "step": 565 }, { "epoch": 3.8767123287671232, "grad_norm": 6138.6591796875, "learning_rate": 3.2904411764705885e-05, "loss": 0.0491, "step": 566 }, { "epoch": 3.883561643835616, "grad_norm": 6717.93017578125, "learning_rate": 3.286764705882353e-05, "loss": 0.0536, "step": 567 }, { "epoch": 3.8904109589041096, "grad_norm": 9413.1044921875, "learning_rate": 3.2830882352941175e-05, "loss": 0.0436, "step": 568 }, { "epoch": 3.897260273972603, "grad_norm": 7110.3759765625, "learning_rate": 3.279411764705883e-05, "loss": 0.0541, "step": 569 }, { "epoch": 3.904109589041096, "grad_norm": 7726.138671875, "learning_rate": 3.275735294117647e-05, "loss": 0.0586, "step": 570 }, { "epoch": 3.910958904109589, "grad_norm": 7693.01123046875, "learning_rate": 3.272058823529412e-05, "loss": 0.0444, "step": 571 }, { "epoch": 3.9178082191780823, "grad_norm": 8720.765625, "learning_rate": 3.2683823529411764e-05, "loss": 0.052, "step": 572 }, { "epoch": 3.9246575342465753, "grad_norm": 8742.3359375, "learning_rate": 3.2647058823529416e-05, "loss": 0.0457, "step": 573 }, { "epoch": 3.9315068493150687, "grad_norm": 7097.43603515625, "learning_rate": 3.261029411764706e-05, "loss": 0.0428, "step": 574 }, { "epoch": 3.9383561643835616, "grad_norm": 11577.9287109375, "learning_rate": 3.2573529411764706e-05, "loss": 0.0496, "step": 575 }, { "epoch": 3.9452054794520546, "grad_norm": 7167.64013671875, "learning_rate": 3.253676470588236e-05, "loss": 0.0434, "step": 576 }, { "epoch": 3.952054794520548, "grad_norm": 9340.6591796875, "learning_rate": 3.2500000000000004e-05, "loss": 0.0599, "step": 577 }, { "epoch": 3.958904109589041, "grad_norm": 11842.4052734375, "learning_rate": 3.246323529411765e-05, "loss": 0.0562, "step": 578 }, { "epoch": 3.9657534246575343, "grad_norm": 9098.181640625, "learning_rate": 3.2426470588235295e-05, "loss": 0.0352, "step": 579 }, { "epoch": 3.9726027397260273, "grad_norm": 7359.5419921875, "learning_rate": 3.238970588235295e-05, "loss": 0.0473, "step": 580 }, { "epoch": 3.9794520547945207, "grad_norm": 5964.90869140625, "learning_rate": 3.235294117647059e-05, "loss": 0.0434, "step": 581 }, { "epoch": 3.9863013698630136, "grad_norm": 9331.779296875, "learning_rate": 3.231617647058824e-05, "loss": 0.0472, "step": 582 }, { "epoch": 3.993150684931507, "grad_norm": 7071.9130859375, "learning_rate": 3.227941176470588e-05, "loss": 0.0517, "step": 583 }, { "epoch": 4.0, "grad_norm": 8607.703125, "learning_rate": 3.2242647058823535e-05, "loss": 0.048, "step": 584 }, { "epoch": 4.0, "eval_f1_macro": 0.409074554818663, "eval_f1_micro": 0.714792899408284, "eval_loss": 0.05271512642502785, "eval_precision": 0.8579545454545454, "eval_recall": 0.6125760649087221, "eval_runtime": 1.0955, "eval_samples_per_second": 355.081, "eval_steps_per_second": 15.518, "step": 584 }, { "epoch": 4.006849315068493, "grad_norm": 6023.16943359375, "learning_rate": 3.220588235294118e-05, "loss": 0.0388, "step": 585 }, { "epoch": 4.013698630136986, "grad_norm": 9791.9189453125, "learning_rate": 3.2169117647058826e-05, "loss": 0.0463, "step": 586 }, { "epoch": 4.02054794520548, "grad_norm": 6219.3828125, "learning_rate": 3.213235294117647e-05, "loss": 0.0449, "step": 587 }, { "epoch": 4.027397260273973, "grad_norm": 6912.25048828125, "learning_rate": 3.209558823529412e-05, "loss": 0.0442, "step": 588 }, { "epoch": 4.034246575342466, "grad_norm": 10272.71484375, "learning_rate": 3.205882352941177e-05, "loss": 0.047, "step": 589 }, { "epoch": 4.041095890410959, "grad_norm": 6616.33447265625, "learning_rate": 3.202205882352941e-05, "loss": 0.0489, "step": 590 }, { "epoch": 4.0479452054794525, "grad_norm": 7063.2080078125, "learning_rate": 3.198529411764706e-05, "loss": 0.0445, "step": 591 }, { "epoch": 4.054794520547945, "grad_norm": 6276.9248046875, "learning_rate": 3.1948529411764705e-05, "loss": 0.0321, "step": 592 }, { "epoch": 4.061643835616438, "grad_norm": 10006.4814453125, "learning_rate": 3.191176470588235e-05, "loss": 0.0559, "step": 593 }, { "epoch": 4.068493150684931, "grad_norm": 8520.703125, "learning_rate": 3.1875e-05, "loss": 0.0445, "step": 594 }, { "epoch": 4.075342465753424, "grad_norm": 13261.8173828125, "learning_rate": 3.183823529411765e-05, "loss": 0.0422, "step": 595 }, { "epoch": 4.082191780821918, "grad_norm": 7789.486328125, "learning_rate": 3.180147058823529e-05, "loss": 0.0489, "step": 596 }, { "epoch": 4.089041095890411, "grad_norm": 7030.4755859375, "learning_rate": 3.176470588235294e-05, "loss": 0.0457, "step": 597 }, { "epoch": 4.095890410958904, "grad_norm": 6411.83056640625, "learning_rate": 3.172794117647059e-05, "loss": 0.0419, "step": 598 }, { "epoch": 4.102739726027397, "grad_norm": 8647.1171875, "learning_rate": 3.1691176470588236e-05, "loss": 0.0538, "step": 599 }, { "epoch": 4.109589041095891, "grad_norm": 7891.404296875, "learning_rate": 3.165441176470588e-05, "loss": 0.0424, "step": 600 }, { "epoch": 4.116438356164384, "grad_norm": 8097.86962890625, "learning_rate": 3.161764705882353e-05, "loss": 0.0388, "step": 601 }, { "epoch": 4.123287671232877, "grad_norm": 8862.1572265625, "learning_rate": 3.158088235294118e-05, "loss": 0.052, "step": 602 }, { "epoch": 4.13013698630137, "grad_norm": 6725.22900390625, "learning_rate": 3.1544117647058824e-05, "loss": 0.0547, "step": 603 }, { "epoch": 4.136986301369863, "grad_norm": 12229.27734375, "learning_rate": 3.150735294117647e-05, "loss": 0.0687, "step": 604 }, { "epoch": 4.1438356164383565, "grad_norm": 6911.9580078125, "learning_rate": 3.147058823529412e-05, "loss": 0.0486, "step": 605 }, { "epoch": 4.1506849315068495, "grad_norm": 6435.03759765625, "learning_rate": 3.143382352941177e-05, "loss": 0.0398, "step": 606 }, { "epoch": 4.157534246575342, "grad_norm": 8734.4951171875, "learning_rate": 3.139705882352941e-05, "loss": 0.046, "step": 607 }, { "epoch": 4.164383561643835, "grad_norm": 7252.90771484375, "learning_rate": 3.136029411764706e-05, "loss": 0.0573, "step": 608 }, { "epoch": 4.171232876712328, "grad_norm": 7077.82177734375, "learning_rate": 3.132352941176471e-05, "loss": 0.037, "step": 609 }, { "epoch": 4.178082191780822, "grad_norm": 8847.84375, "learning_rate": 3.1286764705882355e-05, "loss": 0.0559, "step": 610 }, { "epoch": 4.184931506849315, "grad_norm": 6303.64501953125, "learning_rate": 3.125e-05, "loss": 0.0416, "step": 611 }, { "epoch": 4.191780821917808, "grad_norm": 8064.43408203125, "learning_rate": 3.1213235294117646e-05, "loss": 0.0485, "step": 612 }, { "epoch": 4.198630136986301, "grad_norm": 7774.49169921875, "learning_rate": 3.11764705882353e-05, "loss": 0.0391, "step": 613 }, { "epoch": 4.205479452054795, "grad_norm": 10674.798828125, "learning_rate": 3.1139705882352944e-05, "loss": 0.063, "step": 614 }, { "epoch": 4.212328767123288, "grad_norm": 6215.93896484375, "learning_rate": 3.110294117647059e-05, "loss": 0.0427, "step": 615 }, { "epoch": 4.219178082191781, "grad_norm": 10550.07421875, "learning_rate": 3.1066176470588234e-05, "loss": 0.051, "step": 616 }, { "epoch": 4.226027397260274, "grad_norm": 5613.17529296875, "learning_rate": 3.1029411764705886e-05, "loss": 0.0299, "step": 617 }, { "epoch": 4.232876712328767, "grad_norm": 6822.3525390625, "learning_rate": 3.099264705882353e-05, "loss": 0.0416, "step": 618 }, { "epoch": 4.239726027397261, "grad_norm": 6097.13427734375, "learning_rate": 3.095588235294118e-05, "loss": 0.0443, "step": 619 }, { "epoch": 4.2465753424657535, "grad_norm": 7562.06494140625, "learning_rate": 3.091911764705883e-05, "loss": 0.0496, "step": 620 }, { "epoch": 4.2534246575342465, "grad_norm": 5349.8310546875, "learning_rate": 3.0882352941176475e-05, "loss": 0.0328, "step": 621 }, { "epoch": 4.260273972602739, "grad_norm": 10760.318359375, "learning_rate": 3.084558823529412e-05, "loss": 0.0511, "step": 622 }, { "epoch": 4.267123287671233, "grad_norm": 24031.408203125, "learning_rate": 3.0808823529411765e-05, "loss": 0.0331, "step": 623 }, { "epoch": 4.273972602739726, "grad_norm": 12319.9404296875, "learning_rate": 3.077205882352942e-05, "loss": 0.0548, "step": 624 }, { "epoch": 4.280821917808219, "grad_norm": 8221.5869140625, "learning_rate": 3.073529411764706e-05, "loss": 0.0479, "step": 625 }, { "epoch": 4.287671232876712, "grad_norm": 11113.0185546875, "learning_rate": 3.069852941176471e-05, "loss": 0.0474, "step": 626 }, { "epoch": 4.294520547945205, "grad_norm": 6046.14306640625, "learning_rate": 3.0661764705882354e-05, "loss": 0.0409, "step": 627 }, { "epoch": 4.301369863013699, "grad_norm": 6966.517578125, "learning_rate": 3.0625000000000006e-05, "loss": 0.041, "step": 628 }, { "epoch": 4.308219178082192, "grad_norm": 26900.36328125, "learning_rate": 3.058823529411765e-05, "loss": 0.0624, "step": 629 }, { "epoch": 4.315068493150685, "grad_norm": 8974.69140625, "learning_rate": 3.0551470588235297e-05, "loss": 0.0387, "step": 630 }, { "epoch": 4.321917808219178, "grad_norm": 10555.2265625, "learning_rate": 3.0514705882352945e-05, "loss": 0.0557, "step": 631 }, { "epoch": 4.328767123287671, "grad_norm": 10321.4033203125, "learning_rate": 3.0477941176470594e-05, "loss": 0.0526, "step": 632 }, { "epoch": 4.335616438356165, "grad_norm": 10063.4736328125, "learning_rate": 3.0441176470588233e-05, "loss": 0.0379, "step": 633 }, { "epoch": 4.342465753424658, "grad_norm": 7246.46142578125, "learning_rate": 3.040441176470588e-05, "loss": 0.0445, "step": 634 }, { "epoch": 4.3493150684931505, "grad_norm": 7840.70849609375, "learning_rate": 3.036764705882353e-05, "loss": 0.0499, "step": 635 }, { "epoch": 4.3561643835616435, "grad_norm": 7093.341796875, "learning_rate": 3.0330882352941176e-05, "loss": 0.0517, "step": 636 }, { "epoch": 4.363013698630137, "grad_norm": 10047.1357421875, "learning_rate": 3.0294117647058824e-05, "loss": 0.0506, "step": 637 }, { "epoch": 4.36986301369863, "grad_norm": 6373.73291015625, "learning_rate": 3.025735294117647e-05, "loss": 0.0385, "step": 638 }, { "epoch": 4.376712328767123, "grad_norm": 7343.32861328125, "learning_rate": 3.022058823529412e-05, "loss": 0.0424, "step": 639 }, { "epoch": 4.383561643835616, "grad_norm": 7270.78857421875, "learning_rate": 3.0183823529411764e-05, "loss": 0.0389, "step": 640 }, { "epoch": 4.390410958904109, "grad_norm": 10728.720703125, "learning_rate": 3.0147058823529413e-05, "loss": 0.0475, "step": 641 }, { "epoch": 4.397260273972603, "grad_norm": 8008.35693359375, "learning_rate": 3.0110294117647058e-05, "loss": 0.0518, "step": 642 }, { "epoch": 4.404109589041096, "grad_norm": 9293.9541015625, "learning_rate": 3.0073529411764707e-05, "loss": 0.0516, "step": 643 }, { "epoch": 4.410958904109589, "grad_norm": 8992.046875, "learning_rate": 3.0036764705882352e-05, "loss": 0.0394, "step": 644 }, { "epoch": 4.417808219178082, "grad_norm": 7849.54931640625, "learning_rate": 3e-05, "loss": 0.0376, "step": 645 }, { "epoch": 4.424657534246576, "grad_norm": 7358.3515625, "learning_rate": 2.9963235294117646e-05, "loss": 0.0488, "step": 646 }, { "epoch": 4.431506849315069, "grad_norm": 7454.50146484375, "learning_rate": 2.9926470588235295e-05, "loss": 0.0504, "step": 647 }, { "epoch": 4.438356164383562, "grad_norm": 7360.47802734375, "learning_rate": 2.988970588235294e-05, "loss": 0.0429, "step": 648 }, { "epoch": 4.445205479452055, "grad_norm": 8806.583984375, "learning_rate": 2.985294117647059e-05, "loss": 0.0331, "step": 649 }, { "epoch": 4.4520547945205475, "grad_norm": 7227.88525390625, "learning_rate": 2.9816176470588238e-05, "loss": 0.0505, "step": 650 }, { "epoch": 4.458904109589041, "grad_norm": 7388.896484375, "learning_rate": 2.9779411764705883e-05, "loss": 0.0419, "step": 651 }, { "epoch": 4.465753424657534, "grad_norm": 8294.4248046875, "learning_rate": 2.9742647058823532e-05, "loss": 0.0463, "step": 652 }, { "epoch": 4.472602739726027, "grad_norm": 6537.556640625, "learning_rate": 2.9705882352941177e-05, "loss": 0.0345, "step": 653 }, { "epoch": 4.47945205479452, "grad_norm": 8360.150390625, "learning_rate": 2.9669117647058826e-05, "loss": 0.0433, "step": 654 }, { "epoch": 4.486301369863014, "grad_norm": 5255.33203125, "learning_rate": 2.963235294117647e-05, "loss": 0.0389, "step": 655 }, { "epoch": 4.493150684931507, "grad_norm": 8179.73046875, "learning_rate": 2.959558823529412e-05, "loss": 0.0434, "step": 656 }, { "epoch": 4.5, "grad_norm": 7583.7705078125, "learning_rate": 2.9558823529411766e-05, "loss": 0.0426, "step": 657 }, { "epoch": 4.506849315068493, "grad_norm": 9395.041015625, "learning_rate": 2.9522058823529414e-05, "loss": 0.0454, "step": 658 }, { "epoch": 4.513698630136986, "grad_norm": 6545.5146484375, "learning_rate": 2.948529411764706e-05, "loss": 0.0392, "step": 659 }, { "epoch": 4.52054794520548, "grad_norm": 7847.33251953125, "learning_rate": 2.944852941176471e-05, "loss": 0.0403, "step": 660 }, { "epoch": 4.527397260273973, "grad_norm": 8052.05810546875, "learning_rate": 2.9411764705882354e-05, "loss": 0.0422, "step": 661 }, { "epoch": 4.534246575342466, "grad_norm": 10760.1669921875, "learning_rate": 2.9375000000000003e-05, "loss": 0.0371, "step": 662 }, { "epoch": 4.541095890410959, "grad_norm": 5301.4677734375, "learning_rate": 2.933823529411765e-05, "loss": 0.0339, "step": 663 }, { "epoch": 4.5479452054794525, "grad_norm": 5713.623046875, "learning_rate": 2.9301470588235297e-05, "loss": 0.0328, "step": 664 }, { "epoch": 4.554794520547945, "grad_norm": 5200.01513671875, "learning_rate": 2.9264705882352945e-05, "loss": 0.0332, "step": 665 }, { "epoch": 4.561643835616438, "grad_norm": 7625.19677734375, "learning_rate": 2.922794117647059e-05, "loss": 0.0457, "step": 666 }, { "epoch": 4.568493150684931, "grad_norm": 8776.0732421875, "learning_rate": 2.919117647058824e-05, "loss": 0.0513, "step": 667 }, { "epoch": 4.575342465753424, "grad_norm": 7380.54052734375, "learning_rate": 2.9154411764705885e-05, "loss": 0.0492, "step": 668 }, { "epoch": 4.582191780821918, "grad_norm": 8823.55078125, "learning_rate": 2.9117647058823534e-05, "loss": 0.043, "step": 669 }, { "epoch": 4.589041095890411, "grad_norm": 10876.5185546875, "learning_rate": 2.908088235294118e-05, "loss": 0.0552, "step": 670 }, { "epoch": 4.595890410958904, "grad_norm": 8131.185546875, "learning_rate": 2.9044117647058828e-05, "loss": 0.0396, "step": 671 }, { "epoch": 4.602739726027397, "grad_norm": 8240.1259765625, "learning_rate": 2.9007352941176473e-05, "loss": 0.0484, "step": 672 }, { "epoch": 4.609589041095891, "grad_norm": 8864.208984375, "learning_rate": 2.8970588235294122e-05, "loss": 0.0396, "step": 673 }, { "epoch": 4.616438356164384, "grad_norm": 6949.31201171875, "learning_rate": 2.8933823529411767e-05, "loss": 0.0305, "step": 674 }, { "epoch": 4.623287671232877, "grad_norm": 6499.7822265625, "learning_rate": 2.889705882352941e-05, "loss": 0.0323, "step": 675 }, { "epoch": 4.63013698630137, "grad_norm": 6921.431640625, "learning_rate": 2.8860294117647058e-05, "loss": 0.0411, "step": 676 }, { "epoch": 4.636986301369863, "grad_norm": 9103.341796875, "learning_rate": 2.8823529411764703e-05, "loss": 0.0331, "step": 677 }, { "epoch": 