{ "best_global_step": 1580, "best_metric": 0.8760484622553588, "best_model_checkpoint": "./cysecbert-ttp-bert-100per_ood_data/checkpoint-1580", "epoch": 10.0, "eval_steps": 500, "global_step": 1580, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006329113924050633, "grad_norm": 46756.04296875, "learning_rate": 0.0, "loss": 0.7113, "step": 1 }, { "epoch": 0.012658227848101266, "grad_norm": 43903.5234375, "learning_rate": 5.000000000000001e-07, "loss": 0.7128, "step": 2 }, { "epoch": 0.0189873417721519, "grad_norm": 42806.34375, "learning_rate": 1.0000000000000002e-06, "loss": 0.7093, "step": 3 }, { "epoch": 0.02531645569620253, "grad_norm": 47373.3203125, "learning_rate": 1.5e-06, "loss": 0.7141, "step": 4 }, { "epoch": 0.03164556962025317, "grad_norm": 41472.640625, "learning_rate": 2.0000000000000003e-06, "loss": 0.7105, "step": 5 }, { "epoch": 0.0379746835443038, "grad_norm": 45034.50390625, "learning_rate": 2.5e-06, "loss": 0.7073, "step": 6 }, { "epoch": 0.04430379746835443, "grad_norm": 44123.68359375, "learning_rate": 3e-06, "loss": 0.7068, "step": 7 }, { "epoch": 0.05063291139240506, "grad_norm": 45263.01171875, "learning_rate": 3.5000000000000004e-06, "loss": 0.7023, "step": 8 }, { "epoch": 0.056962025316455694, "grad_norm": 156891.015625, "learning_rate": 4.000000000000001e-06, "loss": 0.699, "step": 9 }, { "epoch": 0.06329113924050633, "grad_norm": 41678.5625, "learning_rate": 4.5e-06, "loss": 0.6948, "step": 10 }, { "epoch": 0.06962025316455696, "grad_norm": 42243.03125, "learning_rate": 5e-06, "loss": 0.6903, "step": 11 }, { "epoch": 0.0759493670886076, "grad_norm": 46105.72265625, "learning_rate": 5.500000000000001e-06, "loss": 0.6881, "step": 12 }, { "epoch": 0.08227848101265822, "grad_norm": 54590.9765625, "learning_rate": 6e-06, "loss": 0.6816, "step": 13 }, { "epoch": 0.08860759493670886, "grad_norm": 51449.453125, "learning_rate": 6.5000000000000004e-06, "loss": 0.6768, "step": 14 }, { "epoch": 0.0949367088607595, "grad_norm": 97889.1640625, "learning_rate": 7.000000000000001e-06, "loss": 0.6706, "step": 15 }, { "epoch": 0.10126582278481013, "grad_norm": 48539.12109375, "learning_rate": 7.5e-06, "loss": 0.6629, "step": 16 }, { "epoch": 0.10759493670886076, "grad_norm": 77225.34375, "learning_rate": 8.000000000000001e-06, "loss": 0.6578, "step": 17 }, { "epoch": 0.11392405063291139, "grad_norm": 55972.33203125, "learning_rate": 8.500000000000002e-06, "loss": 0.6486, "step": 18 }, { "epoch": 0.12025316455696203, "grad_norm": 54871.07421875, "learning_rate": 9e-06, "loss": 0.6415, "step": 19 }, { "epoch": 0.12658227848101267, "grad_norm": 55085.66015625, "learning_rate": 9.5e-06, "loss": 0.6305, "step": 20 }, { "epoch": 0.13291139240506328, "grad_norm": 146644.546875, "learning_rate": 1e-05, "loss": 0.6178, "step": 21 }, { "epoch": 0.13924050632911392, "grad_norm": 60370.9375, "learning_rate": 1.05e-05, "loss": 0.602, "step": 22 }, { "epoch": 0.14556962025316456, "grad_norm": 75777.9140625, "learning_rate": 1.1000000000000001e-05, "loss": 0.5967, "step": 23 }, { "epoch": 0.1518987341772152, "grad_norm": 60152.359375, "learning_rate": 1.1500000000000002e-05, "loss": 0.5781, "step": 24 }, { "epoch": 0.15822784810126583, "grad_norm": 55555.45703125, "learning_rate": 1.2e-05, "loss": 0.569, "step": 25 }, { "epoch": 0.16455696202531644, "grad_norm": 55779.83984375, "learning_rate": 1.25e-05, "loss": 0.5591, "step": 26 }, { "epoch": 0.17088607594936708, "grad_norm": 55596.78515625, "learning_rate": 1.3000000000000001e-05, "loss": 0.546, "step": 27 }, { "epoch": 0.17721518987341772, "grad_norm": 50906.703125, "learning_rate": 1.3500000000000001e-05, "loss": 0.5345, "step": 28 }, { "epoch": 0.18354430379746836, "grad_norm": 50488.7109375, "learning_rate": 1.4000000000000001e-05, "loss": 0.5242, "step": 29 }, { "epoch": 0.189873417721519, "grad_norm": 46347.77734375, "learning_rate": 1.45e-05, "loss": 0.5153, "step": 30 }, { "epoch": 0.1962025316455696, "grad_norm": 48299.84375, "learning_rate": 1.5e-05, "loss": 0.5053, "step": 31 }, { "epoch": 0.20253164556962025, "grad_norm": 46204.08203125, "learning_rate": 1.55e-05, "loss": 0.4956, "step": 32 }, { "epoch": 0.2088607594936709, "grad_norm": 46679.0546875, "learning_rate": 1.6000000000000003e-05, "loss": 0.4874, "step": 33 }, { "epoch": 0.21518987341772153, "grad_norm": 46484.44140625, "learning_rate": 1.65e-05, "loss": 0.4796, "step": 34 }, { "epoch": 0.22151898734177214, "grad_norm": 43498.5546875, "learning_rate": 1.7000000000000003e-05, "loss": 0.4702, "step": 35 }, { "epoch": 0.22784810126582278, "grad_norm": 43309.0859375, "learning_rate": 1.75e-05, "loss": 0.4595, "step": 36 }, { "epoch": 0.23417721518987342, "grad_norm": 43566.9921875, "learning_rate": 1.8e-05, "loss": 0.4517, "step": 37 }, { "epoch": 0.24050632911392406, "grad_norm": 42534.69140625, "learning_rate": 1.85e-05, "loss": 0.4426, "step": 38 }, { "epoch": 0.2468354430379747, "grad_norm": 41563.67578125, "learning_rate": 1.9e-05, "loss": 0.4341, "step": 39 }, { "epoch": 0.25316455696202533, "grad_norm": 41318.15625, "learning_rate": 1.9500000000000003e-05, "loss": 0.4261, "step": 40 }, { "epoch": 0.25949367088607594, "grad_norm": 41546.296875, "learning_rate": 2e-05, "loss": 0.4164, "step": 41 }, { "epoch": 0.26582278481012656, "grad_norm": 39634.2421875, "learning_rate": 2.05e-05, "loss": 0.4093, "step": 42 }, { "epoch": 0.2721518987341772, "grad_norm": 39725.9296875, "learning_rate": 2.1e-05, "loss": 0.4022, "step": 43 }, { "epoch": 0.27848101265822783, "grad_norm": 38803.9140625, "learning_rate": 2.15e-05, "loss": 0.394, "step": 44 }, { "epoch": 0.2848101265822785, "grad_norm": 38972.24609375, "learning_rate": 2.2000000000000003e-05, "loss": 0.3841, "step": 45 }, { "epoch": 0.2911392405063291, "grad_norm": 37933.16015625, "learning_rate": 2.25e-05, "loss": 0.379, "step": 46 }, { "epoch": 0.2974683544303797, "grad_norm": 37990.07421875, "learning_rate": 2.3000000000000003e-05, "loss": 0.3728, "step": 47 }, { "epoch": 0.3037974683544304, "grad_norm": 37188.4609375, "learning_rate": 2.35e-05, "loss": 0.368, "step": 48 }, { "epoch": 0.310126582278481, "grad_norm": 36358.27734375, "learning_rate": 2.4e-05, "loss": 0.3631, "step": 49 }, { "epoch": 0.31645569620253167, "grad_norm": 37056.62890625, "learning_rate": 2.45e-05, "loss": 0.3483, "step": 50 }, { "epoch": 0.3227848101265823, "grad_norm": 36222.83203125, "learning_rate": 2.5e-05, "loss": 0.3396, "step": 51 }, { "epoch": 0.3291139240506329, "grad_norm": 35818.42578125, "learning_rate": 2.5500000000000003e-05, "loss": 0.3344, "step": 52 }, { "epoch": 0.33544303797468356, "grad_norm": 34868.46875, "learning_rate": 2.6000000000000002e-05, "loss": 0.3323, "step": 53 }, { "epoch": 0.34177215189873417, "grad_norm": 34442.5234375, "learning_rate": 2.6500000000000004e-05, "loss": 0.3263, "step": 54 }, { "epoch": 0.34810126582278483, "grad_norm": 34301.0, "learning_rate": 2.7000000000000002e-05, "loss": 0.3123, "step": 55 }, { "epoch": 0.35443037974683544, "grad_norm": 34254.8359375, "learning_rate": 2.7500000000000004e-05, "loss": 0.3116, "step": 56 }, { "epoch": 0.36075949367088606, "grad_norm": 33289.359375, "learning_rate": 2.8000000000000003e-05, "loss": 0.3109, "step": 57 }, { "epoch": 0.3670886075949367, "grad_norm": 32849.875, "learning_rate": 2.8499999999999998e-05, "loss": 0.298, "step": 58 }, { "epoch": 0.37341772151898733, "grad_norm": 33094.53515625, "learning_rate": 2.9e-05, "loss": 0.2879, "step": 59 }, { "epoch": 0.379746835443038, "grad_norm": 31730.12109375, "learning_rate": 2.95e-05, "loss": 0.2849, "step": 60 }, { "epoch": 0.3860759493670886, "grad_norm": 30969.5546875, "learning_rate": 3e-05, "loss": 0.2802, "step": 61 }, { "epoch": 0.3924050632911392, "grad_norm": 30578.40625, "learning_rate": 3.05e-05, "loss": 0.2705, "step": 62 }, { "epoch": 0.3987341772151899, "grad_norm": 29909.7734375, "learning_rate": 3.1e-05, "loss": 0.2629, "step": 63 }, { "epoch": 0.4050632911392405, "grad_norm": 29541.046875, "learning_rate": 3.15e-05, "loss": 0.2604, "step": 64 }, { "epoch": 0.41139240506329117, "grad_norm": 28760.517578125, "learning_rate": 3.2000000000000005e-05, "loss": 0.2591, "step": 65 }, { "epoch": 0.4177215189873418, "grad_norm": 28338.927734375, "learning_rate": 3.2500000000000004e-05, "loss": 0.2502, "step": 66 }, { "epoch": 0.4240506329113924, "grad_norm": 27181.4921875, "learning_rate": 3.3e-05, "loss": 0.2514, "step": 67 }, { "epoch": 0.43037974683544306, "grad_norm": 27737.134765625, "learning_rate": 3.35e-05, "loss": 0.2407, "step": 68 }, { "epoch": 0.43670886075949367, "grad_norm": 24729.41015625, "learning_rate": 3.4000000000000007e-05, "loss": 0.2533, "step": 69 }, { "epoch": 0.4430379746835443, "grad_norm": 25272.05859375, "learning_rate": 3.45e-05, "loss": 0.2287, "step": 70 }, { "epoch": 0.44936708860759494, "grad_norm": 25796.255859375, "learning_rate": 3.5e-05, "loss": 0.2177, "step": 71 }, { "epoch": 0.45569620253164556, "grad_norm": 24324.619140625, "learning_rate": 3.55e-05, "loss": 0.222, "step": 72 }, { "epoch": 0.4620253164556962, "grad_norm": 24672.8359375, "learning_rate": 3.6e-05, "loss": 0.2096, "step": 73 }, { "epoch": 0.46835443037974683, "grad_norm": 23480.125, "learning_rate": 3.65e-05, "loss": 0.2038, "step": 74 }, { "epoch": 0.47468354430379744, "grad_norm": 22790.556640625, "learning_rate": 3.7e-05, "loss": 0.1948, "step": 75 }, { "epoch": 0.4810126582278481, "grad_norm": 22601.65234375, "learning_rate": 3.7500000000000003e-05, "loss": 0.1959, "step": 76 }, { "epoch": 0.4873417721518987, "grad_norm": 21924.119140625, "learning_rate": 3.8e-05, "loss": 0.1879, "step": 77 }, { "epoch": 0.4936708860759494, "grad_norm": 19502.431640625, "learning_rate": 3.85e-05, "loss": 0.1966, "step": 78 }, { "epoch": 0.5, "grad_norm": 20898.177734375, "learning_rate": 3.9000000000000006e-05, "loss": 0.1759, "step": 79 }, { "epoch": 0.5063291139240507, "grad_norm": 18933.306640625, "learning_rate": 3.9500000000000005e-05, "loss": 0.1779, "step": 80 }, { "epoch": 0.5126582278481012, "grad_norm": 19311.931640625, "learning_rate": 4e-05, "loss": 0.1725, "step": 81 }, { "epoch": 0.5189873417721519, "grad_norm": 19286.494140625, "learning_rate": 4.05e-05, "loss": 0.163, "step": 82 }, { "epoch": 0.5253164556962026, "grad_norm": 17589.802734375, "learning_rate": 4.1e-05, "loss": 0.1675, "step": 83 }, { "epoch": 0.5316455696202531, "grad_norm": 17787.642578125, "learning_rate": 4.15e-05, "loss": 0.1681, "step": 84 }, { "epoch": 0.5379746835443038, "grad_norm": 17104.896484375, "learning_rate": 4.2e-05, "loss": 0.1601, "step": 85 }, { "epoch": 0.5443037974683544, "grad_norm": 15737.83203125, "learning_rate": 4.25e-05, "loss": 0.1603, "step": 86 }, { "epoch": 0.5506329113924051, "grad_norm": 15149.8388671875, "learning_rate": 4.3e-05, "loss": 0.1553, "step": 87 }, { "epoch": 0.5569620253164557, "grad_norm": 14509.849609375, "learning_rate": 4.35e-05, "loss": 0.1447, "step": 88 }, { "epoch": 0.5632911392405063, "grad_norm": 14352.2763671875, "learning_rate": 4.4000000000000006e-05, "loss": 0.1402, "step": 89 }, { "epoch": 0.569620253164557, "grad_norm": 13566.87890625, "learning_rate": 4.4500000000000004e-05, "loss": 0.1536, "step": 90 }, { "epoch": 0.5759493670886076, "grad_norm": 12874.9638671875, "learning_rate": 4.5e-05, "loss": 0.1413, "step": 91 }, { "epoch": 0.5822784810126582, "grad_norm": 13147.744140625, "learning_rate": 4.55e-05, "loss": 0.1254, "step": 92 }, { "epoch": 0.5886075949367089, "grad_norm": 11797.8701171875, "learning_rate": 4.600000000000001e-05, "loss": 0.1441, "step": 93 }, { "epoch": 0.5949367088607594, "grad_norm": 11272.1376953125, "learning_rate": 4.6500000000000005e-05, "loss": 0.1282, "step": 94 }, { "epoch": 0.6012658227848101, "grad_norm": 13020.7578125, "learning_rate": 4.7e-05, "loss": 0.1241, "step": 95 }, { "epoch": 0.6075949367088608, "grad_norm": 11524.138671875, "learning_rate": 4.75e-05, "loss": 0.1225, "step": 96 }, { "epoch": 0.6139240506329114, "grad_norm": 10857.755859375, "learning_rate": 4.8e-05, "loss": 0.117, "step": 97 }, { "epoch": 0.620253164556962, "grad_norm": 11077.3642578125, "learning_rate": 4.85e-05, "loss": 0.1272, "step": 98 }, { "epoch": 0.6265822784810127, "grad_norm": 10708.3701171875, "learning_rate": 4.9e-05, "loss": 0.1307, "step": 99 }, { "epoch": 0.6329113924050633, "grad_norm": 10128.716796875, "learning_rate": 4.9500000000000004e-05, "loss": 0.1247, "step": 100 }, { "epoch": 0.6392405063291139, "grad_norm": 9390.5107421875, "learning_rate": 5e-05, "loss": 0.1129, "step": 101 }, { "epoch": 0.6455696202531646, "grad_norm": 8546.12109375, "learning_rate": 4.996621621621622e-05, "loss": 0.1175, "step": 102 }, { "epoch": 0.6518987341772152, "grad_norm": 8942.67578125, "learning_rate": 4.9932432432432435e-05, "loss": 0.1136, "step": 103 }, { "epoch": 0.6582278481012658, "grad_norm": 7663.9638671875, "learning_rate": 4.989864864864865e-05, "loss": 0.1167, "step": 104 }, { "epoch": 0.6645569620253164, "grad_norm": 9257.8369140625, "learning_rate": 4.986486486486487e-05, "loss": 0.1032, "step": 105 }, { "epoch": 0.6708860759493671, "grad_norm": 8268.4990234375, "learning_rate": 4.983108108108108e-05, "loss": 0.1062, "step": 106 }, { "epoch": 0.6772151898734177, "grad_norm": 8120.880859375, "learning_rate": 4.97972972972973e-05, "loss": 0.1174, "step": 107 }, { "epoch": 0.6835443037974683, "grad_norm": 11550.9443359375, "learning_rate": 4.9763513513513515e-05, "loss": 0.1081, "step": 108 }, { "epoch": 0.689873417721519, "grad_norm": 7703.509765625, "learning_rate": 4.972972972972974e-05, "loss": 0.1192, "step": 109 }, { "epoch": 0.6962025316455697, "grad_norm": 7040.79931640625, "learning_rate": 4.969594594594595e-05, "loss": 0.1045, "step": 110 }, { "epoch": 0.7025316455696202, "grad_norm": 8037.07763671875, "learning_rate": 4.9662162162162164e-05, "loss": 0.1103, "step": 111 }, { "epoch": 0.7088607594936709, "grad_norm": 7969.5185546875, "learning_rate": 4.962837837837838e-05, "loss": 0.1193, "step": 112 }, { "epoch": 0.7151898734177216, "grad_norm": 7649.28564453125, "learning_rate": 4.9594594594594596e-05, "loss": 0.1019, "step": 113 }, { "epoch": 0.7215189873417721, "grad_norm": 7921.8115234375, "learning_rate": 4.956081081081081e-05, "loss": 0.1063, "step": 114 }, { "epoch": 0.7278481012658228, "grad_norm": 7828.4931640625, "learning_rate": 4.952702702702703e-05, "loss": 0.1143, "step": 115 }, { "epoch": 0.7341772151898734, "grad_norm": 8267.41015625, "learning_rate": 4.949324324324325e-05, "loss": 0.1172, "step": 116 }, { "epoch": 0.740506329113924, "grad_norm": 7909.19140625, "learning_rate": 4.945945945945946e-05, "loss": 0.1173, "step": 117 }, { "epoch": 0.7468354430379747, "grad_norm": 8466.3037109375, "learning_rate": 4.9425675675675677e-05, "loss": 0.1024, "step": 118 }, { "epoch": 0.7531645569620253, "grad_norm": 11761.5703125, "learning_rate": 4.939189189189189e-05, "loss": 0.1086, "step": 119 }, { "epoch": 0.759493670886076, "grad_norm": 7872.5615234375, "learning_rate": 4.935810810810811e-05, "loss": 0.1016, "step": 120 }, { "epoch": 0.7658227848101266, "grad_norm": 7982.1611328125, "learning_rate": 4.9324324324324325e-05, "loss": 0.1297, "step": 121 }, { "epoch": 0.7721518987341772, "grad_norm": 7937.1806640625, "learning_rate": 4.929054054054054e-05, "loss": 0.1118, "step": 122 }, { "epoch": 0.7784810126582279, "grad_norm": 9423.591796875, "learning_rate": 4.9256756756756764e-05, "loss": 0.1309, "step": 123 }, { "epoch": 0.7848101265822784, "grad_norm": 7673.45556640625, "learning_rate": 4.922297297297297e-05, "loss": 0.1116, "step": 124 }, { "epoch": 0.7911392405063291, "grad_norm": 9288.0439453125, "learning_rate": 4.9189189189189196e-05, "loss": 0.106, "step": 125 }, { "epoch": 0.7974683544303798, "grad_norm": 8156.0888671875, "learning_rate": 4.9155405405405406e-05, "loss": 0.1113, "step": 126 }, { "epoch": 0.8037974683544303, "grad_norm": 8910.923828125, "learning_rate": 4.912162162162162e-05, "loss": 0.0952, "step": 127 }, { "epoch": 0.810126582278481, "grad_norm": 9109.94921875, "learning_rate": 4.908783783783784e-05, "loss": 0.1286, "step": 128 }, { "epoch": 0.8164556962025317, "grad_norm": 7808.35986328125, "learning_rate": 4.9054054054054054e-05, "loss": 0.1095, "step": 129 }, { "epoch": 0.8227848101265823, "grad_norm": 6523.31396484375, "learning_rate": 4.902027027027028e-05, "loss": 0.1018, "step": 130 }, { "epoch": 0.8291139240506329, "grad_norm": 8604.0693359375, "learning_rate": 4.8986486486486486e-05, "loss": 0.1054, "step": 131 }, { "epoch": 0.8354430379746836, "grad_norm": 8048.68408203125, "learning_rate": 4.895270270270271e-05, "loss": 0.103, "step": 132 }, { "epoch": 0.8417721518987342, "grad_norm": 7524.46826171875, "learning_rate": 4.891891891891892e-05, "loss": 0.1203, "step": 133 }, { "epoch": 0.8481012658227848, "grad_norm": 8260.8271484375, "learning_rate": 4.8885135135135135e-05, "loss": 0.1088, "step": 134 }, { "epoch": 0.8544303797468354, "grad_norm": 7689.91943359375, "learning_rate": 4.885135135135136e-05, "loss": 0.104, "step": 135 }, { "epoch": 0.8607594936708861, "grad_norm": 7882.4560546875, "learning_rate": 4.881756756756757e-05, "loss": 0.1227, "step": 136 }, { "epoch": 0.8670886075949367, "grad_norm": 8412.5390625, "learning_rate": 4.878378378378379e-05, "loss": 0.0933, "step": 137 }, { "epoch": 0.8734177215189873, "grad_norm": 6479.29833984375, "learning_rate": 4.875e-05, "loss": 0.1008, "step": 138 }, { "epoch": 0.879746835443038, "grad_norm": 10099.2998046875, "learning_rate": 4.871621621621622e-05, "loss": 0.0991, "step": 139 }, { "epoch": 0.8860759493670886, "grad_norm": 9244.41015625, "learning_rate": 4.868243243243243e-05, "loss": 0.1393, "step": 140 }, { "epoch": 0.8924050632911392, "grad_norm": 7656.8369140625, "learning_rate": 4.8648648648648654e-05, "loss": 0.1119, "step": 141 }, { "epoch": 0.8987341772151899, "grad_norm": 6229.986328125, "learning_rate": 4.861486486486487e-05, "loss": 0.1048, "step": 142 }, { "epoch": 0.9050632911392406, "grad_norm": 6766.28369140625, "learning_rate": 4.858108108108108e-05, "loss": 0.1094, "step": 143 }, { "epoch": 0.9113924050632911, "grad_norm": 7321.6982421875, "learning_rate": 4.85472972972973e-05, "loss": 0.1121, "step": 144 }, { "epoch": 0.9177215189873418, "grad_norm": 7585.0478515625, "learning_rate": 4.851351351351351e-05, "loss": 0.1047, "step": 145 }, { "epoch": 0.9240506329113924, "grad_norm": 7722.02587890625, "learning_rate": 4.8479729729729735e-05, "loss": 0.1156, "step": 146 }, { "epoch": 0.930379746835443, "grad_norm": 7108.27001953125, "learning_rate": 4.8445945945945944e-05, "loss": 0.0987, "step": 147 }, { "epoch": 0.9367088607594937, "grad_norm": 7567.56982421875, "learning_rate": 4.841216216216217e-05, "loss": 0.0935, "step": 148 }, { "epoch": 0.9430379746835443, "grad_norm": 6635.67919921875, "learning_rate": 4.837837837837838e-05, "loss": 0.1139, "step": 149 }, { "epoch": 0.9493670886075949, "grad_norm": 6941.31689453125, "learning_rate": 4.834459459459459e-05, "loss": 0.0919, "step": 150 }, { "epoch": 0.9556962025316456, "grad_norm": 7289.03759765625, "learning_rate": 4.8310810810810816e-05, "loss": 0.1032, "step": 151 }, { "epoch": 0.9620253164556962, "grad_norm": 7938.3857421875, "learning_rate": 4.8277027027027025e-05, "loss": 0.1112, "step": 152 }, { "epoch": 0.9683544303797469, "grad_norm": 7759.6123046875, "learning_rate": 4.824324324324325e-05, "loss": 0.1053, "step": 153 }, { "epoch": 0.9746835443037974, "grad_norm": 8205.6640625, "learning_rate": 4.8209459459459464e-05, "loss": 0.1026, "step": 154 }, { "epoch": 0.9810126582278481, "grad_norm": 9655.42578125, "learning_rate": 4.817567567567568e-05, "loss": 0.0914, "step": 155 }, { "epoch": 0.9873417721518988, "grad_norm": 6485.4453125, "learning_rate": 4.8141891891891896e-05, "loss": 0.0923, "step": 156 }, { "epoch": 0.9936708860759493, "grad_norm": 8231.4375, "learning_rate": 4.810810810810811e-05, "loss": 0.1, "step": 157 }, { "epoch": 1.0, "grad_norm": 13848.521484375, "learning_rate": 4.807432432432433e-05, "loss": 0.1298, "step": 158 }, { "epoch": 1.0, "eval_f1_macro": 0.0, "eval_f1_micro": 0.0, "eval_loss": 0.11079970002174377, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 1.5049, "eval_samples_per_second": 279.754, "eval_steps_per_second": 11.961, "step": 158 }, { "epoch": 1.0063291139240507, "grad_norm": 7363.009765625, "learning_rate": 4.804054054054054e-05, "loss": 0.1023, "step": 159 }, { "epoch": 1.0126582278481013, "grad_norm": 8038.7275390625, "learning_rate": 4.800675675675676e-05, "loss": 0.1045, "step": 160 }, { "epoch": 1.018987341772152, "grad_norm": 