4.6438356164383565, "grad_norm": 7808.62939453125, "learning_rate": 2.8786764705882352e-05, "loss": 0.039, "step": 678 }, { "epoch": 4.6506849315068495, "grad_norm": 6417.98974609375, "learning_rate": 2.8749999999999997e-05, "loss": 0.0314, "step": 679 }, { "epoch": 4.657534246575342, "grad_norm": 5343.80615234375, "learning_rate": 2.8713235294117646e-05, "loss": 0.0358, "step": 680 }, { "epoch": 4.664383561643835, "grad_norm": 7419.75439453125, "learning_rate": 2.8676470588235295e-05, "loss": 0.04, "step": 681 }, { "epoch": 4.671232876712329, "grad_norm": 7083.841796875, "learning_rate": 2.863970588235294e-05, "loss": 0.0447, "step": 682 }, { "epoch": 4.678082191780822, "grad_norm": 8405.4580078125, "learning_rate": 2.860294117647059e-05, "loss": 0.0514, "step": 683 }, { "epoch": 4.684931506849315, "grad_norm": 6881.55224609375, "learning_rate": 2.8566176470588234e-05, "loss": 0.0422, "step": 684 }, { "epoch": 4.691780821917808, "grad_norm": 8598.4033203125, "learning_rate": 2.8529411764705883e-05, "loss": 0.0617, "step": 685 }, { "epoch": 4.698630136986301, "grad_norm": 6465.2001953125, "learning_rate": 2.849264705882353e-05, "loss": 0.0321, "step": 686 }, { "epoch": 4.705479452054795, "grad_norm": 10376.0107421875, "learning_rate": 2.8455882352941177e-05, "loss": 0.0466, "step": 687 }, { "epoch": 4.712328767123288, "grad_norm": 6743.7275390625, "learning_rate": 2.8419117647058823e-05, "loss": 0.0456, "step": 688 }, { "epoch": 4.719178082191781, "grad_norm": 7004.126953125, "learning_rate": 2.838235294117647e-05, "loss": 0.0508, "step": 689 }, { "epoch": 4.726027397260274, "grad_norm": 8116.96240234375, "learning_rate": 2.8345588235294117e-05, "loss": 0.0521, "step": 690 }, { "epoch": 4.732876712328768, "grad_norm": 7490.94775390625, "learning_rate": 2.8308823529411766e-05, "loss": 0.0352, "step": 691 }, { "epoch": 4.739726027397261, "grad_norm": 7208.40576171875, "learning_rate": 2.827205882352941e-05, "loss": 0.0394, "step": 692 }, { "epoch": 4.7465753424657535, "grad_norm": 5930.4287109375, "learning_rate": 2.823529411764706e-05, "loss": 0.0303, "step": 693 }, { "epoch": 4.7534246575342465, "grad_norm": 5899.4736328125, "learning_rate": 2.819852941176471e-05, "loss": 0.0372, "step": 694 }, { "epoch": 4.760273972602739, "grad_norm": 7512.94580078125, "learning_rate": 2.8161764705882354e-05, "loss": 0.0482, "step": 695 }, { "epoch": 4.767123287671232, "grad_norm": 6376.46044921875, "learning_rate": 2.8125000000000003e-05, "loss": 0.0352, "step": 696 }, { "epoch": 4.773972602739726, "grad_norm": 5717.2841796875, "learning_rate": 2.8088235294117648e-05, "loss": 0.0358, "step": 697 }, { "epoch": 4.780821917808219, "grad_norm": 7261.2529296875, "learning_rate": 2.8051470588235297e-05, "loss": 0.0363, "step": 698 }, { "epoch": 4.787671232876712, "grad_norm": 6239.1025390625, "learning_rate": 2.8014705882352942e-05, "loss": 0.04, "step": 699 }, { "epoch": 4.794520547945205, "grad_norm": 5670.60546875, "learning_rate": 2.797794117647059e-05, "loss": 0.0347, "step": 700 }, { "epoch": 4.801369863013699, "grad_norm": 8845.5009765625, "learning_rate": 2.7941176470588236e-05, "loss": 0.0364, "step": 701 }, { "epoch": 4.808219178082192, "grad_norm": 6336.40234375, "learning_rate": 2.7904411764705885e-05, "loss": 0.0412, "step": 702 }, { "epoch": 4.815068493150685, "grad_norm": 6392.5400390625, "learning_rate": 2.786764705882353e-05, "loss": 0.0327, "step": 703 }, { "epoch": 4.821917808219178, "grad_norm": 7235.25, "learning_rate": 2.783088235294118e-05, "loss": 0.0456, "step": 704 }, { "epoch": 4.828767123287671, "grad_norm": 6111.4873046875, "learning_rate": 2.7794117647058824e-05, "loss": 0.0347, "step": 705 }, { "epoch": 4.835616438356165, "grad_norm": 8652.3125, "learning_rate": 2.7757352941176473e-05, "loss": 0.0395, "step": 706 }, { "epoch": 4.842465753424658, "grad_norm": 13647.4990234375, "learning_rate": 2.7720588235294122e-05, "loss": 0.0398, "step": 707 }, { "epoch": 4.8493150684931505, "grad_norm": 4817.86962890625, "learning_rate": 2.7683823529411767e-05, "loss": 0.0283, "step": 708 }, { "epoch": 4.8561643835616435, "grad_norm": 8644.015625, "learning_rate": 2.7647058823529416e-05, "loss": 0.0367, "step": 709 }, { "epoch": 4.863013698630137, "grad_norm": 10173.4111328125, "learning_rate": 2.761029411764706e-05, "loss": 0.0437, "step": 710 }, { "epoch": 4.86986301369863, "grad_norm": 6492.10107421875, "learning_rate": 2.757352941176471e-05, "loss": 0.0352, "step": 711 }, { "epoch": 4.876712328767123, "grad_norm": 7805.3623046875, "learning_rate": 2.7536764705882356e-05, "loss": 0.0427, "step": 712 }, { "epoch": 4.883561643835616, "grad_norm": 9311.1162109375, "learning_rate": 2.7500000000000004e-05, "loss": 0.0389, "step": 713 }, { "epoch": 4.890410958904109, "grad_norm": 7715.2060546875, "learning_rate": 2.746323529411765e-05, "loss": 0.0523, "step": 714 }, { "epoch": 4.897260273972603, "grad_norm": 7084.265625, "learning_rate": 2.74264705882353e-05, "loss": 0.0474, "step": 715 }, { "epoch": 4.904109589041096, "grad_norm": 7221.015625, "learning_rate": 2.7389705882352944e-05, "loss": 0.0457, "step": 716 }, { "epoch": 4.910958904109589, "grad_norm": 8889.0439453125, "learning_rate": 2.7352941176470593e-05, "loss": 0.0366, "step": 717 }, { "epoch": 4.917808219178082, "grad_norm": 7409.9287109375, "learning_rate": 2.7316176470588235e-05, "loss": 0.0425, "step": 718 }, { "epoch": 4.924657534246576, "grad_norm": 9617.689453125, "learning_rate": 2.727941176470588e-05, "loss": 0.058, "step": 719 }, { "epoch": 4.931506849315069, "grad_norm": 9736.0419921875, "learning_rate": 2.724264705882353e-05, "loss": 0.0452, "step": 720 }, { "epoch": 4.938356164383562, "grad_norm": 7348.82666015625, "learning_rate": 2.7205882352941174e-05, "loss": 0.0433, "step": 721 }, { "epoch": 4.945205479452055, "grad_norm": 7927.72314453125, "learning_rate": 2.7169117647058823e-05, "loss": 0.0438, "step": 722 }, { "epoch": 4.9520547945205475, "grad_norm": 8275.806640625, "learning_rate": 2.7132352941176468e-05, "loss": 0.0467, "step": 723 }, { "epoch": 4.958904109589041, "grad_norm": 6585.8818359375, "learning_rate": 2.7095588235294117e-05, "loss": 0.0366, "step": 724 }, { "epoch": 4.965753424657534, "grad_norm": 8603.5146484375, "learning_rate": 2.7058823529411766e-05, "loss": 0.036, "step": 725 }, { "epoch": 4.972602739726027, "grad_norm": 4754.98095703125, "learning_rate": 2.702205882352941e-05, "loss": 0.0258, "step": 726 }, { "epoch": 4.97945205479452, "grad_norm": 7423.80322265625, "learning_rate": 2.698529411764706e-05, "loss": 0.0315, "step": 727 }, { "epoch": 4.986301369863014, "grad_norm": 7441.22900390625, "learning_rate": 2.6948529411764705e-05, "loss": 0.0289, "step": 728 }, { "epoch": 4.993150684931507, "grad_norm": 8691.2607421875, "learning_rate": 2.6911764705882354e-05, "loss": 0.0439, "step": 729 }, { "epoch": 5.0, "grad_norm": 6230.837890625, "learning_rate": 2.6875e-05, "loss": 0.0395, "step": 730 }, { "epoch": 5.0, "eval_f1_macro": 0.5568870021468288, "eval_f1_micro": 0.7932584269662921, "eval_loss": 0.04394844174385071, "eval_precision": 0.889168765743073, "eval_recall": 0.716024340770791, "eval_runtime": 1.0882, "eval_samples_per_second": 357.473, "eval_steps_per_second": 15.622, "step": 730 }, { "epoch": 5.006849315068493, "grad_norm": 5587.9736328125, "learning_rate": 2.6838235294117648e-05, "loss": 0.0341, "step": 731 }, { "epoch": 5.013698630136986, "grad_norm": 8207.36328125, "learning_rate": 2.6801470588235293e-05, "loss": 0.0465, "step": 732 }, { "epoch": 5.02054794520548, "grad_norm": 4896.98193359375, "learning_rate": 2.6764705882352942e-05, "loss": 0.0285, "step": 733 }, { "epoch": 5.027397260273973, "grad_norm": 6909.7041015625, "learning_rate": 2.6727941176470588e-05, "loss": 0.0416, "step": 734 }, { "epoch": 5.034246575342466, "grad_norm": 6374.8984375, "learning_rate": 2.6691176470588236e-05, "loss": 0.0414, "step": 735 }, { "epoch": 5.041095890410959, "grad_norm": 6004.5341796875, "learning_rate": 2.6654411764705882e-05, "loss": 0.0353, "step": 736 }, { "epoch": 5.0479452054794525, "grad_norm": 5743.2626953125, "learning_rate": 2.661764705882353e-05, "loss": 0.03, "step": 737 }, { "epoch": 5.054794520547945, "grad_norm": 6569.35302734375, "learning_rate": 2.658088235294118e-05, "loss": 0.0469, "step": 738 }, { "epoch": 5.061643835616438, "grad_norm": 5952.38623046875, "learning_rate": 2.6544117647058825e-05, "loss": 0.0316, "step": 739 }, { "epoch": 5.068493150684931, "grad_norm": 7132.69873046875, "learning_rate": 2.6507352941176473e-05, "loss": 0.0423, "step": 740 }, { "epoch": 5.075342465753424, "grad_norm": 7760.1650390625, "learning_rate": 2.647058823529412e-05, "loss": 0.0373, "step": 741 }, { "epoch": 5.082191780821918, "grad_norm": 6396.9541015625, "learning_rate": 2.6433823529411767e-05, "loss": 0.0311, "step": 742 }, { "epoch": 5.089041095890411, "grad_norm": 5701.1474609375, "learning_rate": 2.6397058823529413e-05, "loss": 0.0347, "step": 743 }, { "epoch": 5.095890410958904, "grad_norm": 5275.18359375, "learning_rate": 2.636029411764706e-05, "loss": 0.0307, "step": 744 }, { "epoch": 5.102739726027397, "grad_norm": 7336.06884765625, "learning_rate": 2.6323529411764707e-05, "loss": 0.0336, "step": 745 }, { "epoch": 5.109589041095891, "grad_norm": 8911.572265625, "learning_rate": 2.6286764705882356e-05, "loss": 0.0303, "step": 746 }, { "epoch": 5.116438356164384, "grad_norm": 7833.3876953125, "learning_rate": 2.625e-05, "loss": 0.0304, "step": 747 }, { "epoch": 5.123287671232877, "grad_norm": 6829.01123046875, "learning_rate": 2.621323529411765e-05, "loss": 0.0389, "step": 748 }, { "epoch": 5.13013698630137, "grad_norm": 6869.38427734375, "learning_rate": 2.6176470588235295e-05, "loss": 0.0445, "step": 749 }, { "epoch": 5.136986301369863, "grad_norm": 16788.83203125, "learning_rate": 2.6139705882352944e-05, "loss": 0.0413, "step": 750 }, { "epoch": 5.1438356164383565, "grad_norm": 11118.94140625, "learning_rate": 2.6102941176470593e-05, "loss": 0.049, "step": 751 }, { "epoch": 5.1506849315068495, "grad_norm": 6242.04541015625, "learning_rate": 2.6066176470588238e-05, "loss": 0.046, "step": 752 }, { "epoch": 5.157534246575342, "grad_norm": 5894.15771484375, "learning_rate": 2.6029411764705887e-05, "loss": 0.0359, "step": 753 }, { "epoch": 5.164383561643835, "grad_norm": 8105.4677734375, "learning_rate": 2.5992647058823532e-05, "loss": 0.0357, "step": 754 }, { "epoch": 5.171232876712328, "grad_norm": 4957.89453125, "learning_rate": 2.595588235294118e-05, "loss": 0.0285, "step": 755 }, { "epoch": 5.178082191780822, "grad_norm": 6085.69873046875, "learning_rate": 2.5919117647058826e-05, "loss": 0.0352, "step": 756 }, { "epoch": 5.184931506849315, "grad_norm": 5420.125, "learning_rate": 2.5882352941176475e-05, "loss": 0.0281, "step": 757 }, { "epoch": 5.191780821917808, "grad_norm": 5066.52978515625, "learning_rate": 2.584558823529412e-05, "loss": 0.039, "step": 758 }, { "epoch": 5.198630136986301, "grad_norm": 6617.5947265625, "learning_rate": 2.580882352941177e-05, "loss": 0.0367, "step": 759 }, { "epoch": 5.205479452054795, "grad_norm": 5343.1044921875, "learning_rate": 2.577205882352941e-05, "loss": 0.0288, "step": 760 }, { "epoch": 5.212328767123288, "grad_norm": 6210.65576171875, "learning_rate": 2.5735294117647057e-05, "loss": 0.0262, "step": 761 }, { "epoch": 5.219178082191781, "grad_norm": 10814.025390625, "learning_rate": 2.5698529411764705e-05, "loss": 0.0338, "step": 762 }, { "epoch": 5.226027397260274, "grad_norm": 5051.78955078125, "learning_rate": 2.566176470588235e-05, "loss": 0.0266, "step": 763 }, { "epoch": 5.232876712328767, "grad_norm": 5567.283203125, "learning_rate": 2.5625e-05, "loss": 0.0426, "step": 764 }, { "epoch": 5.239726027397261, "grad_norm": 6252.50927734375, "learning_rate": 2.5588235294117645e-05, "loss": 0.0363, "step": 765 }, { "epoch": 5.2465753424657535, "grad_norm": 9249.8544921875, "learning_rate": 2.5551470588235294e-05, "loss": 0.0369, "step": 766 }, { "epoch": 5.2534246575342465, "grad_norm": 7336.54248046875, "learning_rate": 2.551470588235294e-05, "loss": 0.025, "step": 767 }, { "epoch": 5.260273972602739, "grad_norm": 12244.0888671875, "learning_rate": 2.5477941176470588e-05, "loss": 0.058, "step": 768 }, { "epoch": 5.267123287671233, "grad_norm": 9134.4677734375, "learning_rate": 2.5441176470588236e-05, "loss": 0.047, "step": 769 }, { "epoch": 5.273972602739726, "grad_norm": 6535.4453125, "learning_rate": 2.5404411764705882e-05, "loss": 0.0291, "step": 770 }, { "epoch": 5.280821917808219, "grad_norm": 7080.76220703125, "learning_rate": 2.536764705882353e-05, "loss": 0.0279, "step": 771 }, { "epoch": 5.287671232876712, "grad_norm": 7867.48974609375, "learning_rate": 2.5330882352941176e-05, "loss": 0.0424, "step": 772 }, { "epoch": 5.294520547945205, "grad_norm": 9005.1962890625, "learning_rate": 2.5294117647058825e-05, "loss": 0.0305, "step": 773 }, { "epoch": 5.301369863013699, "grad_norm": 4883.71044921875, "learning_rate": 2.525735294117647e-05, "loss": 0.0259, "step": 774 }, { "epoch": 5.308219178082192, "grad_norm": 8886.2705078125, "learning_rate": 2.522058823529412e-05, "loss": 0.0486, "step": 775 }, { "epoch": 5.315068493150685, "grad_norm": 5267.04345703125, "learning_rate": 2.5183823529411764e-05, "loss": 0.0206, "step": 776 }, { "epoch": 5.321917808219178, "grad_norm": 9086.94921875, "learning_rate": 2.5147058823529413e-05, "loss": 0.0362, "step": 777 }, { "epoch": 5.328767123287671, "grad_norm": 8476.4912109375, "learning_rate": 2.511029411764706e-05, "loss": 0.0485, "step": 778 }, { "epoch": 5.335616438356165, "grad_norm": 7314.5107421875, "learning_rate": 2.5073529411764707e-05, "loss": 0.0288, "step": 779 }, { "epoch": 5.342465753424658, "grad_norm": 6002.7685546875, "learning_rate": 2.5036764705882352e-05, "loss": 0.0286, "step": 780 }, { "epoch": 5.3493150684931505, "grad_norm": 10530.2353515625, "learning_rate": 2.5e-05, "loss": 0.0357, "step": 781 }, { "epoch": 5.3561643835616435, "grad_norm": 7913.8232421875, "learning_rate": 2.496323529411765e-05, "loss": 0.041, "step": 782 }, { "epoch": 5.363013698630137, "grad_norm": 5760.63134765625, "learning_rate": 2.4926470588235295e-05, "loss": 0.0331, "step": 783 }, { "epoch": 5.36986301369863, "grad_norm": 7752.29248046875, "learning_rate": 2.4889705882352944e-05, "loss": 0.0373, "step": 784 }, { "epoch": 5.376712328767123, "grad_norm": 5942.8173828125, "learning_rate": 2.485294117647059e-05, "loss": 0.0337, "step": 785 }, { "epoch": 5.383561643835616, "grad_norm": 7210.0673828125, "learning_rate": 2.4816176470588238e-05, "loss": 0.0351, "step": 786 }, { "epoch": 5.390410958904109, "grad_norm": 8678.287109375, "learning_rate": 2.4779411764705884e-05, "loss": 0.0357, "step": 787 }, { "epoch": 5.397260273972603, "grad_norm": 7212.65087890625, "learning_rate": 2.4742647058823532e-05, "loss": 0.0376, "step": 788 }, { "epoch": 5.404109589041096, "grad_norm": 7989.67138671875, "learning_rate": 2.4705882352941178e-05, "loss": 0.038, "step": 789 }, { "epoch": 