7671.73046875, "learning_rate": 4.797297297297298e-05, "loss": 0.1066, "step": 161 }, { "epoch": 1.0253164556962024, "grad_norm": 6749.953125, "learning_rate": 4.793918918918919e-05, "loss": 0.1153, "step": 162 }, { "epoch": 1.0316455696202531, "grad_norm": 7589.17578125, "learning_rate": 4.790540540540541e-05, "loss": 0.116, "step": 163 }, { "epoch": 1.0379746835443038, "grad_norm": 11017.8037109375, "learning_rate": 4.7871621621621625e-05, "loss": 0.1068, "step": 164 }, { "epoch": 1.0443037974683544, "grad_norm": 7952.7568359375, "learning_rate": 4.783783783783784e-05, "loss": 0.1113, "step": 165 }, { "epoch": 1.0506329113924051, "grad_norm": 6798.35986328125, "learning_rate": 4.780405405405405e-05, "loss": 0.1116, "step": 166 }, { "epoch": 1.0569620253164558, "grad_norm": 6166.81640625, "learning_rate": 4.7770270270270274e-05, "loss": 0.0949, "step": 167 }, { "epoch": 1.0632911392405062, "grad_norm": 7967.05322265625, "learning_rate": 4.773648648648649e-05, "loss": 0.1146, "step": 168 }, { "epoch": 1.0696202531645569, "grad_norm": 8814.251953125, "learning_rate": 4.7702702702702706e-05, "loss": 0.0985, "step": 169 }, { "epoch": 1.0759493670886076, "grad_norm": 7114.6845703125, "learning_rate": 4.766891891891892e-05, "loss": 0.0995, "step": 170 }, { "epoch": 1.0822784810126582, "grad_norm": 7389.91845703125, "learning_rate": 4.763513513513514e-05, "loss": 0.1166, "step": 171 }, { "epoch": 1.0886075949367089, "grad_norm": 7875.60205078125, "learning_rate": 4.7601351351351354e-05, "loss": 0.1173, "step": 172 }, { "epoch": 1.0949367088607596, "grad_norm": 8575.4609375, "learning_rate": 4.756756756756757e-05, "loss": 0.1042, "step": 173 }, { "epoch": 1.1012658227848102, "grad_norm": 5384.7412109375, "learning_rate": 4.7533783783783786e-05, "loss": 0.1032, "step": 174 }, { "epoch": 1.1075949367088607, "grad_norm": 7705.45166015625, "learning_rate": 4.75e-05, "loss": 0.1187, "step": 175 }, { "epoch": 1.1139240506329113, "grad_norm": 7998.84326171875, "learning_rate": 4.746621621621622e-05, "loss": 0.1106, "step": 176 }, { "epoch": 1.120253164556962, "grad_norm": 8528.013671875, "learning_rate": 4.7432432432432435e-05, "loss": 0.11, "step": 177 }, { "epoch": 1.1265822784810127, "grad_norm": 8990.9296875, "learning_rate": 4.739864864864865e-05, "loss": 0.1163, "step": 178 }, { "epoch": 1.1329113924050633, "grad_norm": 9226.7373046875, "learning_rate": 4.736486486486487e-05, "loss": 0.1276, "step": 179 }, { "epoch": 1.139240506329114, "grad_norm": 8197.998046875, "learning_rate": 4.733108108108108e-05, "loss": 0.1208, "step": 180 }, { "epoch": 1.1455696202531644, "grad_norm": 9379.705078125, "learning_rate": 4.72972972972973e-05, "loss": 0.1146, "step": 181 }, { "epoch": 1.1518987341772151, "grad_norm": 9781.029296875, "learning_rate": 4.7263513513513516e-05, "loss": 0.1198, "step": 182 }, { "epoch": 1.1582278481012658, "grad_norm": 5346.09619140625, "learning_rate": 4.722972972972973e-05, "loss": 0.0972, "step": 183 }, { "epoch": 1.1645569620253164, "grad_norm": 6580.78369140625, "learning_rate": 4.719594594594595e-05, "loss": 0.1047, "step": 184 }, { "epoch": 1.1708860759493671, "grad_norm": 8369.587890625, "learning_rate": 4.7162162162162164e-05, "loss": 0.1129, "step": 185 }, { "epoch": 1.1772151898734178, "grad_norm": 9310.1796875, "learning_rate": 4.712837837837838e-05, "loss": 0.1126, "step": 186 }, { "epoch": 1.1835443037974684, "grad_norm": 9612.515625, "learning_rate": 4.7094594594594596e-05, "loss": 0.1269, "step": 187 }, { "epoch": 1.189873417721519, "grad_norm": 8043.70751953125, "learning_rate": 4.706081081081081e-05, "loss": 0.1061, "step": 188 }, { "epoch": 1.1962025316455696, "grad_norm": 8403.7109375, "learning_rate": 4.7027027027027035e-05, "loss": 0.1202, "step": 189 }, { "epoch": 1.2025316455696202, "grad_norm": 5852.11328125, "learning_rate": 4.6993243243243245e-05, "loss": 0.1059, "step": 190 }, { "epoch": 1.2088607594936709, "grad_norm": 8216.9873046875, "learning_rate": 4.695945945945946e-05, "loss": 0.1114, "step": 191 }, { "epoch": 1.2151898734177216, "grad_norm": 6450.65234375, "learning_rate": 4.692567567567568e-05, "loss": 0.1049, "step": 192 }, { "epoch": 1.2215189873417722, "grad_norm": 5954.2900390625, "learning_rate": 4.689189189189189e-05, "loss": 0.0972, "step": 193 }, { "epoch": 1.2278481012658227, "grad_norm": 8136.205078125, "learning_rate": 4.685810810810811e-05, "loss": 0.1146, "step": 194 }, { "epoch": 1.2341772151898733, "grad_norm": 6255.01953125, "learning_rate": 4.6824324324324325e-05, "loss": 0.0975, "step": 195 }, { "epoch": 1.240506329113924, "grad_norm": 7666.4521484375, "learning_rate": 4.679054054054055e-05, "loss": 0.0982, "step": 196 }, { "epoch": 1.2468354430379747, "grad_norm": 9347.1875, "learning_rate": 4.675675675675676e-05, "loss": 0.1534, "step": 197 }, { "epoch": 1.2531645569620253, "grad_norm": 7307.60498046875, "learning_rate": 4.6722972972972974e-05, "loss": 0.1027, "step": 198 }, { "epoch": 1.259493670886076, "grad_norm": 8447.380859375, "learning_rate": 4.668918918918919e-05, "loss": 0.1033, "step": 199 }, { "epoch": 1.2658227848101267, "grad_norm": 8674.1396484375, "learning_rate": 4.6655405405405406e-05, "loss": 0.1079, "step": 200 }, { "epoch": 1.2721518987341773, "grad_norm": 6987.97509765625, "learning_rate": 4.662162162162162e-05, "loss": 0.0987, "step": 201 }, { "epoch": 1.2784810126582278, "grad_norm": 7237.66796875, "learning_rate": 4.658783783783784e-05, "loss": 0.0973, "step": 202 }, { "epoch": 1.2848101265822784, "grad_norm": 7143.24560546875, "learning_rate": 4.655405405405406e-05, "loss": 0.1053, "step": 203 }, { "epoch": 1.2911392405063291, "grad_norm": 7215.48828125, "learning_rate": 4.652027027027027e-05, "loss": 0.1201, "step": 204 }, { "epoch": 1.2974683544303798, "grad_norm": 6808.8115234375, "learning_rate": 4.648648648648649e-05, "loss": 0.1094, "step": 205 }, { "epoch": 1.3037974683544304, "grad_norm": 9880.2275390625, "learning_rate": 4.64527027027027e-05, "loss": 0.1065, "step": 206 }, { "epoch": 1.310126582278481, "grad_norm": 9370.966796875, "learning_rate": 4.641891891891892e-05, "loss": 0.1036, "step": 207 }, { "epoch": 1.3164556962025316, "grad_norm": 8294.806640625, "learning_rate": 4.6385135135135135e-05, "loss": 0.1022, "step": 208 }, { "epoch": 1.3227848101265822, "grad_norm": 7843.85693359375, "learning_rate": 4.635135135135135e-05, "loss": 0.1116, "step": 209 }, { "epoch": 1.3291139240506329, "grad_norm": 7222.1630859375, "learning_rate": 4.6317567567567574e-05, "loss": 0.1007, "step": 210 }, { "epoch": 1.3354430379746836, "grad_norm": 8497.388671875, "learning_rate": 4.628378378378378e-05, "loss": 0.1048, "step": 211 }, { "epoch": 1.3417721518987342, "grad_norm": 7453.04638671875, "learning_rate": 4.6250000000000006e-05, "loss": 0.121, "step": 212 }, { "epoch": 1.3481012658227849, "grad_norm": 6351.69970703125, "learning_rate": 4.6216216216216215e-05, "loss": 0.0908, "step": 213 }, { "epoch": 1.3544303797468356, "grad_norm": 6160.57177734375, "learning_rate": 4.618243243243243e-05, "loss": 0.1029, "step": 214 }, { "epoch": 1.360759493670886, "grad_norm": 7969.5439453125, "learning_rate": 4.6148648648648654e-05, "loss": 0.0999, "step": 215 }, { "epoch": 1.3670886075949367, "grad_norm": 9703.892578125, "learning_rate": 4.6114864864864864e-05, "loss": 0.1025, "step": 216 }, { "epoch": 1.3734177215189873, "grad_norm": 8638.66796875, "learning_rate": 4.608108108108109e-05, "loss": 0.1215, "step": 217 }, { "epoch": 1.379746835443038, "grad_norm": 9497.3349609375, "learning_rate": 4.6047297297297296e-05, "loss": 0.1195, "step": 218 }, { "epoch": 1.3860759493670887, "grad_norm": 6788.7822265625, "learning_rate": 4.601351351351352e-05, "loss": 0.0981, "step": 219 }, { "epoch": 1.3924050632911391, "grad_norm": 6963.8095703125, "learning_rate": 4.597972972972973e-05, "loss": 0.1037, "step": 220 }, { "epoch": 1.3987341772151898, "grad_norm": 6522.880859375, "learning_rate": 4.594594594594595e-05, "loss": 0.0944, "step": 221 }, { "epoch": 1.4050632911392404, "grad_norm": 5993.85986328125, "learning_rate": 4.591216216216217e-05, "loss": 0.1092, "step": 222 }, { "epoch": 1.4113924050632911, "grad_norm": 8643.2099609375, "learning_rate": 4.587837837837838e-05, "loss": 0.1026, "step": 223 }, { "epoch": 1.4177215189873418, "grad_norm": 8374.021484375, "learning_rate": 4.58445945945946e-05, "loss": 0.1198, "step": 224 }, { "epoch": 1.4240506329113924, "grad_norm": 8276.7568359375, "learning_rate": 4.581081081081081e-05, "loss": 0.109, "step": 225 }, { "epoch": 1.4303797468354431, "grad_norm": 7108.62646484375, "learning_rate": 4.577702702702703e-05, "loss": 0.0937, "step": 226 }, { "epoch": 1.4367088607594938, "grad_norm": 6412.4150390625, "learning_rate": 4.574324324324324e-05, "loss": 0.1131, "step": 227 }, { "epoch": 1.4430379746835442, "grad_norm": 8123.095703125, "learning_rate": 4.5709459459459464e-05, "loss": 0.1046, "step": 228 }, { "epoch": 1.4493670886075949, "grad_norm": 7289.2255859375, "learning_rate": 4.567567567567568e-05, "loss": 0.0956, "step": 229 }, { "epoch": 1.4556962025316456, "grad_norm": 8549.0693359375, "learning_rate": 4.564189189189189e-05, "loss": 0.0933, "step": 230 }, { "epoch": 1.4620253164556962, "grad_norm": 7329.80859375, "learning_rate": 4.560810810810811e-05, "loss": 0.0997, "step": 231 }, { "epoch": 1.4683544303797469, "grad_norm": 9273.5205078125, "learning_rate": 4.557432432432432e-05, "loss": 0.1128, "step": 232 }, { "epoch": 1.4746835443037973, "grad_norm": 7674.71728515625, "learning_rate": 4.5540540540540545e-05, "loss": 0.1025, "step": 233 }, { "epoch": 1.481012658227848, "grad_norm": 7089.06591796875, "learning_rate": 4.550675675675676e-05, "loss": 0.0954, "step": 234 }, { "epoch": 1.4873417721518987, "grad_norm": 6495.865234375, "learning_rate": 4.547297297297298e-05, "loss": 0.1032, "step": 235 }, { "epoch": 1.4936708860759493, "grad_norm": 9101.0966796875, "learning_rate": 4.543918918918919e-05, "loss": 0.0994, "step": 236 }, { "epoch": 1.5, "grad_norm": 7018.73486328125, "learning_rate": 4.540540540540541e-05, "loss": 0.0965, "step": 237 }, { "epoch": 1.5063291139240507, "grad_norm": 7407.1884765625, "learning_rate": 4.5371621621621625e-05, "loss": 0.103, "step": 238 }, { "epoch": 1.5126582278481013, "grad_norm": 9367.703125, "learning_rate": 4.5337837837837835e-05, "loss": 0.0945, "step": 239 }, { "epoch": 1.518987341772152, "grad_norm": 8471.697265625, "learning_rate": 4.530405405405406e-05, "loss": 0.106, "step": 240 }, { "epoch": 1.5253164556962027, "grad_norm": 6862.34033203125, "learning_rate": 4.5270270270270274e-05, "loss": 0.0897, "step": 241 }, { "epoch": 1.5316455696202531, "grad_norm": 7098.08837890625, "learning_rate": 4.523648648648649e-05, "loss": 0.1054, "step": 242 }, { "epoch": 1.5379746835443038, "grad_norm": 9727.2412109375, "learning_rate": 4.5202702702702706e-05, "loss": 0.1028, "step": 243 }, { "epoch": 1.5443037974683544, "grad_norm": 7618.36767578125, "learning_rate": 4.516891891891892e-05, "loss": 0.1012, "step": 244 }, { "epoch": 1.5506329113924051, "grad_norm": 8109.21826171875, "learning_rate": 4.513513513513514e-05, "loss": 0.1197, "step": 245 }, { "epoch": 1.5569620253164556, "grad_norm": 7516.58544921875, "learning_rate": 4.510135135135135e-05, "loss": 0.0918, "step": 246 }, { "epoch": 1.5632911392405062, "grad_norm": 7361.43408203125, "learning_rate": 4.506756756756757e-05, "loss": 0.099, "step": 247 }, { "epoch": 1.5696202531645569, "grad_norm": 11225.455078125, "learning_rate": 4.503378378378379e-05, "loss": 0.1091, "step": 248 }, { "epoch": 1.5759493670886076, "grad_norm": 7236.96142578125, "learning_rate": 4.5e-05, "loss": 0.1174, "step": 249 }, { "epoch": 1.5822784810126582, "grad_norm": 10003.7001953125, "learning_rate": 4.496621621621622e-05, "loss": 0.1045, "step": 250 }, { "epoch": 1.5886075949367089, "grad_norm": 10172.1728515625, "learning_rate": 4.4932432432432435e-05, "loss": 0.092, "step": 251 }, { "epoch": 1.5949367088607596, "grad_norm": 6540.09228515625, "learning_rate": 4.489864864864865e-05, "loss": 0.0975, "step": 252 }, { "epoch": 1.6012658227848102, "grad_norm": 7101.037109375, "learning_rate": 4.486486486486487e-05, "loss": 0.1013, "step": 253 }, { "epoch": 1.6075949367088609, "grad_norm": 7723.63232421875, "learning_rate": 4.4831081081081083e-05, "loss": 0.107, "step": 254 }, { "epoch": 1.6139240506329116, "grad_norm": 6232.0849609375, "learning_rate": 4.47972972972973e-05, "loss": 0.09, "step": 255 }, { "epoch": 1.620253164556962, "grad_norm": 6917.587890625, "learning_rate": 4.4763513513513516e-05, "loss": 0.0906, "step": 256 }, { "epoch": 1.6265822784810127, "grad_norm": 10106.21875, "learning_rate": 4.472972972972973e-05, "loss": 0.1201, "step": 257 }, { "epoch": 1.6329113924050633, "grad_norm": 8028.9521484375, "learning_rate": 4.469594594594595e-05, "loss": 0.1041, "step": 258 }, { "epoch": 1.6392405063291138, "grad_norm": 8580.0478515625, "learning_rate": 4.4662162162162164e-05, "loss": 0.09, "step": 259 }, { "epoch": 1.6455696202531644, "grad_norm": 8490.4423828125, "learning_rate": 4.462837837837838e-05, "loss": 0.1071, "step": 260 }, { "epoch": 1.6518987341772151, "grad_norm": 6746.068359375, "learning_rate": 4.4594594594594596e-05, "loss": 0.1073, "step": 261 }, { "epoch": 1.6582278481012658, "grad_norm": 7028.51513671875, "learning_rate": 4.456081081081081e-05, "loss": 0.0917, "step": 262 }, { "epoch": 1.6645569620253164, "grad_norm": 8316.666015625, "learning_rate": 4.452702702702703e-05, "loss": 0.1095, "step": 263 }, { "epoch": 1.6708860759493671, "grad_norm": 10374.3505859375, "learning_rate": 4.4493243243243245e-05, "loss": 0.0996, "step": 264 }, { "epoch": 1.6772151898734178, "grad_norm": 9007.337890625, "learning_rate": 4.445945945945946e-05, "loss": 0.0973, "step": 265 }, { "epoch": 1.6835443037974684, "grad_norm": 10437.0888671875, "learning_rate": 4.442567567567568e-05, "loss": 0.1369, "step": 266 }, { "epoch": 1.689873417721519, "grad_norm": 5898.3544921875, "learning_rate": 4.439189189189189e-05, "loss": 0.1069, "step": 267 }, { "epoch": 1.6962025316455698, "grad_norm": 8164.8046875, "learning_rate": 4.435810810810811e-05, "loss": 0.099, "step": 268 }, { "epoch": 1.7025316455696202, "grad_norm": 12486.607421875, "learning_rate": 4.432432432432433e-05, "loss": 0.1045, "step": 269 }, { "epoch": 1.7088607594936709, "grad_norm": 10570.6689453125, "learning_rate": 4.429054054054054e-05, "loss": 0.0988, "step": 270 }, { "epoch": 1.7151898734177216, "grad_norm": 6714.95751953125, "learning_rate": 4.425675675675676e-05, "loss": 0.1013, "step": 271 }, { "epoch": 1.721518987341772, "grad_norm": 11243.419921875, "learning_rate": 4.4222972972972974e-05, "loss": 0.1054, "step": 272 }, { "epoch": 1.7278481012658227, "grad_norm": 9246.298828125, "learning_rate": 4.418918918918919e-05, "loss": 0.0952, "step": 273 }, { "epoch": 1.7341772151898733, "grad_norm": 6584.68896484375, "learning_rate": 4.4155405405405406e-05, "loss": 0.1013, "step": 274 }, { "epoch": 1.740506329113924, "grad_norm": 7794.81884765625, "learning_rate": 4.412162162162162e-05, "loss": 0.0952, "step": 275 }, { "epoch": 1.7468354430379747, "grad_norm": 9474.6943359375, "learning_rate": 4.4087837837837845e-05, "loss": 0.1056, "step": 276 }, { "epoch": 1.7531645569620253, "grad_norm": 6084.5673828125, "learning_rate": 4.4054054054054054e-05, "loss": 0.0973, "step": 277 }, { "epoch": 1.759493670886076, "grad_norm": 8372.78125, "learning_rate": 4.402027027027027e-05, "loss": 0.1219, "step": 278 }, { "epoch": 1.7658227848101267, "grad_norm": 7800.2431640625, "learning_rate": 4.398648648648649e-05, "loss": 0.1066, "step": 279 }, { "epoch": 1.7721518987341773, "grad_norm": 8796.875, "learning_rate": 4.39527027027027e-05, "loss": 0.1053, "step": 280 }, { "epoch": 1.778481012658228, "grad_norm": 7370.41796875, "learning_rate": 4.391891891891892e-05, "loss": 0.1151, "step": 281 }, { "epoch": 1.7848101265822784, "grad_norm": 8680.9091796875, "learning_rate": 4.3885135135135135e-05, "loss": 0.1065, "step": 282 }, { "epoch": 1.7911392405063291, "grad_norm": 8545.8154296875, "learning_rate": 4.385135135135136e-05, "loss": 0.0851, "step": 283 }, { "epoch": 1.7974683544303798, "grad_norm": 7944.9697265625, "learning_rate": 4.381756756756757e-05, "loss": 0.101, "step": 284 }, { "epoch": 1.8037974683544302, "grad_norm": 6207.85400390625, "learning_rate": 4.378378378378379e-05, "loss": 0.0951, "step": 285 }, { "epoch": 1.810126582278481, "grad_norm": 12771.8818359375, "learning_rate": 4.375e-05, "loss": 0.109, "step": 286 }, { "epoch": 1.8164556962025316, "grad_norm": 7748.55712890625, "learning_rate": 4.3716216216216216e-05, "loss": 0.0979, "step": 287 }, { "epoch": 1.8227848101265822, "grad_norm": 7860.2001953125, "learning_rate": 4.368243243243244e-05, "loss": 0.0965, "step": 288 }, { "epoch": 1.8291139240506329, "grad_norm": 8703.4111328125, "learning_rate": 4.364864864864865e-05, "loss": 0.081, "step": 289 }, { "epoch": 1.8354430379746836, "grad_norm": 6319.84130859375, "learning_rate": 4.361486486486487e-05, "loss": 0.0898, "step": 290 }, { "epoch": 1.8417721518987342, "grad_norm": 6228.89404296875, "learning_rate": 4.358108108108108e-05, "loss": 0.0957, "step": 291 }, { "epoch": 1.8481012658227849, "grad_norm": 7037.01611328125, "learning_rate": 4.35472972972973e-05, "loss": 0.0924, "step": 292 }, { "epoch": 1.8544303797468356, "grad_norm": 7974.2890625, "learning_rate": 4.351351351351351e-05, "loss": 0.0946, "step": 293 }, { "epoch": 1.8607594936708862, "grad_norm": 7164.7353515625, "learning_rate": 4.3479729729729735e-05, "loss": 0.0807, "step": 294 }, { "epoch": 1.8670886075949367, "grad_norm": 10718.6650390625, "learning_rate": 4.344594594594595e-05, "loss": 0.0879, "step": 295 }, { "epoch": 1.8734177215189873, "grad_norm": 7302.7197265625, "learning_rate": 4.341216216216216e-05, "loss": 0.0902, "step": 296 }, { "epoch": 1.879746835443038, "grad_norm": 8082.62890625, "learning_rate": 4.3378378378378384e-05, "loss": 0.1069, "step": 297 }, { "epoch": 1.8860759493670884, "grad_norm": 8341.912109375, "learning_rate": 4.334459459459459e-05, "loss": 0.0837, "step": 298 }, { "epoch": 1.8924050632911391, "grad_norm": 6521.84521484375, "learning_rate": 4.3310810810810816e-05, "loss": 0.0899, "step": 299 }, { "epoch": 1.8987341772151898, "grad_norm": 6641.5, "learning_rate": 4.3277027027027025e-05, "loss": 0.0802, "step": 300 }, { "epoch": 1.9050632911392404, "grad_norm": 7545.669921875, "learning_rate": 4.324324324324325e-05, "loss": 0.0985, "step": 301 }, { "epoch": 1.9113924050632911, "grad_norm": 5918.94384765625, "learning_rate": 4.3209459459459464e-05, "loss": 0.0764, "step": 302 }, { "epoch": 1.9177215189873418, "grad_norm": 7024.6494140625, "learning_rate": 4.3175675675675674e-05, "loss": 0.0985, "step": 303 }, { "epoch": 1.9240506329113924, "grad_norm": 8217.626953125, "learning_rate": 4.31418918918919e-05, "loss": 0.1065, "step": 304 }, { "epoch": 1.9303797468354431, "grad_norm": 10667.306640625, "learning_rate": 4.3108108108108106e-05, "loss": 0.1049, "step": 305 }, { "epoch": 1.9367088607594938, "grad_norm": 7221.96435546875, "learning_rate": 4.307432432432433e-05, "loss": 0.0891, "step": 306 }, { "epoch": 1.9430379746835444, "grad_norm": 7068.08447265625, "learning_rate": 4.304054054054054e-05, "loss": 0.0955, "step": 307 }, { "epoch": 1.9493670886075949, "grad_norm": 8129.837890625, "learning_rate": 4.300675675675676e-05, "loss": 0.0938, "step": 308 }, { "epoch": 1.9556962025316456, "grad_norm": 6961.1845703125, "learning_rate": 4.297297297297298e-05, "loss": 0.0804, "step": 309 }, { "epoch": 1.9620253164556962, "grad_norm": 7957.51025390625, "learning_rate": 4.2939189189189193e-05, "loss": 0.1048, "step": 310 }, { "epoch": 1.9683544303797469, "grad_norm": 8525.287109375, "learning_rate": 4.290540540540541e-05, "loss": 0.0951, "step": 311 }, { "epoch": 1.9746835443037973, "grad_norm": 10560.01953125, "learning_rate": 4.287162162162162e-05, "loss": 0.0932, "step": 312 }, { "epoch": 1.981012658227848, "grad_norm": 8906.119140625, "learning_rate": 4.283783783783784e-05, "loss": 0.0985, "step": 313 }, { "epoch": 1.9873417721518987, "grad_norm": 7783.81689453125, "learning_rate": 4.280405405405406e-05, "loss": 0.0967, "step": 314 }, { "epoch": 1.9936708860759493, "grad_norm": 10211.970703125, "learning_rate": 4.2770270270270274e-05, "loss": 0.1062, "step": 315 }, { "epoch": 2.0, "grad_norm": 10142.939453125, "learning_rate": 4.273648648648649e-05, "loss": 0.0844, "step": 316 }, { "epoch": 2.0, "eval_f1_macro": 0.044931350114416485, "eval_f1_micro": 0.30927835051546393, "eval_loss": 