5.410958904109589, "grad_norm": 5333.83984375, "learning_rate": 2.4669117647058826e-05, "loss": 0.0309, "step": 790 }, { "epoch": 5.417808219178082, "grad_norm": 7605.9013671875, "learning_rate": 2.4632352941176472e-05, "loss": 0.0385, "step": 791 }, { "epoch": 5.424657534246576, "grad_norm": 9575.14453125, "learning_rate": 2.4595588235294117e-05, "loss": 0.051, "step": 792 }, { "epoch": 5.431506849315069, "grad_norm": 6784.43017578125, "learning_rate": 2.4558823529411766e-05, "loss": 0.0352, "step": 793 }, { "epoch": 5.438356164383562, "grad_norm": 5473.25537109375, "learning_rate": 2.452205882352941e-05, "loss": 0.0281, "step": 794 }, { "epoch": 5.445205479452055, "grad_norm": 5592.32568359375, "learning_rate": 2.448529411764706e-05, "loss": 0.031, "step": 795 }, { "epoch": 5.4520547945205475, "grad_norm": 5136.62109375, "learning_rate": 2.4448529411764705e-05, "loss": 0.0288, "step": 796 }, { "epoch": 5.458904109589041, "grad_norm": 7540.76953125, "learning_rate": 2.4411764705882354e-05, "loss": 0.03, "step": 797 }, { "epoch": 5.465753424657534, "grad_norm": 6278.25439453125, "learning_rate": 2.4375e-05, "loss": 0.0352, "step": 798 }, { "epoch": 5.472602739726027, "grad_norm": 6933.1640625, "learning_rate": 2.433823529411765e-05, "loss": 0.0208, "step": 799 }, { "epoch": 5.47945205479452, "grad_norm": 6168.09130859375, "learning_rate": 2.4301470588235294e-05, "loss": 0.0263, "step": 800 }, { "epoch": 5.486301369863014, "grad_norm": 6978.314453125, "learning_rate": 2.4264705882352942e-05, "loss": 0.0366, "step": 801 }, { "epoch": 5.493150684931507, "grad_norm": 8291.953125, "learning_rate": 2.4227941176470588e-05, "loss": 0.0346, "step": 802 }, { "epoch": 5.5, "grad_norm": 6061.6923828125, "learning_rate": 2.4191176470588237e-05, "loss": 0.0246, "step": 803 }, { "epoch": 5.506849315068493, "grad_norm": 5955.45263671875, "learning_rate": 2.4154411764705885e-05, "loss": 0.0296, "step": 804 }, { "epoch": 5.513698630136986, "grad_norm": 5686.9814453125, "learning_rate": 2.411764705882353e-05, "loss": 0.0375, "step": 805 }, { "epoch": 5.52054794520548, "grad_norm": 6004.318359375, "learning_rate": 2.408088235294118e-05, "loss": 0.0251, "step": 806 }, { "epoch": 5.527397260273973, "grad_norm": 7318.16357421875, "learning_rate": 2.4044117647058825e-05, "loss": 0.0368, "step": 807 }, { "epoch": 5.534246575342466, "grad_norm": 8269.1875, "learning_rate": 2.4007352941176474e-05, "loss": 0.0354, "step": 808 }, { "epoch": 5.541095890410959, "grad_norm": 8441.1240234375, "learning_rate": 2.397058823529412e-05, "loss": 0.0362, "step": 809 }, { "epoch": 5.5479452054794525, "grad_norm": 10803.1748046875, "learning_rate": 2.3933823529411768e-05, "loss": 0.0309, "step": 810 }, { "epoch": 5.554794520547945, "grad_norm": 11385.5673828125, "learning_rate": 2.3897058823529413e-05, "loss": 0.0473, "step": 811 }, { "epoch": 5.561643835616438, "grad_norm": 6330.8896484375, "learning_rate": 2.3860294117647062e-05, "loss": 0.0295, "step": 812 }, { "epoch": 5.568493150684931, "grad_norm": 6541.31103515625, "learning_rate": 2.3823529411764707e-05, "loss": 0.0326, "step": 813 }, { "epoch": 5.575342465753424, "grad_norm": 7127.06591796875, "learning_rate": 2.3786764705882353e-05, "loss": 0.0264, "step": 814 }, { "epoch": 5.582191780821918, "grad_norm": 6557.96728515625, "learning_rate": 2.375e-05, "loss": 0.0348, "step": 815 }, { "epoch": 5.589041095890411, "grad_norm": 8497.2060546875, "learning_rate": 2.3713235294117647e-05, "loss": 0.0329, "step": 816 }, { "epoch": 5.595890410958904, "grad_norm": 5944.8955078125, "learning_rate": 2.3676470588235295e-05, "loss": 0.0217, "step": 817 }, { "epoch": 5.602739726027397, "grad_norm": 6949.98974609375, "learning_rate": 2.363970588235294e-05, "loss": 0.0275, "step": 818 }, { "epoch": 5.609589041095891, "grad_norm": 6402.06201171875, "learning_rate": 2.360294117647059e-05, "loss": 0.0331, "step": 819 }, { "epoch": 5.616438356164384, "grad_norm": 7283.587890625, "learning_rate": 2.3566176470588235e-05, "loss": 0.0339, "step": 820 }, { "epoch": 5.623287671232877, "grad_norm": 8604.55859375, "learning_rate": 2.3529411764705884e-05, "loss": 0.0335, "step": 821 }, { "epoch": 5.63013698630137, "grad_norm": 7734.4970703125, "learning_rate": 2.349264705882353e-05, "loss": 0.0335, "step": 822 }, { "epoch": 5.636986301369863, "grad_norm": 7388.4658203125, "learning_rate": 2.3455882352941178e-05, "loss": 0.0213, "step": 823 }, { "epoch": 5.6438356164383565, "grad_norm": 12157.748046875, "learning_rate": 2.3419117647058823e-05, "loss": 0.0497, "step": 824 }, { "epoch": 5.6506849315068495, "grad_norm": 6778.88525390625, "learning_rate": 2.3382352941176472e-05, "loss": 0.0298, "step": 825 }, { "epoch": 5.657534246575342, "grad_norm": 9119.44921875, "learning_rate": 2.334558823529412e-05, "loss": 0.0462, "step": 826 }, { "epoch": 5.664383561643835, "grad_norm": 6422.67578125, "learning_rate": 2.3308823529411766e-05, "loss": 0.0371, "step": 827 }, { "epoch": 5.671232876712329, "grad_norm": 6086.390625, "learning_rate": 2.3272058823529415e-05, "loss": 0.0284, "step": 828 }, { "epoch": 5.678082191780822, "grad_norm": 6575.31494140625, "learning_rate": 2.323529411764706e-05, "loss": 0.0321, "step": 829 }, { "epoch": 5.684931506849315, "grad_norm": 8906.9296875, "learning_rate": 2.319852941176471e-05, "loss": 0.0374, "step": 830 }, { "epoch": 5.691780821917808, "grad_norm": 6519.3857421875, "learning_rate": 2.3161764705882354e-05, "loss": 0.0364, "step": 831 }, { "epoch": 5.698630136986301, "grad_norm": 5928.95947265625, "learning_rate": 2.3125000000000003e-05, "loss": 0.0359, "step": 832 }, { "epoch": 5.705479452054795, "grad_norm": 4938.83056640625, "learning_rate": 2.308823529411765e-05, "loss": 0.0297, "step": 833 }, { "epoch": 5.712328767123288, "grad_norm": 6107.7001953125, "learning_rate": 2.3051470588235297e-05, "loss": 0.0254, "step": 834 }, { "epoch": 5.719178082191781, "grad_norm": 6157.7158203125, "learning_rate": 2.3014705882352943e-05, "loss": 0.0305, "step": 835 }, { "epoch": 5.726027397260274, "grad_norm": 6225.365234375, "learning_rate": 2.2977941176470588e-05, "loss": 0.0291, "step": 836 }, { "epoch": 5.732876712328768, "grad_norm": 6109.07275390625, "learning_rate": 2.2941176470588237e-05, "loss": 0.0353, "step": 837 }, { "epoch": 5.739726027397261, "grad_norm": 6426.76025390625, "learning_rate": 2.2904411764705882e-05, "loss": 0.0286, "step": 838 }, { "epoch": 5.7465753424657535, "grad_norm": 6545.119140625, "learning_rate": 2.286764705882353e-05, "loss": 0.026, "step": 839 }, { "epoch": 5.7534246575342465, "grad_norm": 8635.67578125, "learning_rate": 2.2830882352941176e-05, "loss": 0.0354, "step": 840 }, { "epoch": 5.760273972602739, "grad_norm": 7503.8115234375, "learning_rate": 2.2794117647058825e-05, "loss": 0.0224, "step": 841 }, { "epoch": 5.767123287671232, "grad_norm": 4226.76953125, "learning_rate": 2.275735294117647e-05, "loss": 0.0246, "step": 842 }, { "epoch": 5.773972602739726, "grad_norm": 7485.30810546875, "learning_rate": 2.272058823529412e-05, "loss": 0.0373, "step": 843 }, { "epoch": 5.780821917808219, "grad_norm": 10312.9130859375, "learning_rate": 2.2683823529411764e-05, "loss": 0.036, "step": 844 }, { "epoch": 5.787671232876712, "grad_norm": 26659.2109375, "learning_rate": 2.2647058823529413e-05, "loss": 0.0565, "step": 845 }, { "epoch": 5.794520547945205, "grad_norm": 7684.9404296875, "learning_rate": 2.261029411764706e-05, "loss": 0.0409, "step": 846 }, { "epoch": 5.801369863013699, "grad_norm": 22887.88671875, "learning_rate": 2.2573529411764707e-05, "loss": 0.0348, "step": 847 }, { "epoch": 5.808219178082192, "grad_norm": 10275.2841796875, "learning_rate": 2.2536764705882356e-05, "loss": 0.0346, "step": 848 }, { "epoch": 5.815068493150685, "grad_norm": 7011.17431640625, "learning_rate": 2.25e-05, "loss": 0.0284, "step": 849 }, { "epoch": 5.821917808219178, "grad_norm": 7766.92236328125, "learning_rate": 2.246323529411765e-05, "loss": 0.0283, "step": 850 }, { "epoch": 5.828767123287671, "grad_norm": 7168.0234375, "learning_rate": 2.2426470588235296e-05, "loss": 0.03, "step": 851 }, { "epoch": 5.835616438356165, "grad_norm": 6958.8515625, "learning_rate": 2.2389705882352944e-05, "loss": 0.0383, "step": 852 }, { "epoch": 5.842465753424658, "grad_norm": 8071.2451171875, "learning_rate": 2.235294117647059e-05, "loss": 0.0291, "step": 853 }, { "epoch": 5.8493150684931505, "grad_norm": 5526.2666015625, "learning_rate": 2.231617647058824e-05, "loss": 0.0274, "step": 854 }, { "epoch": 5.8561643835616435, "grad_norm": 7994.29736328125, "learning_rate": 2.2279411764705884e-05, "loss": 0.0393, "step": 855 }, { "epoch": 5.863013698630137, "grad_norm": 6951.50537109375, "learning_rate": 2.224264705882353e-05, "loss": 0.032, "step": 856 }, { "epoch": 5.86986301369863, "grad_norm": 7051.30419921875, "learning_rate": 2.2205882352941178e-05, "loss": 0.0282, "step": 857 }, { "epoch": 5.876712328767123, "grad_norm": 6306.4189453125, "learning_rate": 2.2169117647058823e-05, "loss": 0.0299, "step": 858 }, { "epoch": 5.883561643835616, "grad_norm": 8451.232421875, "learning_rate": 2.2132352941176472e-05, "loss": 0.0352, "step": 859 }, { "epoch": 5.890410958904109, "grad_norm": 5076.19189453125, "learning_rate": 2.2095588235294117e-05, "loss": 0.0241, "step": 860 }, { "epoch": 5.897260273972603, "grad_norm": 9469.7021484375, "learning_rate": 2.2058823529411766e-05, "loss": 0.0392, "step": 861 }, { "epoch": 5.904109589041096, "grad_norm": 8628.0888671875, "learning_rate": 2.202205882352941e-05, "loss": 0.0325, "step": 862 }, { "epoch": 5.910958904109589, "grad_norm": 6545.4560546875, "learning_rate": 2.198529411764706e-05, "loss": 0.0315, "step": 863 }, { "epoch": 5.917808219178082, "grad_norm": 8332.845703125, "learning_rate": 2.1948529411764706e-05, "loss": 0.0388, "step": 864 }, { "epoch": 5.924657534246576, "grad_norm": 11515.0498046875, "learning_rate": 2.1911764705882354e-05, "loss": 0.0293, "step": 865 }, { "epoch": 5.931506849315069, "grad_norm": 5809.8232421875, "learning_rate": 2.1875e-05, "loss": 0.0278, "step": 866 }, { "epoch": 5.938356164383562, "grad_norm": 8603.01953125, "learning_rate": 2.183823529411765e-05, "loss": 0.037, "step": 867 }, { "epoch": 5.945205479452055, "grad_norm": 5425.0693359375, "learning_rate": 2.1801470588235294e-05, "loss": 0.0228, "step": 868 }, { "epoch": 5.9520547945205475, "grad_norm": 9101.9541015625, "learning_rate": 2.1764705882352943e-05, "loss": 0.0424, "step": 869 }, { "epoch": 5.958904109589041, "grad_norm": 7689.30810546875, "learning_rate": 2.172794117647059e-05, "loss": 0.0338, "step": 870 }, { "epoch": 5.965753424657534, "grad_norm": 4987.15771484375, "learning_rate": 2.1691176470588237e-05, "loss": 0.0231, "step": 871 }, { "epoch": 5.972602739726027, "grad_norm": 4933.22998046875, "learning_rate": 2.1654411764705886e-05, "loss": 0.0275, "step": 872 }, { "epoch": 5.97945205479452, "grad_norm": 5396.56396484375, "learning_rate": 2.161764705882353e-05, "loss": 0.0295, "step": 873 }, { "epoch": 5.986301369863014, "grad_norm": 6485.00341796875, "learning_rate": 2.158088235294118e-05, "loss": 0.0283, "step": 874 }, { "epoch": 5.993150684931507, "grad_norm": 7381.5, "learning_rate": 2.1544117647058825e-05, "loss": 0.0253, "step": 875 }, { "epoch": 6.0, "grad_norm": 3900.22216796875, "learning_rate": 2.1507352941176474e-05, "loss": 0.0181, "step": 876 }, { "epoch": 6.0, "eval_f1_macro": 0.587683030418625, "eval_f1_micro": 0.8158765159867696, "eval_loss": 0.03869513422250748, "eval_precision": 0.893719806763285, "eval_recall": 0.7505070993914807, "eval_runtime": 1.1011, "eval_samples_per_second": 353.268, "eval_steps_per_second": 15.438, "step": 876 }, { "epoch": 6.006849315068493, "grad_norm": 6255.61181640625, "learning_rate": 2.1470588235294116e-05, "loss": 0.0278, "step": 877 }, { "epoch": 6.013698630136986, "grad_norm": 4930.43798828125, "learning_rate": 2.1433823529411765e-05, "loss": 0.0293, "step": 878 }, { "epoch": 6.02054794520548, "grad_norm": 6900.69482421875, "learning_rate": 2.1397058823529413e-05, "loss": 0.0314, "step": 879 }, { "epoch": 6.027397260273973, "grad_norm": 4499.61181640625, "learning_rate": 2.136029411764706e-05, "loss": 0.0239, "step": 880 }, { "epoch": 6.034246575342466, "grad_norm": 5845.4404296875, "learning_rate": 2.1323529411764707e-05, "loss": 0.0364, "step": 881 }, { "epoch": 6.041095890410959, "grad_norm": 4306.958984375, "learning_rate": 2.1286764705882353e-05, "loss": 0.0255, "step": 882 }, { "epoch": 6.0479452054794525, "grad_norm": 4746.87744140625, "learning_rate": 2.125e-05, "loss": 0.0208, "step": 883 }, { "epoch": 6.054794520547945, "grad_norm": 5558.3671875, "learning_rate": 2.1213235294117647e-05, "loss": 0.0309, "step": 884 }, { "epoch": 6.061643835616438, "grad_norm": 8801.2109375, "learning_rate": 2.1176470588235296e-05, "loss": 0.048, "step": 885 }, { "epoch": 6.068493150684931, "grad_norm": 4654.44970703125, "learning_rate": 2.113970588235294e-05, "loss": 0.0217, "step": 886 }, { "epoch": 6.075342465753424, "grad_norm": 7711.31689453125, "learning_rate": 2.110294117647059e-05, "loss": 0.0301, "step": 887 }, { "epoch": 6.082191780821918, "grad_norm": 5137.5390625, "learning_rate": 2.1066176470588235e-05, "loss": 0.029, "step": 888 }, { "epoch": 6.089041095890411, "grad_norm": 5748.33251953125, "learning_rate": 2.1029411764705884e-05, "loss": 0.0333, "step": 889 }, { "epoch": 6.095890410958904, "grad_norm": 5696.43212890625, "learning_rate": 2.099264705882353e-05, "loss": 0.0308, "step": 890 }, { "epoch": 6.102739726027397, "grad_norm": 5576.82080078125, "learning_rate": 2.0955882352941178e-05, "loss": 0.0316, "step": 891 }, { "epoch": 6.109589041095891, "grad_norm": 4056.412109375, "learning_rate": 2.0919117647058827e-05, "loss": 0.0181, "step": 892 }, { "epoch": 6.116438356164384, "grad_norm": 5952.173828125, "learning_rate": 2.0882352941176472e-05, "loss": 0.0247, "step": 893 }, { "epoch": 6.123287671232877, "grad_norm": 4457.82275390625, "learning_rate": 2.084558823529412e-05, "loss": 0.0286, "step": 894 }, { "epoch": 6.13013698630137, "grad_norm": 8899.123046875, "learning_rate": 2.0808823529411766e-05, "loss": 0.031, "step": 895 }, { "epoch": 6.136986301369863, "grad_norm": 6229.8994140625, "learning_rate": 2.0772058823529415e-05, "loss": 0.0267, "step": 896 }, { "epoch": 6.1438356164383565, "grad_norm": 11629.6328125, "learning_rate": 2.073529411764706e-05, "loss": 0.0272, "step": 897 }, { "epoch": 6.1506849315068495, "grad_norm": 6292.99462890625, "learning_rate": 2.0698529411764706e-05, "loss": 0.0241, "step": 898 }, { "epoch": 6.157534246575342, "grad_norm": 4954.70556640625, "learning_rate": 2.066176470588235e-05, "loss": 0.02, "step": 899 }, { "epoch": 6.164383561643835, "grad_norm": 5328.25830078125, "learning_rate": 2.0625e-05, "loss": 0.0247, "step": 900 }, { "epoch": 6.171232876712328, "grad_norm": 7557.40673828125, "learning_rate": 2.058823529411765e-05, "loss": 0.0326, "step": 901 }, { "epoch": 6.178082191780822, "grad_norm": 7813.22802734375, "learning_rate": 