0.09530407935380936, "eval_precision": 0.8267716535433071, "eval_recall": 0.19021739130434784, "eval_runtime": 1.5178, "eval_samples_per_second": 277.381, "eval_steps_per_second": 11.86, "step": 316 }, { "epoch": 2.0063291139240507, "grad_norm": 9168.240234375, "learning_rate": 4.2702702702702706e-05, "loss": 0.0899, "step": 317 }, { "epoch": 2.0126582278481013, "grad_norm": 8125.50390625, "learning_rate": 4.266891891891892e-05, "loss": 0.0886, "step": 318 }, { "epoch": 2.018987341772152, "grad_norm": 6237.20458984375, "learning_rate": 4.263513513513513e-05, "loss": 0.0941, "step": 319 }, { "epoch": 2.0253164556962027, "grad_norm": 9647.24609375, "learning_rate": 4.2601351351351355e-05, "loss": 0.0738, "step": 320 }, { "epoch": 2.0316455696202533, "grad_norm": 6863.24462890625, "learning_rate": 4.256756756756757e-05, "loss": 0.0828, "step": 321 }, { "epoch": 2.037974683544304, "grad_norm": 7966.7119140625, "learning_rate": 4.253378378378379e-05, "loss": 0.0994, "step": 322 }, { "epoch": 2.0443037974683542, "grad_norm": 7407.2626953125, "learning_rate": 4.25e-05, "loss": 0.0802, "step": 323 }, { "epoch": 2.050632911392405, "grad_norm": 8416.4140625, "learning_rate": 4.246621621621622e-05, "loss": 0.095, "step": 324 }, { "epoch": 2.0569620253164556, "grad_norm": 6670.8515625, "learning_rate": 4.2432432432432435e-05, "loss": 0.0899, "step": 325 }, { "epoch": 2.0632911392405062, "grad_norm": 7195.4658203125, "learning_rate": 4.239864864864865e-05, "loss": 0.0803, "step": 326 }, { "epoch": 2.069620253164557, "grad_norm": 10691.0478515625, "learning_rate": 4.236486486486487e-05, "loss": 0.1066, "step": 327 }, { "epoch": 2.0759493670886076, "grad_norm": 8557.0546875, "learning_rate": 4.2331081081081084e-05, "loss": 0.0965, "step": 328 }, { "epoch": 2.0822784810126582, "grad_norm": 7267.81103515625, "learning_rate": 4.22972972972973e-05, "loss": 0.0837, "step": 329 }, { "epoch": 2.088607594936709, "grad_norm": 7614.06298828125, "learning_rate": 4.2263513513513516e-05, "loss": 0.09, "step": 330 }, { "epoch": 2.0949367088607596, "grad_norm": 7303.154296875, "learning_rate": 4.222972972972973e-05, "loss": 0.0977, "step": 331 }, { "epoch": 2.1012658227848102, "grad_norm": 9759.5087890625, "learning_rate": 4.219594594594595e-05, "loss": 0.08, "step": 332 }, { "epoch": 2.107594936708861, "grad_norm": 7662.77734375, "learning_rate": 4.2162162162162164e-05, "loss": 0.1027, "step": 333 }, { "epoch": 2.1139240506329116, "grad_norm": 7541.6142578125, "learning_rate": 4.212837837837838e-05, "loss": 0.0838, "step": 334 }, { "epoch": 2.1202531645569622, "grad_norm": 9454.6767578125, "learning_rate": 4.2094594594594597e-05, "loss": 0.0945, "step": 335 }, { "epoch": 2.1265822784810124, "grad_norm": 6772.84228515625, "learning_rate": 4.206081081081081e-05, "loss": 0.0764, "step": 336 }, { "epoch": 2.132911392405063, "grad_norm": 16922.380859375, "learning_rate": 4.202702702702703e-05, "loss": 0.08, "step": 337 }, { "epoch": 2.1392405063291138, "grad_norm": 10309.3154296875, "learning_rate": 4.1993243243243245e-05, "loss": 0.095, "step": 338 }, { "epoch": 2.1455696202531644, "grad_norm": 10823.5869140625, "learning_rate": 4.195945945945946e-05, "loss": 0.0828, "step": 339 }, { "epoch": 2.151898734177215, "grad_norm": 8213.8603515625, "learning_rate": 4.192567567567568e-05, "loss": 0.0872, "step": 340 }, { "epoch": 2.1582278481012658, "grad_norm": 8320.44921875, "learning_rate": 4.189189189189189e-05, "loss": 0.0818, "step": 341 }, { "epoch": 2.1645569620253164, "grad_norm": 9091.76171875, "learning_rate": 4.185810810810811e-05, "loss": 0.0873, "step": 342 }, { "epoch": 2.170886075949367, "grad_norm": 8752.6064453125, "learning_rate": 4.1824324324324326e-05, "loss": 0.0913, "step": 343 }, { "epoch": 2.1772151898734178, "grad_norm": 8953.8916015625, "learning_rate": 4.179054054054054e-05, "loss": 0.0853, "step": 344 }, { "epoch": 2.1835443037974684, "grad_norm": 7624.2275390625, "learning_rate": 4.175675675675676e-05, "loss": 0.084, "step": 345 }, { "epoch": 2.189873417721519, "grad_norm": 15232.330078125, "learning_rate": 4.1722972972972974e-05, "loss": 0.1156, "step": 346 }, { "epoch": 2.1962025316455698, "grad_norm": 7201.908203125, "learning_rate": 4.168918918918919e-05, "loss": 0.0618, "step": 347 }, { "epoch": 2.2025316455696204, "grad_norm": 7698.95458984375, "learning_rate": 4.1655405405405406e-05, "loss": 0.081, "step": 348 }, { "epoch": 2.208860759493671, "grad_norm": 7951.533203125, "learning_rate": 4.162162162162163e-05, "loss": 0.0744, "step": 349 }, { "epoch": 2.2151898734177213, "grad_norm": 6763.32470703125, "learning_rate": 4.158783783783784e-05, "loss": 0.0805, "step": 350 }, { "epoch": 2.221518987341772, "grad_norm": 9487.5380859375, "learning_rate": 4.1554054054054055e-05, "loss": 0.0842, "step": 351 }, { "epoch": 2.2278481012658227, "grad_norm": 10050.427734375, "learning_rate": 4.152027027027027e-05, "loss": 0.1, "step": 352 }, { "epoch": 2.2341772151898733, "grad_norm": 7238.08349609375, "learning_rate": 4.148648648648649e-05, "loss": 0.0784, "step": 353 }, { "epoch": 2.240506329113924, "grad_norm": 6305.22314453125, "learning_rate": 4.14527027027027e-05, "loss": 0.0815, "step": 354 }, { "epoch": 2.2468354430379747, "grad_norm": 7193.51904296875, "learning_rate": 4.141891891891892e-05, "loss": 0.0812, "step": 355 }, { "epoch": 2.2531645569620253, "grad_norm": 9271.2509765625, "learning_rate": 4.138513513513514e-05, "loss": 0.0772, "step": 356 }, { "epoch": 2.259493670886076, "grad_norm": 8647.8466796875, "learning_rate": 4.135135135135135e-05, "loss": 0.0855, "step": 357 }, { "epoch": 2.2658227848101267, "grad_norm": 8499.578125, "learning_rate": 4.1317567567567574e-05, "loss": 0.0698, "step": 358 }, { "epoch": 2.2721518987341773, "grad_norm": 7492.1953125, "learning_rate": 4.1283783783783784e-05, "loss": 0.0773, "step": 359 }, { "epoch": 2.278481012658228, "grad_norm": 8617.720703125, "learning_rate": 4.125e-05, "loss": 0.0884, "step": 360 }, { "epoch": 2.2848101265822787, "grad_norm": 8341.619140625, "learning_rate": 4.1216216216216216e-05, "loss": 0.0919, "step": 361 }, { "epoch": 2.291139240506329, "grad_norm": 8851.7021484375, "learning_rate": 4.118243243243243e-05, "loss": 0.0782, "step": 362 }, { "epoch": 2.2974683544303796, "grad_norm": 11447.26171875, "learning_rate": 4.1148648648648655e-05, "loss": 0.0858, "step": 363 }, { "epoch": 2.3037974683544302, "grad_norm": 7446.8720703125, "learning_rate": 4.1114864864864864e-05, "loss": 0.078, "step": 364 }, { "epoch": 2.310126582278481, "grad_norm": 6560.4501953125, "learning_rate": 4.108108108108109e-05, "loss": 0.0748, "step": 365 }, { "epoch": 2.3164556962025316, "grad_norm": 9106.521484375, "learning_rate": 4.1047297297297297e-05, "loss": 0.0709, "step": 366 }, { "epoch": 2.3227848101265822, "grad_norm": 8134.72802734375, "learning_rate": 4.101351351351351e-05, "loss": 0.0785, "step": 367 }, { "epoch": 2.329113924050633, "grad_norm": 8425.869140625, "learning_rate": 4.0979729729729736e-05, "loss": 0.1, "step": 368 }, { "epoch": 2.3354430379746836, "grad_norm": 7251.87939453125, "learning_rate": 4.0945945945945945e-05, "loss": 0.09, "step": 369 }, { "epoch": 2.3417721518987342, "grad_norm": 7628.13037109375, "learning_rate": 4.091216216216217e-05, "loss": 0.0996, "step": 370 }, { "epoch": 2.348101265822785, "grad_norm": 9384.576171875, "learning_rate": 4.087837837837838e-05, "loss": 0.0691, "step": 371 }, { "epoch": 2.3544303797468356, "grad_norm": 9527.9326171875, "learning_rate": 4.08445945945946e-05, "loss": 0.0812, "step": 372 }, { "epoch": 2.3607594936708862, "grad_norm": 8382.279296875, "learning_rate": 4.081081081081081e-05, "loss": 0.0795, "step": 373 }, { "epoch": 2.367088607594937, "grad_norm": 7795.271484375, "learning_rate": 4.077702702702703e-05, "loss": 0.0885, "step": 374 }, { "epoch": 2.3734177215189876, "grad_norm": 8584.7265625, "learning_rate": 4.074324324324325e-05, "loss": 0.0856, "step": 375 }, { "epoch": 2.379746835443038, "grad_norm": 9251.4267578125, "learning_rate": 4.070945945945946e-05, "loss": 0.0868, "step": 376 }, { "epoch": 2.3860759493670884, "grad_norm": 10371.359375, "learning_rate": 4.067567567567568e-05, "loss": 0.1064, "step": 377 }, { "epoch": 2.392405063291139, "grad_norm": 7759.42431640625, "learning_rate": 4.064189189189189e-05, "loss": 0.0837, "step": 378 }, { "epoch": 2.3987341772151898, "grad_norm": 9403.525390625, "learning_rate": 4.060810810810811e-05, "loss": 0.0761, "step": 379 }, { "epoch": 2.4050632911392404, "grad_norm": 9089.7470703125, "learning_rate": 4.057432432432432e-05, "loss": 0.0718, "step": 380 }, { "epoch": 2.411392405063291, "grad_norm": 8263.39453125, "learning_rate": 4.0540540540540545e-05, "loss": 0.0749, "step": 381 }, { "epoch": 2.4177215189873418, "grad_norm": 10646.62109375, "learning_rate": 4.050675675675676e-05, "loss": 0.0787, "step": 382 }, { "epoch": 2.4240506329113924, "grad_norm": 9216.248046875, "learning_rate": 4.047297297297297e-05, "loss": 0.0719, "step": 383 }, { "epoch": 2.430379746835443, "grad_norm": 11809.6328125, "learning_rate": 4.0439189189189194e-05, "loss": 0.0719, "step": 384 }, { "epoch": 2.4367088607594938, "grad_norm": 9071.064453125, "learning_rate": 4.04054054054054e-05, "loss": 0.0933, "step": 385 }, { "epoch": 2.4430379746835444, "grad_norm": 8736.390625, "learning_rate": 4.0371621621621626e-05, "loss": 0.0881, "step": 386 }, { "epoch": 2.449367088607595, "grad_norm": 7297.4150390625, "learning_rate": 4.0337837837837835e-05, "loss": 0.072, "step": 387 }, { "epoch": 2.4556962025316453, "grad_norm": 7521.7744140625, "learning_rate": 4.030405405405406e-05, "loss": 0.0705, "step": 388 }, { "epoch": 2.462025316455696, "grad_norm": 7535.611328125, "learning_rate": 4.0270270270270274e-05, "loss": 0.0788, "step": 389 }, { "epoch": 2.4683544303797467, "grad_norm": 8304.5703125, "learning_rate": 4.023648648648649e-05, "loss": 0.075, "step": 390 }, { "epoch": 2.4746835443037973, "grad_norm": 7364.94140625, "learning_rate": 4.0202702702702707e-05, "loss": 0.0914, "step": 391 }, { "epoch": 2.481012658227848, "grad_norm": 12278.689453125, "learning_rate": 4.0168918918918916e-05, "loss": 0.0878, "step": 392 }, { "epoch": 2.4873417721518987, "grad_norm": 9211.455078125, "learning_rate": 4.013513513513514e-05, "loss": 0.087, "step": 393 }, { "epoch": 2.4936708860759493, "grad_norm": 9720.4736328125, "learning_rate": 4.0101351351351355e-05, "loss": 0.072, "step": 394 }, { "epoch": 2.5, "grad_norm": 8006.5087890625, "learning_rate": 4.006756756756757e-05, "loss": 0.0839, "step": 395 }, { "epoch": 2.5063291139240507, "grad_norm": 10206.1484375, "learning_rate": 4.003378378378379e-05, "loss": 0.0811, "step": 396 }, { "epoch": 2.5126582278481013, "grad_norm": 10057.76953125, "learning_rate": 4e-05, "loss": 0.0726, "step": 397 }, { "epoch": 2.518987341772152, "grad_norm": 9689.33984375, "learning_rate": 3.996621621621622e-05, "loss": 0.0753, "step": 398 }, { "epoch": 2.5253164556962027, "grad_norm": 11726.7041015625, "learning_rate": 3.993243243243243e-05, "loss": 0.1032, "step": 399 }, { "epoch": 2.5316455696202533, "grad_norm": 7336.875, "learning_rate": 3.989864864864865e-05, "loss": 0.0887, "step": 400 }, { "epoch": 2.537974683544304, "grad_norm": 8549.3125, "learning_rate": 3.986486486486487e-05, "loss": 0.0781, "step": 401 }, { "epoch": 2.5443037974683547, "grad_norm": 8361.4208984375, "learning_rate": 3.9831081081081084e-05, "loss": 0.1042, "step": 402 }, { "epoch": 2.5506329113924053, "grad_norm": 9663.365234375, "learning_rate": 3.97972972972973e-05, "loss": 0.0747, "step": 403 }, { "epoch": 2.5569620253164556, "grad_norm": 8029.94140625, "learning_rate": 3.9763513513513516e-05, "loss": 0.0766, "step": 404 }, { "epoch": 2.5632911392405062, "grad_norm": 9406.962890625, "learning_rate": 3.972972972972973e-05, "loss": 0.0732, "step": 405 }, { "epoch": 2.569620253164557, "grad_norm": 13133.2783203125, "learning_rate": 3.969594594594595e-05, "loss": 0.0697, "step": 406 }, { "epoch": 2.5759493670886076, "grad_norm": 8597.294921875, "learning_rate": 3.9662162162162165e-05, "loss": 0.1011, "step": 407 }, { "epoch": 2.5822784810126582, "grad_norm": 8608.1376953125, "learning_rate": 3.962837837837838e-05, "loss": 0.0787, "step": 408 }, { "epoch": 2.588607594936709, "grad_norm": 11194.4111328125, "learning_rate": 3.95945945945946e-05, "loss": 0.0651, "step": 409 }, { "epoch": 2.5949367088607596, "grad_norm": 8102.685546875, "learning_rate": 3.956081081081081e-05, "loss": 0.0631, "step": 410 }, { "epoch": 2.6012658227848102, "grad_norm": 8613.3125, "learning_rate": 3.952702702702703e-05, "loss": 0.088, "step": 411 }, { "epoch": 2.607594936708861, "grad_norm": 10092.728515625, "learning_rate": 3.9493243243243245e-05, "loss": 0.0803, "step": 412 }, { "epoch": 2.6139240506329116, "grad_norm": 9444.9150390625, "learning_rate": 3.945945945945946e-05, "loss": 0.1011, "step": 413 }, { "epoch": 2.620253164556962, "grad_norm": 8225.3447265625, "learning_rate": 3.942567567567568e-05, "loss": 0.0789, "step": 414 }, { "epoch": 2.6265822784810124, "grad_norm": 9002.62890625, "learning_rate": 3.9391891891891894e-05, "loss": 0.0778, "step": 415 }, { "epoch": 2.632911392405063, "grad_norm": 9614.5537109375, "learning_rate": 3.935810810810811e-05, "loss": 0.0815, "step": 416 }, { "epoch": 2.6392405063291138, "grad_norm": 10236.607421875, "learning_rate": 3.9324324324324326e-05, "loss": 0.0667, "step": 417 }, { "epoch": 2.6455696202531644, "grad_norm": 8224.3935546875, "learning_rate": 3.929054054054054e-05, "loss": 0.0769, "step": 418 }, { "epoch": 2.651898734177215, "grad_norm": 7233.70849609375, "learning_rate": 3.925675675675676e-05, "loss": 0.0662, "step": 419 }, { "epoch": 2.6582278481012658, "grad_norm": 7980.392578125, "learning_rate": 3.9222972972972974e-05, "loss": 0.0514, "step": 420 }, { "epoch": 2.6645569620253164, "grad_norm": 7371.083984375, "learning_rate": 3.918918918918919e-05, "loss": 0.0718, "step": 421 }, { "epoch": 2.670886075949367, "grad_norm": 6202.79150390625, "learning_rate": 3.9155405405405406e-05, "loss": 0.0799, "step": 422 }, { "epoch": 2.6772151898734178, "grad_norm": 7815.90673828125, "learning_rate": 3.912162162162162e-05, "loss": 0.0653, "step": 423 }, { "epoch": 2.6835443037974684, "grad_norm": 11966.244140625, "learning_rate": 3.908783783783784e-05, "loss": 0.0765, "step": 424 }, { "epoch": 2.689873417721519, "grad_norm": 6839.54638671875, "learning_rate": 3.9054054054054055e-05, "loss": 0.0636, "step": 425 }, { "epoch": 2.6962025316455698, "grad_norm": 9010.412109375, "learning_rate": 3.902027027027027e-05, "loss": 0.0754, "step": 426 }, { "epoch": 2.7025316455696204, "grad_norm": 5709.07666015625, "learning_rate": 3.898648648648649e-05, "loss": 0.0587, "step": 427 }, { "epoch": 2.708860759493671, "grad_norm": 8216.10546875, "learning_rate": 3.89527027027027e-05, "loss": 0.0661, "step": 428 }, { "epoch": 2.7151898734177218, "grad_norm": 12754.7275390625, "learning_rate": 3.8918918918918926e-05, "loss": 0.0894, "step": 429 }, { "epoch": 2.721518987341772, "grad_norm": 10178.55859375, "learning_rate": 3.8885135135135135e-05, "loss": 0.0921, "step": 430 }, { "epoch": 2.7278481012658227, "grad_norm": 8901.2939453125, "learning_rate": 3.885135135135135e-05, "loss": 0.0696, "step": 431 }, { "epoch": 2.7341772151898733, "grad_norm": 10524.263671875, "learning_rate": 3.881756756756757e-05, "loss": 0.0791, "step": 432 }, { "epoch": 2.740506329113924, "grad_norm": 6828.2216796875, "learning_rate": 3.8783783783783784e-05, "loss": 0.0591, "step": 433 }, { "epoch": 2.7468354430379747, "grad_norm": 22039.212890625, "learning_rate": 3.875e-05, "loss": 0.0853, "step": 434 }, { "epoch": 2.7531645569620253, "grad_norm": 6910.13720703125, "learning_rate": 3.8716216216216216e-05, "loss": 0.0776, "step": 435 }, { "epoch": 2.759493670886076, "grad_norm": 6844.8173828125, "learning_rate": 3.868243243243244e-05, "loss": 0.0704, "step": 436 }, { "epoch": 2.7658227848101267, "grad_norm": 8972.1015625, "learning_rate": 3.864864864864865e-05, "loss": 0.0806, "step": 437 }, { "epoch": 2.7721518987341773, "grad_norm": 10418.728515625, "learning_rate": 3.861486486486487e-05, "loss": 0.0872, "step": 438 }, { "epoch": 2.778481012658228, "grad_norm": 12084.083984375, "learning_rate": 3.858108108108108e-05, "loss": 0.0871, "step": 439 }, { "epoch": 2.7848101265822782, "grad_norm": 9345.3466796875, "learning_rate": 3.85472972972973e-05, "loss": 0.0763, "step": 440 }, { "epoch": 2.791139240506329, "grad_norm": 12591.826171875, "learning_rate": 3.851351351351351e-05, "loss": 0.0763, "step": 441 }, { "epoch": 2.7974683544303796, "grad_norm": 9986.5146484375, "learning_rate": 3.847972972972973e-05, "loss": 0.0803, "step": 442 }, { "epoch": 2.8037974683544302, "grad_norm": 7556.04541015625, "learning_rate": 3.844594594594595e-05, "loss": 0.0604, "step": 443 }, { "epoch": 2.810126582278481, "grad_norm": 8989.7294921875, "learning_rate": 3.841216216216216e-05, "loss": 0.078, "step": 444 }, { "epoch": 2.8164556962025316, "grad_norm": 12331.015625, "learning_rate": 3.8378378378378384e-05, "loss": 0.0588, "step": 445 }, { "epoch": 2.8227848101265822, "grad_norm": 13667.3115234375, "learning_rate": 3.8344594594594594e-05, "loss": 0.0662, "step": 446 }, { "epoch": 2.829113924050633, "grad_norm": 8020.830078125, "learning_rate": 3.831081081081081e-05, "loss": 0.0791, "step": 447 }, { "epoch": 2.8354430379746836, "grad_norm": 7952.17041015625, "learning_rate": 3.827702702702703e-05, "loss": 0.0611, "step": 448 }, { "epoch": 2.8417721518987342, "grad_norm": 12190.7470703125, "learning_rate": 3.824324324324324e-05, "loss": 0.0647, "step": 449 }, { "epoch": 2.848101265822785, "grad_norm": 8166.4541015625, "learning_rate": 3.8209459459459465e-05, "loss": 0.0655, "step": 450 }, { "epoch": 2.8544303797468356, "grad_norm": 9121.451171875, "learning_rate": 3.8175675675675674e-05, "loss": 0.0805, "step": 451 }, { "epoch": 2.8607594936708862, "grad_norm": 16799.4765625, "learning_rate": 3.81418918918919e-05, "loss": 0.0892, "step": 452 }, { "epoch": 2.867088607594937, "grad_norm": 7433.54541015625, "learning_rate": 3.8108108108108106e-05, "loss": 0.0677, "step": 453 }, { "epoch": 2.8734177215189876, "grad_norm": 10253.96875, "learning_rate": 3.807432432432433e-05, "loss": 0.0831, "step": 454 }, { "epoch": 2.879746835443038, "grad_norm": 8681.88671875, "learning_rate": 3.8040540540540545e-05, "loss": 0.0892, "step": 455 }, { "epoch": 2.8860759493670884, "grad_norm": 8994.2880859375, "learning_rate": 3.8006756756756755e-05, "loss": 0.0851, "step": 456 }, { "epoch": 2.892405063291139, "grad_norm": 8148.85595703125, "learning_rate": 3.797297297297298e-05, "loss": 0.0794, "step": 457 }, { "epoch": 2.8987341772151898, "grad_norm": 9296.80078125, "learning_rate": 3.793918918918919e-05, "loss": 0.0735, "step": 458 }, { "epoch": 2.9050632911392404, "grad_norm": 11051.423828125, "learning_rate": 3.790540540540541e-05, "loss": 0.0783, "step": 459 }, { "epoch": 2.911392405063291, "grad_norm": 12645.568359375, "learning_rate": 3.787162162162162e-05, "loss": 0.0718, "step": 460 }, { "epoch": 2.9177215189873418, "grad_norm": 27510.95703125, "learning_rate": 3.783783783783784e-05, "loss": 0.1, "step": 461 }, { "epoch": 2.9240506329113924, "grad_norm": 9283.3232421875, "learning_rate": 3.780405405405406e-05, "loss": 0.0681, "step": 462 }, { "epoch": 2.930379746835443, "grad_norm": 10467.9775390625, "learning_rate": 3.777027027027027e-05, "loss": 0.0713, "step": 463 }, { "epoch": 2.9367088607594938, "grad_norm": 13628.390625, "learning_rate": 3.773648648648649e-05, "loss": 0.0753, "step": 464 }, { "epoch": 2.9430379746835444, "grad_norm": 7285.78271484375, "learning_rate": 3.77027027027027e-05, "loss": 0.0718, "step": 465 }, { "epoch": 2.9493670886075947, "grad_norm": 8366.50390625, "learning_rate": 3.766891891891892e-05, "loss": 0.0707, "step": 466 }, { "epoch": 2.9556962025316453, "grad_norm": 8252.01953125, "learning_rate": 3.763513513513513e-05, "loss": 0.0868, "step": 467 }, { "epoch": 2.962025316455696, "grad_norm": 48065.8515625, "learning_rate": 3.7601351351351355e-05, "loss": 0.1086, "step": 468 }, { "epoch": 2.9683544303797467, "grad_norm": 11955.3662109375, "learning_rate": 3.756756756756757e-05, "loss": 0.0632, "step": 469 }, { "epoch": 2.9746835443037973, "grad_norm": 12909.9287109375, "learning_rate": 3.753378378378379e-05, "loss": 0.0803, "step": 470 }, { "epoch": 2.981012658227848, "grad_norm": 8998.1640625, "learning_rate": 3.7500000000000003e-05, "loss": 0.0695, "step": 471 }, { "epoch": 2.9873417721518987, "grad_norm": 9851.7529296875, "learning_rate": 