2.0551470588235294e-05, "loss": 0.0336, "step": 902 }, { "epoch": 6.184931506849315, "grad_norm": 6645.81689453125, "learning_rate": 2.0514705882352943e-05, "loss": 0.0332, "step": 903 }, { "epoch": 6.191780821917808, "grad_norm": 6545.62548828125, "learning_rate": 2.0477941176470588e-05, "loss": 0.0369, "step": 904 }, { "epoch": 6.198630136986301, "grad_norm": 5510.41796875, "learning_rate": 2.0441176470588237e-05, "loss": 0.0246, "step": 905 }, { "epoch": 6.205479452054795, "grad_norm": 5712.80419921875, "learning_rate": 2.0404411764705882e-05, "loss": 0.0305, "step": 906 }, { "epoch": 6.212328767123288, "grad_norm": 8606.455078125, "learning_rate": 2.036764705882353e-05, "loss": 0.0199, "step": 907 }, { "epoch": 6.219178082191781, "grad_norm": 4413.12646484375, "learning_rate": 2.0330882352941176e-05, "loss": 0.0222, "step": 908 }, { "epoch": 6.226027397260274, "grad_norm": 6485.04638671875, "learning_rate": 2.0294117647058825e-05, "loss": 0.0297, "step": 909 }, { "epoch": 6.232876712328767, "grad_norm": 6743.6865234375, "learning_rate": 2.025735294117647e-05, "loss": 0.0257, "step": 910 }, { "epoch": 6.239726027397261, "grad_norm": 6131.67822265625, "learning_rate": 2.022058823529412e-05, "loss": 0.0301, "step": 911 }, { "epoch": 6.2465753424657535, "grad_norm": 6772.25830078125, "learning_rate": 2.0183823529411765e-05, "loss": 0.0236, "step": 912 }, { "epoch": 6.2534246575342465, "grad_norm": 5547.431640625, "learning_rate": 2.0147058823529413e-05, "loss": 0.0279, "step": 913 }, { "epoch": 6.260273972602739, "grad_norm": 5270.72607421875, "learning_rate": 2.0110294117647062e-05, "loss": 0.0205, "step": 914 }, { "epoch": 6.267123287671233, "grad_norm": 7012.44091796875, "learning_rate": 2.0073529411764708e-05, "loss": 0.0247, "step": 915 }, { "epoch": 6.273972602739726, "grad_norm": 6526.4384765625, "learning_rate": 2.0036764705882356e-05, "loss": 0.0231, "step": 916 }, { "epoch": 6.280821917808219, "grad_norm": 4469.55322265625, "learning_rate": 2e-05, "loss": 0.0269, "step": 917 }, { "epoch": 6.287671232876712, "grad_norm": 7655.8515625, "learning_rate": 1.996323529411765e-05, "loss": 0.0336, "step": 918 }, { "epoch": 6.294520547945205, "grad_norm": 7291.91748046875, "learning_rate": 1.9926470588235296e-05, "loss": 0.0273, "step": 919 }, { "epoch": 6.301369863013699, "grad_norm": 6064.85888671875, "learning_rate": 1.988970588235294e-05, "loss": 0.0278, "step": 920 }, { "epoch": 6.308219178082192, "grad_norm": 6332.345703125, "learning_rate": 1.9852941176470586e-05, "loss": 0.0251, "step": 921 }, { "epoch": 6.315068493150685, "grad_norm": 3714.201416015625, "learning_rate": 1.9816176470588235e-05, "loss": 0.0158, "step": 922 }, { "epoch": 6.321917808219178, "grad_norm": 3927.277099609375, "learning_rate": 1.9779411764705884e-05, "loss": 0.0287, "step": 923 }, { "epoch": 6.328767123287671, "grad_norm": 3158.520751953125, "learning_rate": 1.974264705882353e-05, "loss": 0.0206, "step": 924 }, { "epoch": 6.335616438356165, "grad_norm": 5437.79296875, "learning_rate": 1.9705882352941178e-05, "loss": 0.0271, "step": 925 }, { "epoch": 6.342465753424658, "grad_norm": 4417.53125, "learning_rate": 1.9669117647058824e-05, "loss": 0.023, "step": 926 }, { "epoch": 6.3493150684931505, "grad_norm": 7217.78759765625, "learning_rate": 1.9632352941176472e-05, "loss": 0.0307, "step": 927 }, { "epoch": 6.3561643835616435, "grad_norm": 7369.02294921875, "learning_rate": 1.9595588235294118e-05, "loss": 0.0314, "step": 928 }, { "epoch": 6.363013698630137, "grad_norm": 5451.7373046875, "learning_rate": 1.9558823529411766e-05, "loss": 0.0385, "step": 929 }, { "epoch": 6.36986301369863, "grad_norm": 4802.2451171875, "learning_rate": 1.9522058823529412e-05, "loss": 0.0247, "step": 930 }, { "epoch": 6.376712328767123, "grad_norm": 7564.18212890625, "learning_rate": 1.948529411764706e-05, "loss": 0.0286, "step": 931 }, { "epoch": 6.383561643835616, "grad_norm": 4304.99853515625, "learning_rate": 1.9448529411764706e-05, "loss": 0.0201, "step": 932 }, { "epoch": 6.390410958904109, "grad_norm": 7202.56494140625, "learning_rate": 1.9411764705882355e-05, "loss": 0.0289, "step": 933 }, { "epoch": 6.397260273972603, "grad_norm": 9432.3759765625, "learning_rate": 1.9375e-05, "loss": 0.0239, "step": 934 }, { "epoch": 6.404109589041096, "grad_norm": 8724.4580078125, "learning_rate": 1.933823529411765e-05, "loss": 0.0231, "step": 935 }, { "epoch": 6.410958904109589, "grad_norm": 5771.5263671875, "learning_rate": 1.9301470588235298e-05, "loss": 0.0239, "step": 936 }, { "epoch": 6.417808219178082, "grad_norm": 6464.62548828125, "learning_rate": 1.9264705882352943e-05, "loss": 0.0289, "step": 937 }, { "epoch": 6.424657534246576, "grad_norm": 6679.06689453125, "learning_rate": 1.922794117647059e-05, "loss": 0.0385, "step": 938 }, { "epoch": 6.431506849315069, "grad_norm": 7793.0078125, "learning_rate": 1.9191176470588237e-05, "loss": 0.0249, "step": 939 }, { "epoch": 6.438356164383562, "grad_norm": 5247.92724609375, "learning_rate": 1.9154411764705886e-05, "loss": 0.0245, "step": 940 }, { "epoch": 6.445205479452055, "grad_norm": 6361.404296875, "learning_rate": 1.9117647058823528e-05, "loss": 0.029, "step": 941 }, { "epoch": 6.4520547945205475, "grad_norm": 6761.35205078125, "learning_rate": 1.9080882352941176e-05, "loss": 0.0291, "step": 942 }, { "epoch": 6.458904109589041, "grad_norm": 10144.5205078125, "learning_rate": 1.9044117647058822e-05, "loss": 0.0288, "step": 943 }, { "epoch": 6.465753424657534, "grad_norm": 5911.9052734375, "learning_rate": 1.900735294117647e-05, "loss": 0.0314, "step": 944 }, { "epoch": 6.472602739726027, "grad_norm": 6211.17236328125, "learning_rate": 1.897058823529412e-05, "loss": 0.0304, "step": 945 }, { "epoch": 6.47945205479452, "grad_norm": 4022.568115234375, "learning_rate": 1.8933823529411765e-05, "loss": 0.0196, "step": 946 }, { "epoch": 6.486301369863014, "grad_norm": 4532.18505859375, "learning_rate": 1.8897058823529413e-05, "loss": 0.0221, "step": 947 }, { "epoch": 6.493150684931507, "grad_norm": 4401.65234375, "learning_rate": 1.886029411764706e-05, "loss": 0.0225, "step": 948 }, { "epoch": 6.5, "grad_norm": 12782.63671875, "learning_rate": 1.8823529411764708e-05, "loss": 0.0376, "step": 949 }, { "epoch": 6.506849315068493, "grad_norm": 7145.794921875, "learning_rate": 1.8786764705882353e-05, "loss": 0.0276, "step": 950 }, { "epoch": 6.513698630136986, "grad_norm": 7941.71875, "learning_rate": 1.8750000000000002e-05, "loss": 0.0373, "step": 951 }, { "epoch": 6.52054794520548, "grad_norm": 11798.1083984375, "learning_rate": 1.8713235294117647e-05, "loss": 0.0406, "step": 952 }, { "epoch": 6.527397260273973, "grad_norm": 3468.359619140625, "learning_rate": 1.8676470588235296e-05, "loss": 0.0161, "step": 953 }, { "epoch": 6.534246575342466, "grad_norm": 6157.85302734375, "learning_rate": 1.863970588235294e-05, "loss": 0.0259, "step": 954 }, { "epoch": 6.541095890410959, "grad_norm": 5776.75634765625, "learning_rate": 1.860294117647059e-05, "loss": 0.0269, "step": 955 }, { "epoch": 6.5479452054794525, "grad_norm": 8140.83056640625, "learning_rate": 1.8566176470588235e-05, "loss": 0.0251, "step": 956 }, { "epoch": 6.554794520547945, "grad_norm": 6804.15771484375, "learning_rate": 1.8529411764705884e-05, "loss": 0.0319, "step": 957 }, { "epoch": 6.561643835616438, "grad_norm": 5432.4326171875, "learning_rate": 1.8492647058823533e-05, "loss": 0.0255, "step": 958 }, { "epoch": 6.568493150684931, "grad_norm": 5102.7861328125, "learning_rate": 1.8455882352941178e-05, "loss": 0.0229, "step": 959 }, { "epoch": 6.575342465753424, "grad_norm": 7881.17333984375, "learning_rate": 1.8419117647058827e-05, "loss": 0.0251, "step": 960 }, { "epoch": 6.582191780821918, "grad_norm": 6849.41455078125, "learning_rate": 1.8382352941176472e-05, "loss": 0.0267, "step": 961 }, { "epoch": 6.589041095890411, "grad_norm": 7423.6044921875, "learning_rate": 1.8345588235294118e-05, "loss": 0.0298, "step": 962 }, { "epoch": 6.595890410958904, "grad_norm": 3518.1328125, "learning_rate": 1.8308823529411763e-05, "loss": 0.0159, "step": 963 }, { "epoch": 6.602739726027397, "grad_norm": 4917.0478515625, "learning_rate": 1.8272058823529412e-05, "loss": 0.0256, "step": 964 }, { "epoch": 6.609589041095891, "grad_norm": 6179.9609375, "learning_rate": 1.8235294117647057e-05, "loss": 0.025, "step": 965 }, { "epoch": 6.616438356164384, "grad_norm": 6606.26953125, "learning_rate": 1.8198529411764706e-05, "loss": 0.0345, "step": 966 }, { "epoch": 6.623287671232877, "grad_norm": 3547.204345703125, "learning_rate": 1.8161764705882355e-05, "loss": 0.0197, "step": 967 }, { "epoch": 6.63013698630137, "grad_norm": 6826.13525390625, "learning_rate": 1.8125e-05, "loss": 0.034, "step": 968 }, { "epoch": 6.636986301369863, "grad_norm": 8068.3671875, "learning_rate": 1.808823529411765e-05, "loss": 0.0281, "step": 969 }, { "epoch": 6.6438356164383565, "grad_norm": 10396.8466796875, "learning_rate": 1.8051470588235294e-05, "loss": 0.0312, "step": 970 }, { "epoch": 6.6506849315068495, "grad_norm": 3679.21875, "learning_rate": 1.8014705882352943e-05, "loss": 0.0175, "step": 971 }, { "epoch": 6.657534246575342, "grad_norm": 5543.42578125, "learning_rate": 1.797794117647059e-05, "loss": 0.0295, "step": 972 }, { "epoch": 6.664383561643835, "grad_norm": 4589.06201171875, "learning_rate": 1.7941176470588237e-05, "loss": 0.0197, "step": 973 }, { "epoch": 6.671232876712329, "grad_norm": 6784.16748046875, "learning_rate": 1.7904411764705882e-05, "loss": 0.0293, "step": 974 }, { "epoch": 6.678082191780822, "grad_norm": 4807.26904296875, "learning_rate": 1.786764705882353e-05, "loss": 0.0206, "step": 975 }, { "epoch": 6.684931506849315, "grad_norm": 3941.919921875, "learning_rate": 1.7830882352941177e-05, "loss": 0.0208, "step": 976 }, { "epoch": 6.691780821917808, "grad_norm": 6731.00634765625, "learning_rate": 1.7794117647058825e-05, "loss": 0.0268, "step": 977 }, { "epoch": 6.698630136986301, "grad_norm": 5573.61474609375, "learning_rate": 1.775735294117647e-05, "loss": 0.0246, "step": 978 }, { "epoch": 6.705479452054795, "grad_norm": 5104.92724609375, "learning_rate": 1.772058823529412e-05, "loss": 0.0202, "step": 979 }, { "epoch": 6.712328767123288, "grad_norm": 8361.2197265625, "learning_rate": 1.7683823529411768e-05, "loss": 0.0265, "step": 980 }, { "epoch": 6.719178082191781, "grad_norm": 5249.89697265625, "learning_rate": 1.7647058823529414e-05, "loss": 0.0281, "step": 981 }, { "epoch": 6.726027397260274, "grad_norm": 5865.0, "learning_rate": 1.7610294117647062e-05, "loss": 0.0189, "step": 982 }, { "epoch": 6.732876712328768, "grad_norm": 9215.04296875, "learning_rate": 1.7573529411764704e-05, "loss": 0.032, "step": 983 }, { "epoch": 6.739726027397261, "grad_norm": 7711.40185546875, "learning_rate": 1.7536764705882353e-05, "loss": 0.0422, "step": 984 }, { "epoch": 6.7465753424657535, "grad_norm": 8890.955078125, "learning_rate": 1.75e-05, "loss": 0.0279, "step": 985 }, { "epoch": 6.7534246575342465, "grad_norm": 6132.775390625, "learning_rate": 1.7463235294117647e-05, "loss": 0.0307, "step": 986 }, { "epoch": 6.760273972602739, "grad_norm": 4567.98779296875, "learning_rate": 1.7426470588235293e-05, "loss": 0.0208, "step": 987 }, { "epoch": 6.767123287671232, "grad_norm": 6029.92626953125, "learning_rate": 1.738970588235294e-05, "loss": 0.0304, "step": 988 }, { "epoch": 6.773972602739726, "grad_norm": 7717.0224609375, "learning_rate": 1.735294117647059e-05, "loss": 0.0265, "step": 989 }, { "epoch": 6.780821917808219, "grad_norm": 7314.884765625, "learning_rate": 1.7316176470588235e-05, "loss": 0.0267, "step": 990 }, { "epoch": 6.787671232876712, "grad_norm": 7766.0380859375, "learning_rate": 1.7279411764705884e-05, "loss": 0.0331, "step": 991 }, { "epoch": 6.794520547945205, "grad_norm": 8191.09326171875, "learning_rate": 1.724264705882353e-05, "loss": 0.0223, "step": 992 }, { "epoch": 6.801369863013699, "grad_norm": 9929.1376953125, "learning_rate": 1.720588235294118e-05, "loss": 0.0356, "step": 993 }, { "epoch": 6.808219178082192, "grad_norm": 5216.33837890625, "learning_rate": 1.7169117647058824e-05, "loss": 0.0203, "step": 994 }, { "epoch": 6.815068493150685, "grad_norm": 8073.47607421875, "learning_rate": 1.7132352941176472e-05, "loss": 0.0335, "step": 995 }, { "epoch": 6.821917808219178, "grad_norm": 8895.767578125, "learning_rate": 1.7095588235294118e-05, "loss": 0.0357, "step": 996 }, { "epoch": 6.828767123287671, "grad_norm": 2822.36279296875, "learning_rate": 1.7058823529411767e-05, "loss": 0.0153, "step": 997 }, { "epoch": 6.835616438356165, "grad_norm": 4473.52001953125, "learning_rate": 1.7022058823529412e-05, "loss": 0.0215, "step": 998 }, { "epoch": 6.842465753424658, "grad_norm": 9064.0029296875, "learning_rate": 1.698529411764706e-05, "loss": 0.0392, "step": 999 }, { "epoch": 6.8493150684931505, "grad_norm": 10523.1513671875, "learning_rate": 1.6948529411764706e-05, "loss": 0.0451, "step": 1000 }, { "epoch": 6.8561643835616435, "grad_norm": 9220.6796875, "learning_rate": 1.6911764705882355e-05, "loss": 0.04, "step": 1001 }, { "epoch": 6.863013698630137, "grad_norm": 6817.91259765625, "learning_rate": 1.6875000000000004e-05, "loss": 0.0269, "step": 1002 }, { "epoch": 6.86986301369863, "grad_norm": 8044.4521484375, "learning_rate": 1.683823529411765e-05, "loss": 0.0265, "step": 1003 }, { "epoch": 6.876712328767123, "grad_norm": 4975.56884765625, "learning_rate": 1.6801470588235298e-05, "loss": 0.0247, "step": 1004 }, { "epoch": 6.883561643835616, "grad_norm": 6807.12353515625, "learning_rate": 1.676470588235294e-05, "loss": 0.0305, "step": 1005 }, { "epoch": 6.890410958904109, "grad_norm": 8871.470703125, "learning_rate": 1.672794117647059e-05, "loss": 0.0302, "step": 1006 }, { "epoch": 6.897260273972603, "grad_norm": 10929.6298828125, "learning_rate": 1.6691176470588234e-05, "loss": 0.0337, "step": 1007 }, { "epoch": 6.904109589041096, "grad_norm": 7087.83837890625, "learning_rate": 1.6654411764705883e-05, "loss": 0.029, "step": 1008 }, { "epoch": 6.910958904109589, "grad_norm": 8454.2060546875, "learning_rate": 1.6617647058823528e-05, "loss": 0.0298, "step": 1009 }, { "epoch": 6.917808219178082, "grad_norm": 6260.994140625, "learning_rate": 1.6580882352941177e-05, "loss": 0.028, "step": 1010 }, { "epoch": 6.924657534246576, "grad_norm": 4539.2724609375, "learning_rate": 1.6544117647058825e-05, "loss": 0.0206, "step": 1011 }, { "epoch": 6.931506849315069, "grad_norm": 8717.158203125, "learning_rate": 1.650735294117647e-05, "loss": 0.0361, "step": 1012 }, { "epoch": 6.938356164383562, "grad_norm": 7537.84619140625, "learning_rate": 1.647058823529412e-05, "loss": 0.0187, "step": 1013 }, { "epoch": 6.945205479452055, "grad_norm": 8055.9384765625, "learning_rate": 1.6433823529411765e-05, "loss": 0.0275, "step": 1014 }, { "epoch": 6.9520547945205475, "grad_norm": 9117.1787109375, "learning_rate": 1.6397058823529414e-05, "loss": 0.0312, "step": 1015 }, { "epoch": 6.958904109589041, "grad_norm": 8809.9169921875, "learning_rate": 1.636029411764706e-05, "loss": 