3.746621621621621e-05, "loss": 0.066, "step": 472 }, { "epoch": 2.9936708860759493, "grad_norm": 10714.15625, "learning_rate": 3.7432432432432436e-05, "loss": 0.0747, "step": 473 }, { "epoch": 3.0, "grad_norm": 39123.7265625, "learning_rate": 3.739864864864865e-05, "loss": 0.0796, "step": 474 }, { "epoch": 3.0, "eval_f1_macro": 0.15793885389623852, "eval_f1_micro": 0.5037593984962406, "eval_loss": 0.07351958006620407, "eval_precision": 0.8170731707317073, "eval_recall": 0.3641304347826087, "eval_runtime": 1.1705, "eval_samples_per_second": 359.687, "eval_steps_per_second": 15.379, "step": 474 }, { "epoch": 3.0063291139240507, "grad_norm": 7408.00048828125, "learning_rate": 3.736486486486487e-05, "loss": 0.0651, "step": 475 }, { "epoch": 3.0126582278481013, "grad_norm": 10191.9541015625, "learning_rate": 3.7331081081081084e-05, "loss": 0.0841, "step": 476 }, { "epoch": 3.018987341772152, "grad_norm": 14755.0068359375, "learning_rate": 3.72972972972973e-05, "loss": 0.0957, "step": 477 }, { "epoch": 3.0253164556962027, "grad_norm": 8386.5361328125, "learning_rate": 3.7263513513513516e-05, "loss": 0.0727, "step": 478 }, { "epoch": 3.0316455696202533, "grad_norm": 10756.5322265625, "learning_rate": 3.722972972972973e-05, "loss": 0.0748, "step": 479 }, { "epoch": 3.037974683544304, "grad_norm": 8717.2275390625, "learning_rate": 3.719594594594595e-05, "loss": 0.0615, "step": 480 }, { "epoch": 3.0443037974683542, "grad_norm": 9173.341796875, "learning_rate": 3.7162162162162165e-05, "loss": 0.0597, "step": 481 }, { "epoch": 3.050632911392405, "grad_norm": 7230.5771484375, "learning_rate": 3.712837837837838e-05, "loss": 0.0743, "step": 482 }, { "epoch": 3.0569620253164556, "grad_norm": 5801.44873046875, "learning_rate": 3.70945945945946e-05, "loss": 0.0558, "step": 483 }, { "epoch": 3.0632911392405062, "grad_norm": 9158.3759765625, "learning_rate": 3.706081081081081e-05, "loss": 0.0781, "step": 484 }, { "epoch": 3.069620253164557, "grad_norm": 11292.8134765625, "learning_rate": 3.702702702702703e-05, "loss": 0.0721, "step": 485 }, { "epoch": 3.0759493670886076, "grad_norm": 8146.35400390625, "learning_rate": 3.6993243243243245e-05, "loss": 0.0476, "step": 486 }, { "epoch": 3.0822784810126582, "grad_norm": 7871.75146484375, "learning_rate": 3.695945945945946e-05, "loss": 0.0727, "step": 487 }, { "epoch": 3.088607594936709, "grad_norm": 9776.5439453125, "learning_rate": 3.692567567567568e-05, "loss": 0.0846, "step": 488 }, { "epoch": 3.0949367088607596, "grad_norm": 7157.787109375, "learning_rate": 3.6891891891891894e-05, "loss": 0.0658, "step": 489 }, { "epoch": 3.1012658227848102, "grad_norm": 8743.6484375, "learning_rate": 3.685810810810811e-05, "loss": 0.0653, "step": 490 }, { "epoch": 3.107594936708861, "grad_norm": 18645.6484375, "learning_rate": 3.6824324324324326e-05, "loss": 0.0624, "step": 491 }, { "epoch": 3.1139240506329116, "grad_norm": 17745.140625, "learning_rate": 3.679054054054054e-05, "loss": 0.0794, "step": 492 }, { "epoch": 3.1202531645569622, "grad_norm": 8325.162109375, "learning_rate": 3.675675675675676e-05, "loss": 0.0711, "step": 493 }, { "epoch": 3.1265822784810124, "grad_norm": 7614.90869140625, "learning_rate": 3.6722972972972974e-05, "loss": 0.0661, "step": 494 }, { "epoch": 3.132911392405063, "grad_norm": 8207.1787109375, "learning_rate": 3.668918918918919e-05, "loss": 0.0579, "step": 495 }, { "epoch": 3.1392405063291138, "grad_norm": 8822.5703125, "learning_rate": 3.665540540540541e-05, "loss": 0.0694, "step": 496 }, { "epoch": 3.1455696202531644, "grad_norm": 7685.3583984375, "learning_rate": 3.662162162162162e-05, "loss": 0.0637, "step": 497 }, { "epoch": 3.151898734177215, "grad_norm": 7975.06787109375, "learning_rate": 3.658783783783784e-05, "loss": 0.0667, "step": 498 }, { "epoch": 3.1582278481012658, "grad_norm": 6882.64013671875, "learning_rate": 3.6554054054054055e-05, "loss": 0.0547, "step": 499 }, { "epoch": 3.1645569620253164, "grad_norm": 8058.65576171875, "learning_rate": 3.652027027027027e-05, "loss": 0.0633, "step": 500 }, { "epoch": 3.170886075949367, "grad_norm": 8638.927734375, "learning_rate": 3.648648648648649e-05, "loss": 0.0758, "step": 501 }, { "epoch": 3.1772151898734178, "grad_norm": 7627.6552734375, "learning_rate": 3.6452702702702703e-05, "loss": 0.0748, "step": 502 }, { "epoch": 3.1835443037974684, "grad_norm": 5833.21728515625, "learning_rate": 3.641891891891892e-05, "loss": 0.0495, "step": 503 }, { "epoch": 3.189873417721519, "grad_norm": 7546.7890625, "learning_rate": 3.6385135135135136e-05, "loss": 0.0675, "step": 504 }, { "epoch": 3.1962025316455698, "grad_norm": 7546.38818359375, "learning_rate": 3.635135135135135e-05, "loss": 0.0533, "step": 505 }, { "epoch": 3.2025316455696204, "grad_norm": 10206.15234375, "learning_rate": 3.631756756756757e-05, "loss": 0.0803, "step": 506 }, { "epoch": 3.208860759493671, "grad_norm": 8699.2138671875, "learning_rate": 3.6283783783783784e-05, "loss": 0.0525, "step": 507 }, { "epoch": 3.2151898734177213, "grad_norm": 7206.87548828125, "learning_rate": 3.625e-05, "loss": 0.0643, "step": 508 }, { "epoch": 3.221518987341772, "grad_norm": 7428.94775390625, "learning_rate": 3.621621621621622e-05, "loss": 0.0568, "step": 509 }, { "epoch": 3.2278481012658227, "grad_norm": 10053.6455078125, "learning_rate": 3.618243243243243e-05, "loss": 0.0675, "step": 510 }, { "epoch": 3.2341772151898733, "grad_norm": 9338.541015625, "learning_rate": 3.6148648648648655e-05, "loss": 0.0626, "step": 511 }, { "epoch": 3.240506329113924, "grad_norm": 8473.140625, "learning_rate": 3.6114864864864865e-05, "loss": 0.067, "step": 512 }, { "epoch": 3.2468354430379747, "grad_norm": 8531.408203125, "learning_rate": 3.608108108108108e-05, "loss": 0.0542, "step": 513 }, { "epoch": 3.2531645569620253, "grad_norm": 6944.78662109375, "learning_rate": 3.60472972972973e-05, "loss": 0.0588, "step": 514 }, { "epoch": 3.259493670886076, "grad_norm": 7333.8125, "learning_rate": 3.601351351351351e-05, "loss": 0.0648, "step": 515 }, { "epoch": 3.2658227848101267, "grad_norm": 7603.05419921875, "learning_rate": 3.5979729729729736e-05, "loss": 0.0496, "step": 516 }, { "epoch": 3.2721518987341773, "grad_norm": 7347.0517578125, "learning_rate": 3.5945945945945945e-05, "loss": 0.0602, "step": 517 }, { "epoch": 3.278481012658228, "grad_norm": 8512.7216796875, "learning_rate": 3.591216216216217e-05, "loss": 0.065, "step": 518 }, { "epoch": 3.2848101265822787, "grad_norm": 7576.22998046875, "learning_rate": 3.587837837837838e-05, "loss": 0.0436, "step": 519 }, { "epoch": 3.291139240506329, "grad_norm": 7023.65380859375, "learning_rate": 3.5844594594594594e-05, "loss": 0.0545, "step": 520 }, { "epoch": 3.2974683544303796, "grad_norm": 7091.69140625, "learning_rate": 3.581081081081081e-05, "loss": 0.0627, "step": 521 }, { "epoch": 3.3037974683544302, "grad_norm": 10481.8798828125, "learning_rate": 3.5777027027027026e-05, "loss": 0.0521, "step": 522 }, { "epoch": 3.310126582278481, "grad_norm": 10738.923828125, "learning_rate": 3.574324324324325e-05, "loss": 0.0757, "step": 523 }, { "epoch": 3.3164556962025316, "grad_norm": 7190.3408203125, "learning_rate": 3.570945945945946e-05, "loss": 0.0506, "step": 524 }, { "epoch": 3.3227848101265822, "grad_norm": 8040.017578125, "learning_rate": 3.567567567567568e-05, "loss": 0.0643, "step": 525 }, { "epoch": 3.329113924050633, "grad_norm": 7625.2080078125, "learning_rate": 3.564189189189189e-05, "loss": 0.0675, "step": 526 }, { "epoch": 3.3354430379746836, "grad_norm": 11968.021484375, "learning_rate": 3.5608108108108113e-05, "loss": 0.0586, "step": 527 }, { "epoch": 3.3417721518987342, "grad_norm": 8314.00390625, "learning_rate": 3.557432432432433e-05, "loss": 0.0553, "step": 528 }, { "epoch": 3.348101265822785, "grad_norm": 8011.75927734375, "learning_rate": 3.554054054054054e-05, "loss": 0.073, "step": 529 }, { "epoch": 3.3544303797468356, "grad_norm": 7680.171875, "learning_rate": 3.550675675675676e-05, "loss": 0.0637, "step": 530 }, { "epoch": 3.3607594936708862, "grad_norm": 9702.4873046875, "learning_rate": 3.547297297297297e-05, "loss": 0.0483, "step": 531 }, { "epoch": 3.367088607594937, "grad_norm": 7104.0302734375, "learning_rate": 3.5439189189189194e-05, "loss": 0.0607, "step": 532 }, { "epoch": 3.3734177215189876, "grad_norm": 7849.912109375, "learning_rate": 3.5405405405405403e-05, "loss": 0.0565, "step": 533 }, { "epoch": 3.379746835443038, "grad_norm": 6671.203125, "learning_rate": 3.5371621621621626e-05, "loss": 0.0498, "step": 534 }, { "epoch": 3.3860759493670884, "grad_norm": 6492.68896484375, "learning_rate": 3.533783783783784e-05, "loss": 0.0598, "step": 535 }, { "epoch": 3.392405063291139, "grad_norm": 7108.591796875, "learning_rate": 3.530405405405405e-05, "loss": 0.0486, "step": 536 }, { "epoch": 3.3987341772151898, "grad_norm": 11836.6318359375, "learning_rate": 3.5270270270270275e-05, "loss": 0.0757, "step": 537 }, { "epoch": 3.4050632911392404, "grad_norm": 8737.64453125, "learning_rate": 3.5236486486486484e-05, "loss": 0.0519, "step": 538 }, { "epoch": 3.411392405063291, "grad_norm": 9047.123046875, "learning_rate": 3.520270270270271e-05, "loss": 0.0589, "step": 539 }, { "epoch": 3.4177215189873418, "grad_norm": 8261.876953125, "learning_rate": 3.5168918918918916e-05, "loss": 0.0596, "step": 540 }, { "epoch": 3.4240506329113924, "grad_norm": 7132.49755859375, "learning_rate": 3.513513513513514e-05, "loss": 0.0555, "step": 541 }, { "epoch": 3.430379746835443, "grad_norm": 8391.318359375, "learning_rate": 3.5101351351351355e-05, "loss": 0.054, "step": 542 }, { "epoch": 3.4367088607594938, "grad_norm": 6279.7265625, "learning_rate": 3.506756756756757e-05, "loss": 0.0515, "step": 543 }, { "epoch": 3.4430379746835444, "grad_norm": 8527.859375, "learning_rate": 3.503378378378379e-05, "loss": 0.064, "step": 544 }, { "epoch": 3.449367088607595, "grad_norm": 8436.900390625, "learning_rate": 3.5e-05, "loss": 0.0707, "step": 545 }, { "epoch": 3.4556962025316453, "grad_norm": 10160.3203125, "learning_rate": 3.496621621621622e-05, "loss": 0.0485, "step": 546 }, { "epoch": 3.462025316455696, "grad_norm": 8795.5185546875, "learning_rate": 3.493243243243243e-05, "loss": 0.0721, "step": 547 }, { "epoch": 3.4683544303797467, "grad_norm": 9170.884765625, "learning_rate": 3.489864864864865e-05, "loss": 