0.0275, "step": 1016 }, { "epoch": 6.965753424657534, "grad_norm": 8724.7060546875, "learning_rate": 1.6323529411764708e-05, "loss": 0.028, "step": 1017 }, { "epoch": 6.972602739726027, "grad_norm": 4698.90478515625, "learning_rate": 1.6286764705882353e-05, "loss": 0.0207, "step": 1018 }, { "epoch": 6.97945205479452, "grad_norm": 5314.38134765625, "learning_rate": 1.6250000000000002e-05, "loss": 0.0211, "step": 1019 }, { "epoch": 6.986301369863014, "grad_norm": 7979.9462890625, "learning_rate": 1.6213235294117647e-05, "loss": 0.0317, "step": 1020 }, { "epoch": 6.993150684931507, "grad_norm": 5805.4287109375, "learning_rate": 1.6176470588235296e-05, "loss": 0.0253, "step": 1021 }, { "epoch": 7.0, "grad_norm": 8465.9765625, "learning_rate": 1.613970588235294e-05, "loss": 0.0288, "step": 1022 }, { "epoch": 7.0, "eval_f1_macro": 0.6431169350570771, "eval_f1_micro": 0.8313891834570519, "eval_loss": 0.03551609069108963, "eval_precision": 0.8711111111111111, "eval_recall": 0.795131845841785, "eval_runtime": 1.0973, "eval_samples_per_second": 354.499, "eval_steps_per_second": 15.492, "step": 1022 }, { "epoch": 7.006849315068493, "grad_norm": 6582.72216796875, "learning_rate": 1.610294117647059e-05, "loss": 0.0267, "step": 1023 }, { "epoch": 7.013698630136986, "grad_norm": 7356.06787109375, "learning_rate": 1.6066176470588236e-05, "loss": 0.0223, "step": 1024 }, { "epoch": 7.02054794520548, "grad_norm": 6371.90283203125, "learning_rate": 1.6029411764705884e-05, "loss": 0.0277, "step": 1025 }, { "epoch": 7.027397260273973, "grad_norm": 3727.25927734375, "learning_rate": 1.599264705882353e-05, "loss": 0.0207, "step": 1026 }, { "epoch": 7.034246575342466, "grad_norm": 5180.36376953125, "learning_rate": 1.5955882352941175e-05, "loss": 0.0298, "step": 1027 }, { "epoch": 7.041095890410959, "grad_norm": 3388.027099609375, "learning_rate": 1.5919117647058824e-05, "loss": 0.0181, "step": 1028 }, { "epoch": 7.0479452054794525, "grad_norm": 3696.1728515625, "learning_rate": 1.588235294117647e-05, "loss": 0.0228, "step": 1029 }, { "epoch": 7.054794520547945, "grad_norm": 6096.78173828125, "learning_rate": 1.5845588235294118e-05, "loss": 0.023, "step": 1030 }, { "epoch": 7.061643835616438, "grad_norm": 6847.19921875, "learning_rate": 1.5808823529411763e-05, "loss": 0.0317, "step": 1031 }, { "epoch": 7.068493150684931, "grad_norm": 5466.44482421875, "learning_rate": 1.5772058823529412e-05, "loss": 0.0225, "step": 1032 }, { "epoch": 7.075342465753424, "grad_norm": 6546.259765625, "learning_rate": 1.573529411764706e-05, "loss": 0.0269, "step": 1033 }, { "epoch": 7.082191780821918, "grad_norm": 5933.81787109375, "learning_rate": 1.5698529411764706e-05, "loss": 0.0258, "step": 1034 }, { "epoch": 7.089041095890411, "grad_norm": 6409.60107421875, "learning_rate": 1.5661764705882355e-05, "loss": 0.0342, "step": 1035 }, { "epoch": 7.095890410958904, "grad_norm": 7501.12158203125, "learning_rate": 1.5625e-05, "loss": 0.0311, "step": 1036 }, { "epoch": 7.102739726027397, "grad_norm": 3915.88525390625, "learning_rate": 1.558823529411765e-05, "loss": 0.0217, "step": 1037 }, { "epoch": 7.109589041095891, "grad_norm": 7001.2900390625, "learning_rate": 1.5551470588235294e-05, "loss": 0.0242, "step": 1038 }, { "epoch": 7.116438356164384, "grad_norm": 2907.997314453125, "learning_rate": 1.5514705882352943e-05, "loss": 0.0137, "step": 1039 }, { "epoch": 7.123287671232877, "grad_norm": 5298.4560546875, "learning_rate": 1.547794117647059e-05, "loss": 0.0201, "step": 1040 }, { "epoch": 7.13013698630137, "grad_norm": 2789.67822265625, "learning_rate": 1.5441176470588237e-05, "loss": 0.0191, "step": 1041 }, { "epoch": 7.136986301369863, "grad_norm": 4167.24267578125, "learning_rate": 1.5404411764705883e-05, "loss": 0.0232, "step": 1042 }, { "epoch": 7.1438356164383565, "grad_norm": 4988.18603515625, "learning_rate": 1.536764705882353e-05, "loss": 0.0229, "step": 1043 }, { "epoch": 7.1506849315068495, "grad_norm": 5862.60302734375, "learning_rate": 1.5330882352941177e-05, "loss": 0.022, "step": 1044 }, { "epoch": 7.157534246575342, "grad_norm": 4336.72802734375, "learning_rate": 1.5294117647058826e-05, "loss": 0.0242, "step": 1045 }, { "epoch": 7.164383561643835, "grad_norm": 6057.86474609375, "learning_rate": 1.5257352941176473e-05, "loss": 0.0288, "step": 1046 }, { "epoch": 7.171232876712328, "grad_norm": 5908.251953125, "learning_rate": 1.5220588235294116e-05, "loss": 0.0266, "step": 1047 }, { "epoch": 7.178082191780822, "grad_norm": 8310.8681640625, "learning_rate": 1.5183823529411765e-05, "loss": 0.0323, "step": 1048 }, { "epoch": 7.184931506849315, "grad_norm": 6309.19970703125, "learning_rate": 1.5147058823529412e-05, "loss": 0.0208, "step": 1049 }, { "epoch": 7.191780821917808, "grad_norm": 4016.859375, "learning_rate": 1.511029411764706e-05, "loss": 0.0215, "step": 1050 }, { "epoch": 7.198630136986301, "grad_norm": 11591.537109375, "learning_rate": 1.5073529411764706e-05, "loss": 0.0252, "step": 1051 }, { "epoch": 7.205479452054795, "grad_norm": 9439.849609375, "learning_rate": 1.5036764705882353e-05, "loss": 0.0194, "step": 1052 }, { "epoch": 7.212328767123288, "grad_norm": 9379.865234375, "learning_rate": 1.5e-05, "loss": 0.0366, "step": 1053 }, { "epoch": 7.219178082191781, "grad_norm": 7884.4404296875, "learning_rate": 1.4963235294117647e-05, "loss": 0.029, "step": 1054 }, { "epoch": 7.226027397260274, "grad_norm": 5343.81884765625, "learning_rate": 1.4926470588235295e-05, "loss": 0.0285, "step": 1055 }, { "epoch": 7.232876712328767, "grad_norm": 5796.96142578125, "learning_rate": 1.4889705882352942e-05, "loss": 0.0236, "step": 1056 }, { "epoch": 7.239726027397261, "grad_norm": 8583.462890625, "learning_rate": 1.4852941176470589e-05, "loss": 0.0322, "step": 1057 }, { "epoch": 7.2465753424657535, "grad_norm": 5199.9326171875, "learning_rate": 1.4816176470588236e-05, "loss": 0.0272, "step": 1058 }, { "epoch": 7.2534246575342465, "grad_norm": 3421.471435546875, "learning_rate": 1.4779411764705883e-05, "loss": 0.0183, "step": 1059 }, { "epoch": 7.260273972602739, "grad_norm": 7199.8798828125, "learning_rate": 1.474264705882353e-05, "loss": 0.0319, "step": 1060 }, { "epoch": 7.267123287671233, "grad_norm": 5265.10888671875, "learning_rate": 1.4705882352941177e-05, "loss": 0.0274, "step": 1061 }, { "epoch": 7.273972602739726, "grad_norm": 4701.056640625, "learning_rate": 1.4669117647058826e-05, "loss": 0.0222, "step": 1062 }, { "epoch": 7.280821917808219, "grad_norm": 5154.03466796875, "learning_rate": 1.4632352941176473e-05, "loss": 0.0217, "step": 1063 }, { "epoch": 7.287671232876712, "grad_norm": 3564.419921875, "learning_rate": 1.459558823529412e-05, "loss": 0.0203, "step": 1064 }, { "epoch": 7.294520547945205, "grad_norm": 4997.02734375, "learning_rate": 1.4558823529411767e-05, "loss": 0.0194, "step": 1065 }, { "epoch": 7.301369863013699, "grad_norm": 3202.300537109375, "learning_rate": 1.4522058823529414e-05, "loss": 0.0157, "step": 1066 }, { "epoch": 7.308219178082192, "grad_norm": 5481.90771484375, "learning_rate": 1.4485294117647061e-05, "loss": 0.0261, "step": 1067 }, { "epoch": 7.315068493150685, "grad_norm": 5392.1396484375, "learning_rate": 1.4448529411764705e-05, "loss": 0.0287, "step": 1068 }, { "epoch": 7.321917808219178, "grad_norm": 5734.1162109375, "learning_rate": 1.4411764705882352e-05, "loss": 0.0192, "step": 1069 }, { "epoch": 7.328767123287671, "grad_norm": 3820.251220703125, "learning_rate": 1.4374999999999999e-05, "loss": 0.0186, "step": 1070 }, { "epoch": 7.335616438356165, "grad_norm": 7598.3173828125, "learning_rate": 1.4338235294117647e-05, "loss": 0.0295, "step": 1071 }, { "epoch": 7.342465753424658, "grad_norm": 6839.001953125, "learning_rate": 1.4301470588235295e-05, "loss": 0.0245, "step": 1072 }, { "epoch": 7.3493150684931505, "grad_norm": 6975.84326171875, "learning_rate": 1.4264705882352942e-05, "loss": 0.0226, "step": 1073 }, { "epoch": 7.3561643835616435, "grad_norm": 5108.74072265625, "learning_rate": 1.4227941176470589e-05, "loss": 0.02, "step": 1074 }, { "epoch": 7.363013698630137, "grad_norm": 3214.761474609375, "learning_rate": 1.4191176470588236e-05, "loss": 0.0185, "step": 1075 }, { "epoch": 7.36986301369863, "grad_norm": 5543.298828125, "learning_rate": 1.4154411764705883e-05, "loss": 0.0159, "step": 1076 }, { "epoch": 7.376712328767123, "grad_norm": 4493.65283203125, "learning_rate": 1.411764705882353e-05, "loss": 0.018, "step": 1077 }, { "epoch": 7.383561643835616, "grad_norm": 9446.65234375, "learning_rate": 1.4080882352941177e-05, "loss": 0.0293, "step": 1078 }, { "epoch": 7.390410958904109, "grad_norm": 3662.65234375, "learning_rate": 1.4044117647058824e-05, "loss": 0.0151, "step": 1079 }, { "epoch": 7.397260273972603, "grad_norm": 7986.0029296875, "learning_rate": 1.4007352941176471e-05, "loss": 0.0278, "step": 1080 }, { "epoch": 7.404109589041096, "grad_norm": 8410.220703125, "learning_rate": 1.3970588235294118e-05, "loss": 0.0371, "step": 1081 }, { "epoch": 7.410958904109589, "grad_norm": 9289.373046875, "learning_rate": 1.3933823529411765e-05, "loss": 0.0161, "step": 1082 }, { "epoch": 7.417808219178082, "grad_norm": 7955.26904296875, "learning_rate": 1.3897058823529412e-05, "loss": 0.0242, "step": 1083 }, { "epoch": 7.424657534246576, "grad_norm": 5415.4521484375, "learning_rate": 1.3860294117647061e-05, "loss": 0.0239, "step": 1084 }, { "epoch": 7.431506849315069, "grad_norm": 17940.53125, "learning_rate": 1.3823529411764708e-05, "loss": 0.0307, "step": 1085 }, { "epoch": 7.438356164383562, "grad_norm": 4370.40283203125, "learning_rate": 1.3786764705882355e-05, "loss": 0.0204, "step": 1086 }, { "epoch": 7.445205479452055, "grad_norm": 5505.19189453125, "learning_rate": 1.3750000000000002e-05, "loss": 0.0258, "step": 1087 }, { "epoch": 7.4520547945205475, "grad_norm": 3706.83837890625, "learning_rate": 1.371323529411765e-05, "loss": 0.0173, "step": 1088 }, { "epoch": 7.458904109589041, "grad_norm": 9215.1416015625, "learning_rate": 1.3676470588235296e-05, "loss": 0.0244, "step": 1089 }, { "epoch": 7.465753424657534, "grad_norm": 3778.92919921875, "learning_rate": 1.363970588235294e-05, "loss": 0.0117, "step": 1090 }, { "epoch": 7.472602739726027, "grad_norm": 4707.736328125, "learning_rate": 1.3602941176470587e-05, "loss": 0.021, "step": 1091 }, { "epoch": 7.47945205479452, "grad_norm": 5125.04052734375, "learning_rate": 1.3566176470588234e-05, "loss": 0.0285, "step": 1092 }, { "epoch": 7.486301369863014, "grad_norm": 6182.1162109375, "learning_rate": 1.3529411764705883e-05, "loss": 0.0194, "step": 1093 }, { "epoch": 7.493150684931507, "grad_norm": 7423.04150390625, "learning_rate": 1.349264705882353e-05, "loss": 0.0232, "step": 1094 }, { "epoch": 7.5, "grad_norm": 5135.29931640625, "learning_rate": 1.3455882352941177e-05, "loss": 0.0258, "step": 1095 }, { "epoch": 7.506849315068493, "grad_norm": 8011.9599609375, "learning_rate": 1.3419117647058824e-05, "loss": 0.0254, "step": 1096 }, { "epoch": 7.513698630136986, "grad_norm": 9411.025390625, "learning_rate": 1.3382352941176471e-05, "loss": 0.0213, "step": 1097 }, { "epoch": 7.52054794520548, "grad_norm": 7190.63818359375, "learning_rate": 1.3345588235294118e-05, "loss": 0.0276, "step": 1098 }, { "epoch": 7.527397260273973, "grad_norm": 10174.173828125, "learning_rate": 1.3308823529411765e-05, "loss": 0.0229, "step": 1099 }, { "epoch": 7.534246575342466, "grad_norm": 8468.541015625, "learning_rate": 1.3272058823529412e-05, "loss": 0.0295, "step": 1100 }, { "epoch": 7.541095890410959, "grad_norm": 8242.1650390625, "learning_rate": 1.323529411764706e-05, "loss": 0.0241, "step": 1101 }, { "epoch": 7.5479452054794525, "grad_norm": 6180.65625, "learning_rate": 1.3198529411764706e-05, "loss": 0.0245, "step": 1102 }, { "epoch": 7.554794520547945, "grad_norm": 5051.427734375, "learning_rate": 1.3161764705882353e-05, "loss": 0.0214, "step": 1103 }, { "epoch": 7.561643835616438, "grad_norm": 5385.43994140625, "learning_rate": 1.3125e-05, "loss": 0.0271, "step": 1104 }, { "epoch": 7.568493150684931, "grad_norm": 5431.44091796875, "learning_rate": 1.3088235294117648e-05, "loss": 0.028, "step": 1105 }, { "epoch": 7.575342465753424, "grad_norm": 7911.646484375, "learning_rate": 1.3051470588235296e-05, "loss": 0.0301, "step": 1106 }, { "epoch": 7.582191780821918, "grad_norm": 6153.849609375, "learning_rate": 1.3014705882352943e-05, "loss": 0.0261, "step": 1107 }, { "epoch": 7.589041095890411, "grad_norm": 8045.6630859375, "learning_rate": 1.297794117647059e-05, "loss": 0.0276, "step": 1108 }, { "epoch": 7.595890410958904, "grad_norm": 7955.76123046875, "learning_rate": 1.2941176470588238e-05, "loss": 0.0226, "step": 1109 }, { "epoch": 7.602739726027397, "grad_norm": 2690.396240234375, "learning_rate": 1.2904411764705885e-05, "loss": 0.0137, "step": 1110 }, { "epoch": 7.609589041095891, "grad_norm": 8637.78125, "learning_rate": 1.2867647058823528e-05, "loss": 0.0326, "step": 1111 }, { "epoch": 7.616438356164384, "grad_norm": 6146.0302734375, "learning_rate": 1.2830882352941175e-05, "loss": 0.0278, "step": 1112 }, { "epoch": 7.623287671232877, "grad_norm": 6979.5107421875, "learning_rate": 1.2794117647058822e-05, "loss": 0.02, "step": 1113 }, { "epoch": 7.63013698630137, "grad_norm": 7011.9228515625, "learning_rate": 1.275735294117647e-05, "loss": 0.0248, "step": 1114 }, { "epoch": 7.636986301369863, "grad_norm": 6171.59375, "learning_rate": 1.2720588235294118e-05, "loss": 0.0209, "step": 1115 }, { "epoch": 7.6438356164383565, "grad_norm": 3266.54638671875, "learning_rate": 1.2683823529411765e-05, "loss": 0.0192, "step": 1116 }, { "epoch": 7.6506849315068495, "grad_norm": 4120.10009765625, "learning_rate": 1.2647058823529412e-05, "loss": 0.0164, "step": 1117 }, { "epoch": 7.657534246575342, "grad_norm": 4882.458984375, "learning_rate": 1.261029411764706e-05, "loss": 0.025, "step": 1118 }, { "epoch": 7.664383561643835, "grad_norm": 5537.4130859375, "learning_rate": 1.2573529411764706e-05, "loss": 0.0204, "step": 1119 }, { "epoch": 7.671232876712329, "grad_norm": 6052.7041015625, "learning_rate": 1.2536764705882354e-05, "loss": 0.0262, "step": 1120 }, { "epoch": 7.678082191780822, "grad_norm": 4371.041015625, "learning_rate": 1.25e-05, "loss": 0.0163, "step": 1121 }, { "epoch": 7.684931506849315, "grad_norm": 7362.3193359375, "learning_rate": 1.2463235294117648e-05, "loss": 0.0218, "step": 1122 }, { "epoch": 7.691780821917808, "grad_norm": 6064.75244140625, "learning_rate": 1.2426470588235295e-05, "loss": 0.0341, "step": 1123 }, { "epoch": 7.698630136986301, "grad_norm": 5288.2998046875, "learning_rate": 1.2389705882352942e-05, "loss": 0.023, "step": 1124 }, { "epoch": 7.705479452054795, "grad_norm": 12668.6416015625, "learning_rate": 1.2352941176470589e-05, "loss": 0.0216, "step": 1125 }, { "epoch": 7.712328767123288, "grad_norm": 3775.320556640625, "learning_rate": 1.2316176470588236e-05, "loss": 0.0149, "step": 1126 }, { "epoch": 7.719178082191781, "grad_norm": 6200.82421875, "learning_rate": 1.2279411764705883e-05, "loss": 0.0246, "step": 1127 }, { "epoch": 7.726027397260274, "grad_norm": 5355.66259765625, "learning_rate": 1.224264705882353e-05, "loss": 0.0275, "step": 1128 }, { "epoch": 7.732876712328768, "grad_norm": 4179.326171875, "learning_rate": 1.2205882352941177e-05, "loss": 0.0159, "step": 1129 }, { "epoch": 7.739726027397261, "grad_norm": 5568.27978515625, "learning_rate": 1.2169117647058824e-05, "loss": 0.0234, "step": 1130 }, { "epoch": 7.7465753424657535, "grad_norm": 6037.5751953125, "learning_rate": 1.2132352941176471e-05, "loss": 0.0237, "step": 1131 }, { "epoch": 7.7534246575342465, "grad_norm": 4121.2890625, "learning_rate": 1.2095588235294118e-05, "loss": 0.0215, "step": 1132 }, { "epoch": 7.760273972602739, "grad_norm": 3811.6767578125, "learning_rate": 1.2058823529411765e-05, "loss": 0.0199, "step": 1133 }, { "epoch": 7.767123287671232, "grad_norm": 4657.64501953125, "learning_rate": 1.2022058823529412e-05, "loss": 0.0199, "step": 1134 }, { "epoch": 7.773972602739726, "grad_norm": 6376.9873046875, "learning_rate": 1.198529411764706e-05, "loss": 0.017, "step": 1135 }, { "epoch": 7.780821917808219, "grad_norm": 4508.6904296875, "learning_rate": 1.1948529411764707e-05, "loss": 0.0144, "step": 1136 }, { "epoch": 7.787671232876712, "grad_norm": 7256.7216796875, "learning_rate": 1.1911764705882354e-05, "loss": 0.026, "step": 1137 }, { "epoch": 7.794520547945205, "grad_norm": 4538.4345703125, "learning_rate": 1.1875e-05, "loss": 0.0199, "step": 1138 }, { "epoch": 7.801369863013699, "grad_norm": 4147.4970703125, "learning_rate": 1.1838235294117648e-05, "loss": 0.016, "step": 1139 }, { "epoch": 7.808219178082192, "grad_norm": 4753.19189453125, "learning_rate": 1.1801470588235295e-05, "loss": 0.024, "step": 1140 }, { "epoch": 7.815068493150685, "grad_norm": 3071.251953125, "learning_rate": 1.1764705882352942e-05, "loss": 0.0161, "step": 1141 }, { "epoch": 7.821917808219178, "grad_norm": 8314.15625, "learning_rate": 1.1727941176470589e-05, "loss": 0.0289, "step": 1142 }, { "epoch": 7.828767123287671, "grad_norm": 4836.9970703125, "learning_rate": 1.1691176470588236e-05, "loss": 0.0219, "step": 1143 }, { "epoch": 7.835616438356165, "grad_norm": 5740.61083984375, "learning_rate": 1.1654411764705883e-05, "loss": 0.0259, "step": 1144 }, { "epoch": 7.842465753424658, "grad_norm": 7830.9345703125, "learning_rate": 1.161764705882353e-05, "loss": 0.0323, "step": 1145 }, { "epoch": 7.8493150684931505, "grad_norm": 5039.26416015625, "learning_rate": 1.1580882352941177e-05, "loss": 0.0221, "step": 1146 }, { "epoch": 7.8561643835616435, "grad_norm": 4110.4462890625, "learning_rate": 1.1544117647058824e-05, "loss": 0.022, "step": 1147 }, { "epoch": 7.863013698630137, "grad_norm": 3494.761962890625, "learning_rate": 1.1507352941176471e-05, "loss": 0.0134, "step": 1148 }, { "epoch": 7.86986301369863, "grad_norm": 4563.998046875, "learning_rate": 1.1470588235294118e-05, "loss": 0.0186, "step": 1149 }, { "epoch": 7.876712328767123, "grad_norm": 9455.634765625, "learning_rate": 1.1433823529411765e-05, "loss": 0.0254, "step": 1150 }, { "epoch": 7.883561643835616, "grad_norm": 6145.96875, "learning_rate": 1.1397058823529412e-05, "loss": 0.0239, "step": 1151 }, { "epoch": 7.890410958904109, "grad_norm": 4412.74853515625, "learning_rate": 1.136029411764706e-05, "loss": 0.0212, "step": 1152 }, { "epoch": 7.897260273972603, "grad_norm": 6575.05224609375, "learning_rate": 1.1323529411764707e-05, "loss": 0.0234, "step": 1153 }, { "epoch": 7.904109589041096, "grad_norm": 3551.0859375, "learning_rate": 1.1286764705882354e-05, "loss": 0.0175, "step": 1154 }, { "epoch": 7.910958904109589, "grad_norm": 3847.32568359375, "learning_rate": 1.125e-05, "loss": 0.0162, "step": 1155 }, { "epoch": 7.917808219178082, "grad_norm": 5356.28076171875, "learning_rate": 1.1213235294117648e-05, "loss": 0.0239, "step": 1156 }, { "epoch": 7.924657534246576, "grad_norm": 5749.80419921875, "learning_rate": 1.1176470588235295e-05, "loss": 0.0209, "step": 1157 }, { "epoch": 7.931506849315069, "grad_norm": 9904.0556640625, "learning_rate": 1.1139705882352942e-05, "loss": 0.0273, "step": 1158 }, { "epoch": 7.938356164383562, "grad_norm": 5773.90771484375, "learning_rate": 1.1102941176470589e-05, "loss": 0.0252, "step": 1159 }, { "epoch": 7.945205479452055, "grad_norm": 4829.7509765625, "learning_rate": 1.1066176470588236e-05, "loss": 0.0279, "step": 1160 }, { "epoch": 7.9520547945205475, "grad_norm": 5096.05517578125, "learning_rate": 1.1029411764705883e-05, "loss": 0.0201, "step": 1161 }, { "epoch": 7.958904109589041, "grad_norm": 6907.58349609375, "learning_rate": 1.099264705882353e-05, "loss": 0.0296, "step": 1162 }, { "epoch": 7.965753424657534, "grad_norm": 4351.9736328125, "learning_rate": 1.0955882352941177e-05, "loss": 0.0127, "step": 1163 }, { "epoch": 7.972602739726027, "grad_norm": 8447.6845703125, "learning_rate": 1.0919117647058824e-05, "loss": 0.0248, "step": 1164 }, { "epoch": 7.97945205479452, "grad_norm": 6737.4912109375, "learning_rate": 1.0882352941176471e-05, "loss": 0.0234, "step": 1165 }, { "epoch": 7.986301369863014, "grad_norm": 4142.8037109375, "learning_rate": 1.0845588235294118e-05, "loss": 0.0178, "step": 1166 }, { "epoch": 7.993150684931507, "grad_norm": 11261.896484375, "learning_rate": 1.0808823529411765e-05, "loss": 0.0275, "step": 1167 }, { "epoch": 8.0, "grad_norm": 7062.54736328125, "learning_rate": 1.0772058823529413e-05, "loss": 0.022, "step": 1168 }, { "epoch": 8.0, "eval_f1_macro": 0.6850242841979528, "eval_f1_micro": 0.8450106157112527, "eval_loss": 0.03247131034731865, "eval_precision": 0.8864142538975501, "eval_recall": 0.8073022312373225, "eval_runtime": 1.0823, "eval_samples_per_second": 359.424, "eval_steps_per_second": 15.707, "step": 1168 }, { "epoch": 8.006849315068493, "grad_norm": 4541.85302734375, "learning_rate": 1.0735294117647058e-05, "loss": 0.0154, "step": 1169 }, { "epoch": 8.013698630136986, "grad_norm": 9183.7421875, "learning_rate": 1.0698529411764707e-05, "loss": 0.0285, "step": 1170 }, { "epoch": 8.020547945205479, "grad_norm": 4472.54931640625, "learning_rate": 1.0661764705882354e-05, "loss": 0.0199, "step": 1171 }, { "epoch": 8.027397260273972, "grad_norm": 5322.875, "learning_rate": 1.0625e-05, "loss": 0.0211, "step": 1172 }, { "epoch": 8.034246575342467, "grad_norm": 5346.693359375, "learning_rate": 1.0588235294117648e-05, "loss": 0.0178, "step": 1173 }, { "epoch": 8.04109589041096, "grad_norm": 7249.31201171875, "learning_rate": 1.0551470588235295e-05, "loss": 0.0224, "step": 1174 }, { "epoch": 8.047945205479452, "grad_norm": 4754.71240234375, "learning_rate": 1.0514705882352942e-05, "loss": 0.0272, "step": 1175 }, { "epoch": 8.054794520547945, "grad_norm": 5397.96142578125, "learning_rate": 1.0477941176470589e-05, "loss": 0.0203, "step": 1176 }, { "epoch": 8.061643835616438, "grad_norm": 3804.02294921875, "learning_rate": 1.0441176470588236e-05, "loss": 0.0126, "step": 1177 }, { "epoch": 8.068493150684931, "grad_norm": 7731.5244140625, "learning_rate": 1.0404411764705883e-05, "loss": 0.0223, "step": 1178 }, { "epoch": 8.075342465753424, "grad_norm": 9881.583984375, "learning_rate": 1.036764705882353e-05, "loss": 0.0234, "step": 1179 }, { "epoch": 8.082191780821917, "grad_norm": 6742.40234375, "learning_rate": 1.0330882352941176e-05, "loss": 0.0163, "step": 1180 }, { "epoch": 8.08904109589041, "grad_norm": 6253.18017578125, "learning_rate": 1.0294117647058824e-05, "loss": 0.0246, "step": 1181 }, { "epoch": 8.095890410958905, "grad_norm": 7844.349609375, "learning_rate": 1.0257352941176471e-05, "loss": 0.029, "step": 1182 }, { "epoch": 8.102739726027398, "grad_norm": 2412.95654296875, "learning_rate": 1.0220588235294118e-05, "loss": 0.0152, "step": 1183 }, { "epoch": 8.10958904109589, "grad_norm": 4480.3515625, "learning_rate": 1.0183823529411766e-05, "loss": 0.0123, "step": 1184 }, { "epoch": 8.116438356164384, "grad_norm": 5771.64697265625, "learning_rate": 1.0147058823529413e-05, "loss": 0.0234, "step": 1185 }, { "epoch": 8.123287671232877, "grad_norm": 7140.0341796875, "learning_rate": 1.011029411764706e-05, "loss": 0.0289, "step": 1186 }, { "epoch": 8.13013698630137, "grad_norm": 3353.077880859375, "learning_rate": 1.0073529411764707e-05, "loss": 0.0167, "step": 1187 }, { "epoch": 8.136986301369863, "grad_norm": 4797.7041015625, "learning_rate": 1.0036764705882354e-05, "loss": 0.0174, "step": 1188 }, { "epoch": 8.143835616438356, "grad_norm": 5935.8974609375, "learning_rate": 1e-05, "loss": 0.0224, "step": 1189 }, { "epoch": 8.150684931506849, "grad_norm": 5436.45166015625, "learning_rate": 9.963235294117648e-06, "loss": 0.0191, "step": 1190 }, { "epoch": 8.157534246575343, "grad_norm": 5102.3447265625, "learning_rate": 9.926470588235293e-06, "loss": 0.0198, "step": 1191 }, { "epoch": 8.164383561643836, "grad_norm": 3549.24072265625, "learning_rate": 9.889705882352942e-06, "loss": 0.0144, "step": 1192 }, { "epoch": 8.17123287671233, "grad_norm": 8458.4609375, "learning_rate": 9.852941176470589e-06, "loss": 0.0203, "step": 1193 }, { "epoch": 8.178082191780822, "grad_norm": 5743.81103515625, "learning_rate": 9.816176470588236e-06, "loss": 0.0263, "step": 1194 }, { "epoch": 8.184931506849315, "grad_norm": 7113.33154296875, "learning_rate": 9.779411764705883e-06, "loss": 0.0298, "step": 1195 }, { "epoch": 8.191780821917808, "grad_norm": 7438.54931640625, "learning_rate": 9.74264705882353e-06, "loss": 0.0324, "step": 1196 }, { "epoch": 8.198630136986301, "grad_norm": 5607.13037109375, "learning_rate": 9.705882352941177e-06, "loss": 0.0218, "step": 1197 }, { "epoch": 8.205479452054794, "grad_norm": 5714.34521484375, "learning_rate": 9.669117647058824e-06, "loss": 0.0172, "step": 1198 }, { "epoch": 8.212328767123287, "grad_norm": 5645.89990234375, "learning_rate": 9.632352941176471e-06, "loss": 0.022, "step": 1199 }, { "epoch": 8.219178082191782, "grad_norm": 8813.728515625, "learning_rate": 9.595588235294119e-06, "loss": 0.0273, "step": 1200 }, { "epoch": 8.226027397260275, "grad_norm": 7545.21240234375, "learning_rate": 9.558823529411764e-06, "loss": 0.0342, "step": 1201 }, { "epoch": 8.232876712328768, "grad_norm": 6159.37939453125, "learning_rate": 9.522058823529411e-06, "loss": 0.0304, "step": 1202 }, { "epoch": 8.23972602739726, "grad_norm": 6265.50439453125, "learning_rate": 9.48529411764706e-06, "loss": 0.0247, "step": 1203 }, { "epoch": 8.246575342465754, "grad_norm": 4664.033203125, "learning_rate": 9.448529411764707e-06, "loss": 0.0177, "step": 1204 }, { "epoch": 8.253424657534246, "grad_norm": 4533.64453125, "learning_rate": 9.411764705882354e-06, "loss": 0.0205, "step": 1205 }, { "epoch": 8.26027397260274, "grad_norm": 4588.54052734375, "learning_rate": 9.375000000000001e-06, "loss": 0.0177, "step": 1206 }, { "epoch": 8.267123287671232, "grad_norm": 5491.21826171875, "learning_rate": 9.338235294117648e-06, "loss": 0.0292, "step": 1207 }, { "epoch": 8.273972602739725, "grad_norm": 3524.196533203125, "learning_rate": 9.301470588235295e-06, "loss": 0.017, "step": 1208 }, { "epoch": 8.280821917808218, "grad_norm": 5426.9091796875, "learning_rate": 9.264705882352942e-06, "loss": 0.0129, "step": 1209 }, { "epoch": 8.287671232876713, "grad_norm": 4440.92041015625, "learning_rate": 9.227941176470589e-06, "loss": 0.0191, "step": 1210 }, { "epoch": 8.294520547945206, "grad_norm": 3849.89599609375, "learning_rate": 9.191176470588236e-06, "loss": 0.0174, "step": 1211 }, { "epoch": 8.301369863013699, "grad_norm": 3148.7900390625, "learning_rate": 9.154411764705882e-06, "loss": 0.0203, "step": 1212 }, { "epoch": 8.308219178082192, "grad_norm": 6796.30029296875, "learning_rate": 9.117647058823529e-06, "loss": 0.0229, "step": 1213 }, { "epoch": 8.315068493150685, "grad_norm": 6361.79541015625, "learning_rate": 9.080882352941177e-06, "loss": 0.0212, "step": 1214 }, { "epoch": 8.321917808219178, "grad_norm": 4931.10400390625, "learning_rate": 9.044117647058824e-06, "loss": 0.0176, "step": 1215 }, { "epoch": 8.32876712328767, "grad_norm": 5525.39208984375, "learning_rate": 9.007352941176471e-06, "loss": 0.0256, "step": 1216 }, { "epoch": 8.335616438356164, "grad_norm": 6054.22412109375, "learning_rate": 8.970588235294119e-06, "loss": 0.0238, "step": 1217 }, { "epoch": 8.342465753424657, "grad_norm": 6394.05908203125, "learning_rate": 8.933823529411766e-06, "loss": 0.0219, "step": 1218 }, { "epoch": 8.349315068493151, "grad_norm": 6148.7470703125, "learning_rate": 8.897058823529413e-06, "loss": 0.0189, "step": 1219 }, { "epoch": 8.356164383561644, "grad_norm": 5380.94677734375, "learning_rate": 8.86029411764706e-06, "loss": 0.0163, "step": 1220 }, { "epoch": 8.363013698630137, "grad_norm": 5119.18115234375, "learning_rate": 8.823529411764707e-06, "loss": 0.0205, "step": 1221 }, { "epoch": 8.36986301369863, "grad_norm": 5724.4296875, "learning_rate": 8.786764705882352e-06, "loss": 0.0204, "step": 1222 }, { "epoch": 8.376712328767123, "grad_norm": 5172.21630859375, "learning_rate": 8.75e-06, "loss": 0.0153, "step": 1223 }, { "epoch": 8.383561643835616, "grad_norm": 3985.71728515625, "learning_rate": 8.713235294117646e-06, "loss": 0.0186, "step": 1224 }, { "epoch": 8.39041095890411, "grad_norm": 5415.1044921875, "learning_rate": 8.676470588235295e-06, "loss": 0.0154, "step": 1225 }, { "epoch": 8.397260273972602, "grad_norm": 6348.25244140625, "learning_rate": 8.639705882352942e-06, "loss": 0.0283, "step": 1226 }, { "epoch": 8.404109589041095, "grad_norm": 7106.29052734375, "learning_rate": 8.60294117647059e-06, "loss": 0.0221, "step": 1227 }, { "epoch": 8.41095890410959, "grad_norm": 6441.85986328125, "learning_rate": 8.566176470588236e-06, "loss": 0.0137, "step": 1228 }, { "epoch": 8.417808219178083, "grad_norm": 6555.59375, "learning_rate": 8.529411764705883e-06, "loss": 0.0303, "step": 1229 }, { "epoch": 8.424657534246576, "grad_norm": 4977.1435546875, "learning_rate": 8.49264705882353e-06, "loss": 0.0169, "step": 1230 }, { "epoch": 8.431506849315069, "grad_norm": 4084.87890625, "learning_rate": 8.455882352941177e-06, "loss": 0.0214, "step": 1231 }, { "epoch": 8.438356164383562, "grad_norm": 3497.677490234375, "learning_rate": 8.419117647058824e-06, "loss": 0.017, "step": 1232 }, { "epoch": 8.445205479452055, "grad_norm": 6128.38720703125, "learning_rate": 8.38235294117647e-06, "loss": 0.0228, "step": 1233 }, { "epoch": 8.452054794520548, "grad_norm": 3884.683837890625, "learning_rate": 8.345588235294117e-06, "loss": 0.0233, "step": 1234 }, { "epoch": 8.45890410958904, "grad_norm": 4644.84228515625, "learning_rate": 8.308823529411764e-06, "loss": 0.0221, "step": 1235 }, { "epoch": 8.465753424657533, "grad_norm": 5247.68505859375, "learning_rate": 8.272058823529413e-06, "loss": 0.0241, "step": 1236 }, { "epoch": 8.472602739726028, "grad_norm": 3386.068359375, "learning_rate": 8.23529411764706e-06, "loss": 0.0158, "step": 1237 }, { "epoch": 8.479452054794521, "grad_norm": 5475.67138671875, "learning_rate": 8.198529411764707e-06, "loss": 0.0176, "step": 1238 }, { "epoch": 8.486301369863014, "grad_norm": 2767.168212890625, "learning_rate": 8.161764705882354e-06, "loss": 0.0143, "step": 1239 }, { "epoch": 8.493150684931507, "grad_norm": 4987.00244140625, "learning_rate": 8.125000000000001e-06, "loss": 0.022, "step": 1240 }, { "epoch": 8.5, "grad_norm": 6273.91943359375, "learning_rate": 8.088235294117648e-06, "loss": 0.0236, "step": 1241 }, { "epoch": 8.506849315068493, "grad_norm": 5251.60791015625, "learning_rate": 8.051470588235295e-06, "loss": 0.0176, "step": 1242 }, { "epoch": 8.513698630136986, "grad_norm": 4033.757080078125, "learning_rate": 8.014705882352942e-06, "loss": 0.0164, "step": 1243 }, { "epoch": 8.520547945205479, "grad_norm": 5680.2890625, "learning_rate": 7.977941176470588e-06, "loss": 0.0211, "step": 1244 }, { "epoch": 8.527397260273972, "grad_norm": 4952.94287109375, "learning_rate": 7.941176470588235e-06, "loss": 0.0216, "step": 1245 }, { "epoch": 8.534246575342467, "grad_norm": 4097.16455078125, "learning_rate": 7.904411764705882e-06, "loss": 0.0142, "step": 1246 }, { "epoch": 8.54109589041096, "grad_norm": 7242.3408203125, "learning_rate": 7.86764705882353e-06, "loss": 0.0207, "step": 1247 }, { "epoch": 8.547945205479452, "grad_norm": 6621.06103515625, "learning_rate": 7.830882352941177e-06, "loss": 0.0238, "step": 1248 }, { "epoch": 8.554794520547945, "grad_norm": 4503.2353515625, "learning_rate": 7.794117647058825e-06, "loss": 0.0149, "step": 1249 }, { "epoch": 8.561643835616438, "grad_norm": 6996.91259765625, "learning_rate": 7.757352941176472e-06, "loss": 0.0228, "step": 1250 }, { "epoch": 8.568493150684931, "grad_norm": 5421.51025390625, "learning_rate": 7.720588235294119e-06, "loss": 0.0251, "step": 1251 }, { "epoch": 8.575342465753424, "grad_norm": 6914.9814453125, "learning_rate": 7.683823529411766e-06, "loss": 0.0279, "step": 1252 }, { "epoch": 8.582191780821917, "grad_norm": 3802.258544921875, "learning_rate": 7.647058823529413e-06, "loss": 0.0197, "step": 1253 }, { "epoch": 8.58904109589041, "grad_norm": 4331.6689453125, "learning_rate": 7.610294117647058e-06, "loss": 0.0169, "step": 1254 }, { "epoch": 8.595890410958905, "grad_norm": 3657.446533203125, "learning_rate": 7.573529411764706e-06, "loss": 0.0131, "step": 1255 }, { "epoch": 8.602739726027398, "grad_norm": 3816.567626953125, "learning_rate": 7.536764705882353e-06, "loss": 0.0223, "step": 1256 }, { "epoch": 8.60958904109589, "grad_norm": 2697.7734375, "learning_rate": 7.5e-06, "loss": 0.0143, "step": 1257 }, { "epoch": 8.616438356164384, "grad_norm": 5623.01953125, "learning_rate": 7.463235294117647e-06, "loss": 0.0292, "step": 1258 }, { "epoch": 8.623287671232877, "grad_norm": 4039.58935546875, "learning_rate": 7.426470588235294e-06, "loss": 0.0207, "step": 1259 }, { "epoch": 8.63013698630137, "grad_norm": 4517.98583984375, "learning_rate": 7.389705882352941e-06, "loss": 0.0217, "step": 1260 }, { "epoch": 8.636986301369863, "grad_norm": 4189.509765625, "learning_rate": 7.3529411764705884e-06, "loss": 0.0228, "step": 1261 }, { "epoch": 8.643835616438356, "grad_norm": 3803.249755859375, "learning_rate": 7.316176470588236e-06, "loss": 0.0179, "step": 1262 }, { "epoch": 8.650684931506849, "grad_norm": 4503.64794921875, "learning_rate": 7.279411764705883e-06, "loss": 0.0195, "step": 1263 }, { "epoch": 8.657534246575342, "grad_norm": 4195.49462890625, "learning_rate": 7.2426470588235305e-06, "loss": 0.0224, "step": 1264 }, { "epoch": 8.664383561643836, "grad_norm": 13399.82421875, "learning_rate": 7.205882352941176e-06, "loss": 0.0295, "step": 1265 }, { "epoch": 8.67123287671233, "grad_norm": 11992.556640625, "learning_rate": 7.169117647058824e-06, "loss": 0.0288, "step": 1266 }, { "epoch": 8.678082191780822, "grad_norm": 16663.88671875, "learning_rate": 7.132352941176471e-06, "loss": 0.0362, "step": 1267 }, { "epoch": 8.684931506849315, "grad_norm": 6070.83447265625, "learning_rate": 7.095588235294118e-06, "loss": 0.0197, "step": 1268 }, { "epoch": 8.691780821917808, "grad_norm": 5923.22021484375, "learning_rate": 7.058823529411765e-06, "loss": 0.0279, "step": 1269 }, { "epoch": 8.698630136986301, "grad_norm": 3253.744384765625, "learning_rate": 7.022058823529412e-06, "loss": 0.0155, "step": 1270 }, { "epoch": 8.705479452054794, "grad_norm": 4064.458984375, "learning_rate": 6.985294117647059e-06, "loss": 0.0211, "step": 1271 }, { "epoch": 8.712328767123287, "grad_norm": 4946.61328125, "learning_rate": 6.948529411764706e-06, "loss": 0.0158, "step": 1272 }, { "epoch": 8.719178082191782, "grad_norm": 4827.43017578125, "learning_rate": 6.911764705882354e-06, "loss": 0.0139, "step": 1273 }, { "epoch": 8.726027397260275, "grad_norm": 4277.22265625, "learning_rate": 6.875000000000001e-06, "loss": 0.0184, "step": 1274 }, { "epoch": 8.732876712328768, "grad_norm": 6874.42919921875, "learning_rate": 6.838235294117648e-06, "loss": 0.026, "step": 1275 }, { "epoch": 8.73972602739726, "grad_norm": 5215.197265625, "learning_rate": 6.8014705882352935e-06, "loss": 0.019, "step": 1276 }, { "epoch": 8.746575342465754, "grad_norm": 5542.5087890625, "learning_rate": 6.7647058823529414e-06, "loss": 0.0213, "step": 1277 }, { "epoch": 8.753424657534246, "grad_norm": 3589.567138671875, "learning_rate": 6.7279411764705885e-06, "loss": 0.0181, "step": 1278 }, { "epoch": 8.76027397260274, "grad_norm": 6478.78955078125, "learning_rate": 6.6911764705882356e-06, "loss": 0.0211, "step": 1279 }, { "epoch": 8.767123287671232, "grad_norm": 5025.642578125, "learning_rate": 6.654411764705883e-06, "loss": 0.0193, "step": 1280 }, { "epoch": 8.773972602739725, "grad_norm": 2352.10791015625, "learning_rate": 6.61764705882353e-06, "loss": 0.0129, "step": 1281 }, { "epoch": 8.780821917808218, "grad_norm": 3512.092041015625, "learning_rate": 6.580882352941177e-06, "loss": 0.0123, "step": 1282 }, { "epoch": 8.787671232876713, "grad_norm": 3372.852294921875, "learning_rate": 6.544117647058824e-06, "loss": 0.0146, "step": 1283 }, { "epoch": 8.794520547945206, "grad_norm": 3868.18359375, "learning_rate": 6.507352941176472e-06, "loss": 0.0182, "step": 1284 }, { "epoch": 8.801369863013699, "grad_norm": 4565.2353515625, "learning_rate": 6.470588235294119e-06, "loss": 0.0202, "step": 1285 }, { "epoch": 8.808219178082192, "grad_norm": 5022.525390625, "learning_rate": 6.433823529411764e-06, "loss": 0.0178, "step": 1286 }, { "epoch": 8.815068493150685, "grad_norm": 8207.416015625, "learning_rate": 6.397058823529411e-06, "loss": 0.0267, "step": 1287 }, { "epoch": 8.821917808219178, "grad_norm": 5107.724609375, "learning_rate": 6.360294117647059e-06, "loss": 0.0183, "step": 1288 }, { "epoch": 8.82876712328767, "grad_norm": 5814.7861328125, "learning_rate": 6.323529411764706e-06, "loss": 0.0198, "step": 1289 }, { "epoch": 8.835616438356164, "grad_norm": 4342.291015625, "learning_rate": 6.286764705882353e-06, "loss": 0.0252, "step": 1290 }, { "epoch": 8.842465753424658, "grad_norm": 6978.3056640625, "learning_rate": 6.25e-06, "loss": 0.0227, "step": 1291 }, { "epoch": 8.849315068493151, "grad_norm": 3265.183349609375, "learning_rate": 6.213235294117647e-06, "loss": 0.0163, "step": 1292 }, { "epoch": 8.856164383561644, "grad_norm": 8181.576171875, "learning_rate": 6.1764705882352944e-06, "loss": 0.0314, "step": 1293 }, { "epoch": 8.863013698630137, "grad_norm": 5901.658203125, "learning_rate": 6.1397058823529415e-06, "loss": 0.0158, "step": 1294 }, { "epoch": 8.86986301369863, "grad_norm": 10069.875, "learning_rate": 6.1029411764705885e-06, "loss": 0.0245, "step": 1295 }, { "epoch": 8.876712328767123, "grad_norm": 4953.12060546875, "learning_rate": 6.066176470588236e-06, "loss": 0.019, "step": 1296 }, { "epoch": 8.883561643835616, "grad_norm": 10164.6162109375, "learning_rate": 6.029411764705883e-06, "loss": 0.0238, "step": 1297 }, { "epoch": 8.89041095890411, "grad_norm": 4848.7431640625, "learning_rate": 5.99264705882353e-06, "loss": 0.0164, "step": 1298 }, { "epoch": 8.897260273972602, "grad_norm": 4710.1669921875, "learning_rate": 5.955882352941177e-06, "loss": 0.0244, "step": 1299 }, { "epoch": 8.904109589041095, "grad_norm": 5786.27001953125, "learning_rate": 5.919117647058824e-06, "loss": 0.0191, "step": 1300 }, { "epoch": 8.91095890410959, "grad_norm": 4429.71044921875, "learning_rate": 5.882352941176471e-06, "loss": 0.0193, "step": 1301 }, { "epoch": 8.917808219178083, "grad_norm": 6694.62548828125, "learning_rate": 5.845588235294118e-06, "loss": 0.0191, "step": 1302 }, { "epoch": 8.924657534246576, "grad_norm": 3201.27197265625, "learning_rate": 5.808823529411765e-06, "loss": 0.0146, "step": 1303 }, { "epoch": 8.931506849315069, "grad_norm": 4259.83447265625, "learning_rate": 5.772058823529412e-06, "loss": 0.0209, "step": 1304 }, { "epoch": 8.938356164383562, "grad_norm": 4127.8740234375, "learning_rate": 5.735294117647059e-06, "loss": 0.0173, "step": 1305 }, { "epoch": 8.945205479452055, "grad_norm": 3544.054443359375, "learning_rate": 5.698529411764706e-06, "loss": 0.0153, "step": 1306 }, { "epoch": 8.952054794520548, "grad_norm": 4324.02392578125, "learning_rate": 5.661764705882353e-06, "loss": 0.0162, "step": 1307 }, { "epoch": 8.95890410958904, "grad_norm": 5476.2919921875, "learning_rate": 5.625e-06, "loss": 0.0198, "step": 1308 }, { "epoch": 8.965753424657533, "grad_norm": 4598.50244140625, "learning_rate": 5.588235294117647e-06, "loss": 0.0158, "step": 1309 }, { "epoch": 8.972602739726028, "grad_norm": 2988.697021484375, "learning_rate": 5.5514705882352945e-06, "loss": 0.0136, "step": 1310 }, { "epoch": 8.979452054794521, "grad_norm": 4713.43505859375, "learning_rate": 5.5147058823529415e-06, "loss": 0.0217, "step": 1311 }, { "epoch": 8.986301369863014, "grad_norm": 4899.80078125, "learning_rate": 5.477941176470589e-06, "loss": 0.0193, "step": 1312 }, { "epoch": 8.993150684931507, "grad_norm": 6522.97119140625, "learning_rate": 5.441176470588236e-06, "loss": 0.0226, "step": 1313 }, { "epoch": 9.0, "grad_norm": 4301.0830078125, "learning_rate": 5.404411764705883e-06, "loss": 0.0158, "step": 1314 }, { "epoch": 9.0, "eval_f1_macro": 0.7310716253275542, "eval_f1_micro": 0.8553326293558606, "eval_loss": 0.030886737629771233, "eval_precision": 0.8920704845814978, "eval_recall": 0.821501014198783, "eval_runtime": 1.1092, "eval_samples_per_second": 350.694, "eval_steps_per_second": 15.326, "step": 1314 }, { "epoch": 9.006849315068493, "grad_norm": 4131.61767578125, "learning_rate": 5.367647058823529e-06, "loss": 0.0201, "step": 1315 }, { "epoch": 9.013698630136986, "grad_norm": 4817.69384765625, "learning_rate": 5.330882352941177e-06, "loss": 0.0125, "step": 1316 }, { "epoch": 9.020547945205479, "grad_norm": 5156.3935546875, "learning_rate": 5.294117647058824e-06, "loss": 0.0217, "step": 1317 }, { "epoch": 9.027397260273972, "grad_norm": 4541.52490234375, "learning_rate": 5.257352941176471e-06, "loss": 0.0185, "step": 1318 }, { "epoch": 9.034246575342467, "grad_norm": 3621.814453125, "learning_rate": 5.220588235294118e-06, "loss": 0.0185, "step": 1319 }, { "epoch": 9.04109589041096, "grad_norm": 4808.51123046875, "learning_rate": 5.183823529411765e-06, "loss": 0.0178, "step": 1320 }, { "epoch": 9.047945205479452, "grad_norm": 4504.28271484375, "learning_rate": 5.147058823529412e-06, "loss": 0.0176, "step": 1321 }, { "epoch": 9.054794520547945, "grad_norm": 5055.54443359375, "learning_rate": 5.110294117647059e-06, "loss": 0.0176, "step": 1322 }, { "epoch": 9.061643835616438, "grad_norm": 5574.9443359375, "learning_rate": 5.073529411764706e-06, "loss": 0.0253, "step": 1323 }, { "epoch": 9.068493150684931, "grad_norm": 3120.865966796875, "learning_rate": 5.036764705882353e-06, "loss": 0.0141, "step": 1324 }, { "epoch": 9.075342465753424, "grad_norm": 6690.48046875, "learning_rate": 5e-06, "loss": 0.0267, "step": 1325 }, { "epoch": 9.082191780821917, "grad_norm": 5650.14697265625, "learning_rate": 4.963235294117647e-06, "loss": 0.0181, "step": 1326 }, { "epoch": 9.08904109589041, "grad_norm": 4311.11767578125, "learning_rate": 4.9264705882352945e-06, "loss": 0.019, "step": 1327 }, { "epoch": 9.095890410958905, "grad_norm": 2790.629638671875, "learning_rate": 4.889705882352942e-06, "loss": 0.0143, "step": 1328 }, { "epoch": 9.102739726027398, "grad_norm": 3376.26708984375, "learning_rate": 4.852941176470589e-06, "loss": 0.0169, "step": 1329 }, { "epoch": 9.10958904109589, "grad_norm": 4595.39794921875, "learning_rate": 4.816176470588236e-06, "loss": 0.0211, "step": 1330 }, { "epoch": 9.116438356164384, "grad_norm": 3769.186767578125, "learning_rate": 4.779411764705882e-06, "loss": 0.018, "step": 1331 }, { "epoch": 9.123287671232877, "grad_norm": 5017.54443359375, "learning_rate": 4.74264705882353e-06, "loss": 0.0227, "step": 1332 }, { "epoch": 9.13013698630137, "grad_norm": 4475.94482421875, "learning_rate": 4.705882352941177e-06, "loss": 0.0202, "step": 1333 }, { "epoch": 9.136986301369863, "grad_norm": 4872.05029296875, "learning_rate": 4.669117647058824e-06, "loss": 0.023, "step": 1334 }, { "epoch": 9.143835616438356, "grad_norm": 4143.2958984375, "learning_rate": 4.632352941176471e-06, "loss": 0.014, "step": 1335 }, { "epoch": 9.150684931506849, "grad_norm": 7046.80078125, "learning_rate": 4.595588235294118e-06, "loss": 0.0205, "step": 1336 }, { "epoch": 9.157534246575343, "grad_norm": 3851.023193359375, "learning_rate": 4.558823529411764e-06, "loss": 0.0225, "step": 1337 }, { "epoch": 9.164383561643836, "grad_norm": 1987.7022705078125, "learning_rate": 4.522058823529412e-06, "loss": 0.0105, "step": 1338 }, { "epoch": 9.17123287671233, "grad_norm": 3028.40283203125, "learning_rate": 4.485294117647059e-06, "loss": 0.014, "step": 1339 }, { "epoch": 9.178082191780822, "grad_norm": 4880.58154296875, "learning_rate": 4.448529411764706e-06, "loss": 0.0177, "step": 1340 }, { "epoch": 9.184931506849315, "grad_norm": 4359.837890625, "learning_rate": 4.411764705882353e-06, "loss": 0.0178, "step": 1341 }, { "epoch": 9.191780821917808, "grad_norm": 3289.3701171875, "learning_rate": 4.375e-06, "loss": 0.0148, "step": 1342 }, { "epoch": 9.198630136986301, "grad_norm": 3635.2978515625, "learning_rate": 4.3382352941176475e-06, "loss": 0.0174, "step": 1343 }, { "epoch": 9.205479452054794, "grad_norm": 5401.73876953125, "learning_rate": 4.301470588235295e-06, "loss": 0.0163, "step": 1344 }, { "epoch": 9.212328767123287, "grad_norm": 7756.82958984375, "learning_rate": 4.264705882352942e-06, "loss": 0.0211, "step": 1345 }, { "epoch": 9.219178082191782, "grad_norm": 4389.8291015625, "learning_rate": 4.227941176470589e-06, "loss": 0.0175, "step": 1346 }, { "epoch": 9.226027397260275, "grad_norm": 5680.26220703125, "learning_rate": 4.191176470588235e-06, "loss": 0.0201, "step": 1347 }, { "epoch": 9.232876712328768, "grad_norm": 2196.7197265625, "learning_rate": 4.154411764705882e-06, "loss": 0.0134, "step": 1348 }, { "epoch": 9.23972602739726, "grad_norm": 4348.8408203125, "learning_rate": 4.11764705882353e-06, "loss": 0.0172, "step": 1349 }, { "epoch": 9.246575342465754, "grad_norm": 7189.74365234375, "learning_rate": 4.080882352941177e-06, "loss": 0.0164, "step": 1350 }, { "epoch": 9.253424657534246, "grad_norm": 4816.51318359375, "learning_rate": 4.044117647058824e-06, "loss": 0.023, "step": 1351 }, { "epoch": 9.26027397260274, "grad_norm": 2551.389892578125, "learning_rate": 4.007352941176471e-06, "loss": 0.016, "step": 1352 }, { "epoch": 9.267123287671232, "grad_norm": 5910.20654296875, "learning_rate": 3.970588235294117e-06, "loss": 0.022, "step": 1353 }, { "epoch": 9.273972602739725, "grad_norm": 5776.76953125, "learning_rate": 3.933823529411765e-06, "loss": 0.0201, "step": 1354 }, { "epoch": 9.280821917808218, "grad_norm": 4196.22998046875, "learning_rate": 3.897058823529412e-06, "loss": 0.0164, "step": 1355 }, { "epoch": 9.287671232876713, "grad_norm": 2319.540771484375, "learning_rate": 3.860294117647059e-06, "loss": 0.0096, "step": 1356 }, { "epoch": 9.294520547945206, "grad_norm": 7820.650390625, "learning_rate": 3.823529411764706e-06, "loss": 0.0186, "step": 1357 }, { "epoch": 9.301369863013699, "grad_norm": 5949.67138671875, "learning_rate": 3.786764705882353e-06, "loss": 0.026, "step": 1358 }, { "epoch": 9.308219178082192, "grad_norm": 9209.65234375, "learning_rate": 3.75e-06, "loss": 0.0134, "step": 1359 }, { "epoch": 9.315068493150685, "grad_norm": 5822.78662109375, "learning_rate": 3.713235294117647e-06, "loss": 0.0147, "step": 1360 }, { "epoch": 9.321917808219178, "grad_norm": 3885.351806640625, "learning_rate": 3.6764705882352942e-06, "loss": 0.0175, "step": 1361 }, { "epoch": 9.32876712328767, "grad_norm": 7455.01220703125, "learning_rate": 3.6397058823529417e-06, "loss": 0.0283, "step": 1362 }, { "epoch": 9.335616438356164, "grad_norm": 6660.6884765625, "learning_rate": 3.602941176470588e-06, "loss": 0.0228, "step": 1363 }, { "epoch": 9.342465753424657, "grad_norm": 4030.115966796875, "learning_rate": 3.5661764705882354e-06, "loss": 0.0186, "step": 1364 }, { "epoch": 9.349315068493151, "grad_norm": 4945.51220703125, "learning_rate": 3.5294117647058825e-06, "loss": 0.0181, "step": 1365 }, { "epoch": 9.356164383561644, "grad_norm": 4344.10107421875, "learning_rate": 3.4926470588235295e-06, "loss": 0.0144, "step": 1366 }, { "epoch": 9.363013698630137, "grad_norm": 4267.1171875, "learning_rate": 3.455882352941177e-06, "loss": 0.0245, "step": 1367 }, { "epoch": 9.36986301369863, "grad_norm": 5512.6201171875, "learning_rate": 3.419117647058824e-06, "loss": 0.0215, "step": 1368 }, { "epoch": 9.376712328767123, "grad_norm": 2833.68017578125, "learning_rate": 3.3823529411764707e-06, "loss": 0.0134, "step": 1369 }, { "epoch": 9.383561643835616, "grad_norm": 5259.572265625, "learning_rate": 3.3455882352941178e-06, "loss": 0.0189, "step": 1370 }, { "epoch": 9.39041095890411, "grad_norm": 9011.7509765625, "learning_rate": 3.308823529411765e-06, "loss": 0.021, "step": 1371 }, { "epoch": 9.397260273972602, "grad_norm": 3825.388671875, "learning_rate": 3.272058823529412e-06, "loss": 0.0224, "step": 1372 }, { "epoch": 9.404109589041095, "grad_norm": 3926.69287109375, "learning_rate": 3.2352941176470594e-06, "loss": 0.0206, "step": 1373 }, { "epoch": 9.41095890410959, "grad_norm": 6468.81298828125, "learning_rate": 3.1985294117647056e-06, "loss": 0.023, "step": 1374 }, { "epoch": 9.417808219178083, "grad_norm": 3494.99365234375, "learning_rate": 3.161764705882353e-06, "loss": 0.021, "step": 1375 }, { "epoch": 9.424657534246576, "grad_norm": 6147.67431640625, "learning_rate": 3.125e-06, "loss": 0.0172, "step": 1376 }, { "epoch": 9.431506849315069, "grad_norm": 7161.31982421875, "learning_rate": 3.0882352941176472e-06, "loss": 0.0166, "step": 1377 }, { "epoch": 9.438356164383562, "grad_norm": 7930.70068359375, "learning_rate": 3.0514705882352943e-06, "loss": 0.0322, "step": 1378 }, { "epoch": 9.445205479452055, "grad_norm": 7675.86279296875, "learning_rate": 3.0147058823529413e-06, "loss": 0.0226, "step": 1379 }, { "epoch": 9.452054794520548, "grad_norm": 7641.51416015625, "learning_rate": 2.9779411764705884e-06, "loss": 0.0278, "step": 1380 }, { "epoch": 9.45890410958904, "grad_norm": 2816.803955078125, "learning_rate": 2.9411764705882355e-06, "loss": 0.0126, "step": 1381 }, { "epoch": 9.465753424657533, "grad_norm": 7547.00634765625, "learning_rate": 2.9044117647058825e-06, "loss": 0.0194, "step": 1382 }, { "epoch": 9.472602739726028, "grad_norm": 4844.7587890625, "learning_rate": 2.8676470588235296e-06, "loss": 0.0185, "step": 1383 }, { "epoch": 9.479452054794521, "grad_norm": 7746.482421875, "learning_rate": 2.8308823529411766e-06, "loss": 0.0274, "step": 1384 }, { "epoch": 9.486301369863014, "grad_norm": 2736.326416015625, "learning_rate": 2.7941176470588237e-06, "loss": 0.0161, "step": 1385 }, { "epoch": 9.493150684931507, "grad_norm": 5613.677734375, "learning_rate": 2.7573529411764708e-06, "loss": 0.0144, "step": 1386 }, { "epoch": 9.5, "grad_norm": 5732.8203125, "learning_rate": 2.720588235294118e-06, "loss": 0.0226, "step": 1387 }, { "epoch": 9.506849315068493, "grad_norm": 4411.044921875, "learning_rate": 2.6838235294117645e-06, "loss": 0.0156, "step": 1388 }, { "epoch": 9.513698630136986, "grad_norm": 5625.70166015625, "learning_rate": 2.647058823529412e-06, "loss": 0.0219, "step": 1389 }, { "epoch": 9.520547945205479, "grad_norm": 3961.402099609375, "learning_rate": 2.610294117647059e-06, "loss": 0.0187, "step": 1390 }, { "epoch": 9.527397260273972, "grad_norm": 3743.966796875, "learning_rate": 2.573529411764706e-06, "loss": 0.0159, "step": 1391 }, { "epoch": 9.534246575342467, "grad_norm": 3553.27490234375, "learning_rate": 2.536764705882353e-06, "loss": 0.0149, "step": 1392 }, { "epoch": 9.54109589041096, "grad_norm": 3908.112548828125, "learning_rate": 2.5e-06, "loss": 0.0217, "step": 1393 }, { "epoch": 9.547945205479452, "grad_norm": 5654.05224609375, "learning_rate": 2.4632352941176473e-06, "loss": 0.0221, "step": 1394 }, { "epoch": 9.554794520547945, "grad_norm": 3011.832763671875, "learning_rate": 2.4264705882352943e-06, "loss": 0.0159, "step": 1395 }, { "epoch": 9.561643835616438, "grad_norm": 3529.498291015625, "learning_rate": 2.389705882352941e-06, "loss": 0.0099, "step": 1396 }, { "epoch": 9.568493150684931, "grad_norm": 7236.67529296875, "learning_rate": 2.3529411764705885e-06, "loss": 0.0151, "step": 1397 }, { "epoch": 9.575342465753424, "grad_norm": 3509.02490234375, "learning_rate": 2.3161764705882355e-06, "loss": 0.0179, "step": 1398 }, { "epoch": 9.582191780821917, "grad_norm": 4880.41259765625, "learning_rate": 2.279411764705882e-06, "loss": 0.0249, "step": 1399 }, { "epoch": 9.58904109589041, "grad_norm": 5625.2880859375, "learning_rate": 2.2426470588235296e-06, "loss": 0.0215, "step": 1400 }, { "epoch": 9.595890410958905, "grad_norm": 3121.973388671875, "learning_rate": 2.2058823529411767e-06, "loss": 0.0166, "step": 1401 }, { "epoch": 9.602739726027398, "grad_norm": 2833.5615234375, "learning_rate": 2.1691176470588238e-06, "loss": 0.0153, "step": 1402 }, { "epoch": 9.60958904109589, "grad_norm": 4078.66845703125, "learning_rate": 2.132352941176471e-06, "loss": 0.019, "step": 1403 }, { "epoch": 9.616438356164384, "grad_norm": 5582.037109375, "learning_rate": 2.0955882352941175e-06, "loss": 0.0205, "step": 1404 }, { "epoch": 9.623287671232877, "grad_norm": 4974.453125, "learning_rate": 2.058823529411765e-06, "loss": 0.0197, "step": 1405 }, { "epoch": 9.63013698630137, "grad_norm": 4517.66796875, "learning_rate": 2.022058823529412e-06, "loss": 0.0192, "step": 1406 }, { "epoch": 9.636986301369863, "grad_norm": 1918.50341796875, "learning_rate": 1.9852941176470586e-06, "loss": 0.0108, "step": 1407 }, { "epoch": 9.643835616438356, "grad_norm": 3399.26025390625, "learning_rate": 1.948529411764706e-06, "loss": 0.0181, "step": 1408 }, { "epoch": 9.650684931506849, "grad_norm": 4456.1806640625, "learning_rate": 1.911764705882353e-06, "loss": 0.0132, "step": 1409 }, { "epoch": 9.657534246575342, "grad_norm": 4877.7890625, "learning_rate": 1.875e-06, "loss": 0.0167, "step": 1410 }, { "epoch": 9.664383561643836, "grad_norm": 2746.900390625, "learning_rate": 1.8382352941176471e-06, "loss": 0.0166, "step": 1411 }, { "epoch": 9.67123287671233, "grad_norm": 4245.41650390625, "learning_rate": 1.801470588235294e-06, "loss": 0.0203, "step": 1412 }, { "epoch": 9.678082191780822, "grad_norm": 6012.5068359375, "learning_rate": 1.7647058823529412e-06, "loss": 0.0217, "step": 1413 }, { "epoch": 9.684931506849315, "grad_norm": 6138.42138671875, "learning_rate": 1.7279411764705885e-06, "loss": 0.0235, "step": 1414 }, { "epoch": 9.691780821917808, "grad_norm": 3973.088623046875, "learning_rate": 1.6911764705882354e-06, "loss": 0.0193, "step": 1415 }, { "epoch": 9.698630136986301, "grad_norm": 2892.230224609375, "learning_rate": 1.6544117647058824e-06, "loss": 0.0162, "step": 1416 }, { "epoch": 9.705479452054794, "grad_norm": 6025.94970703125, "learning_rate": 1.6176470588235297e-06, "loss": 0.0188, "step": 1417 }, { "epoch": 9.712328767123287, "grad_norm": 7891.95166015625, "learning_rate": 1.5808823529411765e-06, "loss": 0.0267, "step": 1418 }, { "epoch": 9.719178082191782, "grad_norm": 3310.082275390625, "learning_rate": 1.5441176470588236e-06, "loss": 0.0135, "step": 1419 }, { "epoch": 9.726027397260275, "grad_norm": 3953.1943359375, "learning_rate": 1.5073529411764707e-06, "loss": 0.0212, "step": 1420 }, { "epoch": 9.732876712328768, "grad_norm": 6593.970703125, "learning_rate": 1.4705882352941177e-06, "loss": 0.0253, "step": 1421 }, { "epoch": 9.73972602739726, "grad_norm": 3894.427734375, "learning_rate": 1.4338235294117648e-06, "loss": 0.017, "step": 1422 }, { "epoch": 9.746575342465754, "grad_norm": 1972.543701171875, "learning_rate": 1.3970588235294119e-06, "loss": 0.0109, "step": 1423 }, { "epoch": 9.753424657534246, "grad_norm": 8215.3525390625, "learning_rate": 1.360294117647059e-06, "loss": 0.0384, "step": 1424 }, { "epoch": 9.76027397260274, "grad_norm": 6750.5634765625, "learning_rate": 1.323529411764706e-06, "loss": 0.0245, "step": 1425 }, { "epoch": 9.767123287671232, "grad_norm": 4030.0556640625, "learning_rate": 1.286764705882353e-06, "loss": 0.013, "step": 1426 }, { "epoch": 9.773972602739725, "grad_norm": 5268.14013671875, "learning_rate": 1.25e-06, "loss": 0.0235, "step": 1427 }, { "epoch": 9.780821917808218, "grad_norm": 7238.4326171875, "learning_rate": 1.2132352941176472e-06, "loss": 0.0143, "step": 1428 }, { "epoch": 9.787671232876713, "grad_norm": 5467.58642578125, "learning_rate": 1.1764705882352942e-06, "loss": 0.0121, "step": 1429 }, { "epoch": 9.794520547945206, "grad_norm": 5205.6728515625, "learning_rate": 1.139705882352941e-06, "loss": 0.0216, "step": 1430 }, { "epoch": 9.801369863013699, "grad_norm": 3977.044189453125, "learning_rate": 1.1029411764705884e-06, "loss": 0.0143, "step": 1431 }, { "epoch": 9.808219178082192, "grad_norm": 4280.52978515625, "learning_rate": 1.0661764705882354e-06, "loss": 0.019, "step": 1432 }, { "epoch": 9.815068493150685, "grad_norm": 3753.154296875, "learning_rate": 1.0294117647058825e-06, "loss": 0.0203, "step": 1433 }, { "epoch": 9.821917808219178, "grad_norm": 3272.504638671875, "learning_rate": 9.926470588235293e-07, "loss": 0.0146, "step": 1434 }, { "epoch": 9.82876712328767, "grad_norm": 3557.2880859375, "learning_rate": 9.558823529411766e-07, "loss": 0.0174, "step": 1435 }, { "epoch": 9.835616438356164, "grad_norm": 3608.613037109375, "learning_rate": 9.191176470588236e-07, "loss": 0.0212, "step": 1436 }, { "epoch": 9.842465753424658, "grad_norm": 5467.74951171875, "learning_rate": 8.823529411764706e-07, "loss": 0.0173, "step": 1437 }, { "epoch": 9.849315068493151, "grad_norm": 5838.95068359375, "learning_rate": 8.455882352941177e-07, "loss": 0.0217, "step": 1438 }, { "epoch": 9.856164383561644, "grad_norm": 4560.04541015625, "learning_rate": 8.088235294117648e-07, "loss": 0.022, "step": 1439 }, { "epoch": 9.863013698630137, "grad_norm": 5522.4248046875, "learning_rate": 7.720588235294118e-07, "loss": 0.0227, "step": 1440 }, { "epoch": 9.86986301369863, "grad_norm": 4472.0712890625, "learning_rate": 7.352941176470589e-07, "loss": 0.0192, "step": 1441 }, { "epoch": 9.876712328767123, "grad_norm": 3644.4765625, "learning_rate": 6.985294117647059e-07, "loss": 0.0183, "step": 1442 }, { "epoch": 9.883561643835616, "grad_norm": 3120.27783203125, "learning_rate": 6.61764705882353e-07, "loss": 0.0157, "step": 1443 }, { "epoch": 9.89041095890411, "grad_norm": 4872.23583984375, "learning_rate": 6.25e-07, "loss": 0.0211, "step": 1444 }, { "epoch": 9.897260273972602, "grad_norm": 5433.33740234375, "learning_rate": 5.882352941176471e-07, "loss": 0.0254, "step": 1445 }, { "epoch": 9.904109589041095, "grad_norm": 3995.15869140625, "learning_rate": 5.514705882352942e-07, "loss": 0.0221, "step": 1446 }, { "epoch": 9.91095890410959, "grad_norm": 4211.3173828125, "learning_rate": 5.147058823529412e-07, "loss": 0.0206, "step": 1447 }, { "epoch": 9.917808219178083, "grad_norm": 1719.68505859375, "learning_rate": 4.779411764705883e-07, "loss": 0.0115, "step": 1448 }, { "epoch": 9.924657534246576, "grad_norm": 4735.38525390625, "learning_rate": 4.411764705882353e-07, "loss": 0.022, "step": 1449 }, { "epoch": 9.931506849315069, "grad_norm": 3057.939453125, "learning_rate": 4.044117647058824e-07, "loss": 0.0169, "step": 1450 }, { "epoch": 9.938356164383562, "grad_norm": 5399.38818359375, "learning_rate": 3.6764705882352943e-07, "loss": 0.0219, "step": 1451 }, { "epoch": 9.945205479452055, "grad_norm": 3336.729248046875, "learning_rate": 3.308823529411765e-07, "loss": 0.0177, "step": 1452 }, { "epoch": 9.952054794520548, "grad_norm": 3333.05810546875, "learning_rate": 2.9411764705882356e-07, "loss": 0.0136, "step": 1453 }, { "epoch": 9.95890410958904, "grad_norm": 3022.948486328125, "learning_rate": 2.573529411764706e-07, "loss": 0.0193, "step": 1454 }, { "epoch": 9.965753424657533, "grad_norm": 13254.845703125, "learning_rate": 2.2058823529411765e-07, "loss": 0.0364, "step": 1455 }, { "epoch": 9.972602739726028, "grad_norm": 3753.4775390625, "learning_rate": 1.8382352941176472e-07, "loss": 0.0184, "step": 1456 }, { "epoch": 9.979452054794521, "grad_norm": 5821.45068359375, "learning_rate": 1.4705882352941178e-07, "loss": 0.0252, "step": 1457 }, { "epoch": 9.986301369863014, "grad_norm": 6088.38623046875, "learning_rate": 1.1029411764705883e-07, "loss": 0.0209, "step": 1458 }, { "epoch": 9.993150684931507, "grad_norm": 2052.54052734375, "learning_rate": 7.352941176470589e-08, "loss": 0.0112, "step": 1459 }, { "epoch": 10.0, "grad_norm": 5916.71923828125, "learning_rate": 3.6764705882352945e-08, "loss": 0.0178, "step": 1460 }, { "epoch": 10.0, "eval_f1_macro": 0.7537425761964708, "eval_f1_micro": 0.8658280922431866, "eval_loss": 0.030240267515182495, "eval_precision": 0.89587852494577, "eval_recall": 0.8377281947261663, "eval_runtime": 1.0956, "eval_samples_per_second": 355.044, "eval_steps_per_second": 15.516, "step": 1460 } ], "logging_steps": 1, "max_steps": 1460, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9202326737879040.0, "train_batch_size": 24, "trial_name": null, "trial_params": null }