0.06, "step": 548 }, { "epoch": 3.4746835443037973, "grad_norm": 7030.39794921875, "learning_rate": 3.486486486486487e-05, "loss": 0.0538, "step": 549 }, { "epoch": 3.481012658227848, "grad_norm": 7818.87060546875, "learning_rate": 3.4831081081081084e-05, "loss": 0.0716, "step": 550 }, { "epoch": 3.4873417721518987, "grad_norm": 7727.59375, "learning_rate": 3.47972972972973e-05, "loss": 0.0685, "step": 551 }, { "epoch": 3.4936708860759493, "grad_norm": 9165.5556640625, "learning_rate": 3.476351351351351e-05, "loss": 0.0622, "step": 552 }, { "epoch": 3.5, "grad_norm": 7467.8759765625, "learning_rate": 3.472972972972973e-05, "loss": 0.0645, "step": 553 }, { "epoch": 3.5063291139240507, "grad_norm": 9200.458984375, "learning_rate": 3.469594594594595e-05, "loss": 0.0645, "step": 554 }, { "epoch": 3.5126582278481013, "grad_norm": 7778.7099609375, "learning_rate": 3.4662162162162165e-05, "loss": 0.0627, "step": 555 }, { "epoch": 3.518987341772152, "grad_norm": 12766.3359375, "learning_rate": 3.462837837837838e-05, "loss": 0.0809, "step": 556 }, { "epoch": 3.5253164556962027, "grad_norm": 9366.955078125, "learning_rate": 3.45945945945946e-05, "loss": 0.0439, "step": 557 }, { "epoch": 3.5316455696202533, "grad_norm": 8687.7666015625, "learning_rate": 3.456081081081081e-05, "loss": 0.0521, "step": 558 }, { "epoch": 3.537974683544304, "grad_norm": 11210.19140625, "learning_rate": 3.452702702702703e-05, "loss": 0.0488, "step": 559 }, { "epoch": 3.5443037974683547, "grad_norm": 6372.29541015625, "learning_rate": 3.4493243243243246e-05, "loss": 0.0605, "step": 560 }, { "epoch": 3.5506329113924053, "grad_norm": 5499.072265625, "learning_rate": 3.445945945945946e-05, "loss": 0.0524, "step": 561 }, { "epoch": 3.5569620253164556, "grad_norm": 8271.888671875, "learning_rate": 3.442567567567568e-05, "loss": 0.0621, "step": 562 }, { "epoch": 3.5632911392405062, "grad_norm": 11741.26953125, "learning_rate": 3.4391891891891894e-05, "loss": 0.0729, "step": 563 }, { "epoch": 3.569620253164557, "grad_norm": 9335.8994140625, "learning_rate": 3.435810810810811e-05, "loss": 0.0633, "step": 564 }, { "epoch": 3.5759493670886076, "grad_norm": 8326.1435546875, "learning_rate": 3.4324324324324326e-05, "loss": 0.0638, "step": 565 }, { "epoch": 3.5822784810126582, "grad_norm": 10945.2470703125, "learning_rate": 3.429054054054054e-05, "loss": 0.0526, "step": 566 }, { "epoch": 3.588607594936709, "grad_norm": 5985.87939453125, "learning_rate": 3.425675675675676e-05, "loss": 0.0464, "step": 567 }, { "epoch": 3.5949367088607596, "grad_norm": 14322.7587890625, "learning_rate": 3.4222972972972975e-05, "loss": 0.0599, "step": 568 }, { "epoch": 3.6012658227848102, "grad_norm": 9323.373046875, "learning_rate": 3.418918918918919e-05, "loss": 0.0597, "step": 569 }, { "epoch": 3.607594936708861, "grad_norm": 6420.25, "learning_rate": 3.415540540540541e-05, "loss": 0.0531, "step": 570 }, { "epoch": 3.6139240506329116, "grad_norm": 10547.533203125, "learning_rate": 3.412162162162162e-05, "loss": 0.0528, "step": 571 }, { "epoch": 3.620253164556962, "grad_norm": 7691.53173828125, "learning_rate": 3.408783783783784e-05, "loss": 0.0535, "step": 572 }, { "epoch": 3.6265822784810124, "grad_norm": 8786.765625, "learning_rate": 3.4054054054054055e-05, "loss": 0.0681, "step": 573 }, { "epoch": 3.632911392405063, "grad_norm": 7157.61962890625, "learning_rate": 3.402027027027027e-05, "loss": 0.07, "step": 574 }, { "epoch": 3.6392405063291138, "grad_norm": 9294.3916015625, "learning_rate": 3.398648648648649e-05, "loss": 0.0639, "step": 575 }, { "epoch": 3.6455696202531644, "grad_norm": 8716.3095703125, "learning_rate": 3.3952702702702704e-05, "loss": 0.0632, "step": 576 }, { "epoch": 3.651898734177215, "grad_norm": 9241.38671875, "learning_rate": 3.391891891891892e-05, "loss": 0.0602, "step": 577 }, { "epoch": 3.6582278481012658, "grad_norm": 10046.1025390625, "learning_rate": 3.3885135135135136e-05, "loss": 0.0603, "step": 578 }, { "epoch": 3.6645569620253164, "grad_norm": 11961.8642578125, "learning_rate": 3.385135135135135e-05, "loss": 0.0694, "step": 579 }, { "epoch": 3.670886075949367, "grad_norm": 7798.8544921875, "learning_rate": 3.381756756756757e-05, "loss": 0.0582, "step": 580 }, { "epoch": 3.6772151898734178, "grad_norm": 11675.2451171875, "learning_rate": 3.3783783783783784e-05, "loss": 0.0564, "step": 581 }, { "epoch": 3.6835443037974684, "grad_norm": 7438.71337890625, "learning_rate": 3.375000000000001e-05, "loss": 0.0524, "step": 582 }, { "epoch": 3.689873417721519, "grad_norm": 9172.47265625, "learning_rate": 3.3716216216216217e-05, "loss": 0.056, "step": 583 }, { "epoch": 3.6962025316455698, "grad_norm": 11564.970703125, "learning_rate": 3.368243243243243e-05, "loss": 0.0608, "step": 584 }, { "epoch": 3.7025316455696204, "grad_norm": 9330.4248046875, "learning_rate": 3.364864864864865e-05, "loss": 0.0604, "step": 585 }, { "epoch": 3.708860759493671, "grad_norm": 8805.2333984375, "learning_rate": 3.3614864864864865e-05, "loss": 0.0668, "step": 586 }, { "epoch": 3.7151898734177218, "grad_norm": 7251.5224609375, "learning_rate": 3.358108108108108e-05, "loss": 0.0589, "step": 587 }, { "epoch": 3.721518987341772, "grad_norm": 10530.4169921875, "learning_rate": 3.35472972972973e-05, "loss": 0.0552, "step": 588 }, { "epoch": 3.7278481012658227, "grad_norm": 7462.43505859375, "learning_rate": 3.351351351351352e-05, "loss": 0.0573, "step": 589 }, { "epoch": 3.7341772151898733, "grad_norm": 6844.58447265625, "learning_rate": 3.347972972972973e-05, "loss": 0.0442, "step": 590 }, { "epoch": 3.740506329113924, "grad_norm": 10098.4296875, "learning_rate": 3.344594594594595e-05, "loss": 0.0508, "step": 591 }, { "epoch": 3.7468354430379747, "grad_norm": 9058.671875, "learning_rate": 3.341216216216216e-05, "loss": 0.077, "step": 592 }, { "epoch": 3.7531645569620253, "grad_norm": 9620.3671875, "learning_rate": 3.337837837837838e-05, "loss": 0.0717, "step": 593 }, { "epoch": 3.759493670886076, "grad_norm": 6988.28369140625, "learning_rate": 3.3344594594594594e-05, "loss": 0.0528, "step": 594 }, { "epoch": 3.7658227848101267, "grad_norm": 8957.4052734375, "learning_rate": 3.331081081081081e-05, "loss": 0.0518, "step": 595 }, { "epoch": 3.7721518987341773, "grad_norm": 9882.7001953125, "learning_rate": 3.327702702702703e-05, "loss": 0.0443, "step": 596 }, { "epoch": 3.778481012658228, "grad_norm": 9059.9267578125, "learning_rate": 3.324324324324324e-05, "loss": 0.0663, "step": 597 }, { "epoch": 3.7848101265822782, "grad_norm": 9318.1962890625, "learning_rate": 3.3209459459459465e-05, "loss": 0.0443, "step": 598 }, { "epoch": 3.791139240506329, "grad_norm": 7256.1806640625, "learning_rate": 3.3175675675675675e-05, "loss": 0.0431, "step": 599 }, { "epoch": 3.7974683544303796, "grad_norm": 8756.6875, "learning_rate": 3.314189189189189e-05, "loss": 0.0625, "step": 600 }, { "epoch": 3.8037974683544302, "grad_norm": 12375.884765625, "learning_rate": 3.310810810810811e-05, "loss": 0.0678, "step": 601 }, { "epoch": 3.810126582278481, "grad_norm": 8285.8359375, "learning_rate": 3.307432432432432e-05, "loss": 0.0621, "step": 602 }, { "epoch": 3.8164556962025316, "grad_norm": 9693.8310546875, "learning_rate": 3.3040540540540546e-05, "loss": 0.0573, "step": 603 }, { "epoch": 3.8227848101265822, "grad_norm": 9439.9521484375, "learning_rate": 3.3006756756756755e-05, "loss": 0.0606, "step": 604 }, { "epoch": 3.829113924050633, "grad_norm": 9318.8125, "learning_rate": 3.297297297297298e-05, "loss": 0.0459, "step": 605 }, { "epoch": 3.8354430379746836, "grad_norm": 7651.31494140625, "learning_rate": 3.293918918918919e-05, "loss": 0.0514, "step": 606 }, { "epoch": 3.8417721518987342, "grad_norm": 10018.3251953125, "learning_rate": 3.290540540540541e-05, "loss": 0.0576, "step": 607 }, { "epoch": 3.848101265822785, "grad_norm": 8550.7080078125, "learning_rate": 3.2871621621621627e-05, "loss": 0.0476, "step": 608 }, { "epoch": 3.8544303797468356, "grad_norm": 12940.9345703125, "learning_rate": 3.2837837837837836e-05, "loss": 0.0465, "step": 609 }, { "epoch": 3.8607594936708862, "grad_norm": 11908.7470703125, "learning_rate": 3.280405405405406e-05, "loss": 0.0855, "step": 610 }, { "epoch": 3.867088607594937, "grad_norm": 9688.65234375, "learning_rate": 3.277027027027027e-05, "loss": 0.0589, "step": 611 }, { "epoch": 3.8734177215189876, "grad_norm": 8413.7685546875, "learning_rate": 3.273648648648649e-05, "loss": 0.0548, "step": 612 }, { "epoch": 3.879746835443038, "grad_norm": 7900.341796875, "learning_rate": 3.27027027027027e-05, "loss": 0.0487, "step": 613 }, { "epoch": 3.8860759493670884, "grad_norm": 9638.9765625, "learning_rate": 3.266891891891892e-05, "loss": 0.0483, "step": 614 }, { "epoch": 3.892405063291139, "grad_norm": 6680.05908203125, "learning_rate": 3.263513513513514e-05, "loss": 0.0456, "step": 615 }, { "epoch": 3.8987341772151898, "grad_norm": 8335.7041015625, "learning_rate": 3.260135135135135e-05, "loss": 0.0554, "step": 616 }, { "epoch": 3.9050632911392404, "grad_norm": 18322.029296875, "learning_rate": 3.256756756756757e-05, "loss": 0.0561, "step": 617 }, { "epoch": 3.911392405063291, "grad_norm": 15999.255859375, "learning_rate": 3.253378378378378e-05, "loss": 0.0449, "step": 618 }, { "epoch": 3.9177215189873418, "grad_norm": 6070.3837890625, "learning_rate": 3.2500000000000004e-05, "loss": 0.0472, "step": 619 }, { "epoch": 3.9240506329113924, "grad_norm": 8545.580078125, "learning_rate": 3.246621621621621e-05, "loss": 0.0424, "step": 620 }, { "epoch": 3.930379746835443, "grad_norm": 7581.09521484375, "learning_rate": 3.2432432432432436e-05, "loss": 0.0555, "step": 621 }, { "epoch": 3.9367088607594938, "grad_norm": 10058.6083984375, "learning_rate": 3.239864864864865e-05, "loss": 0.05, "step": 622 }, { "epoch": 3.9430379746835444, "grad_norm": 10865.89453125, "learning_rate": 3.236486486486487e-05, "loss": 0.0503, "step": 623 }, { "epoch": 3.9493670886075947, "grad_norm": 6671.5703125, "learning_rate": 3.2331081081081085e-05, "loss": 0.0545, "step": 624 }, { "epoch": 3.9556962025316453, "grad_norm": 10356.5400390625, "learning_rate": 3.2297297297297294e-05, "loss": 0.0495, "step": 625 }, { "epoch": 3.962025316455696, "grad_norm": 8928.998046875, "learning_rate": 3.226351351351352e-05, "loss": 0.0497, "step": 626 }, { "epoch": 3.9683544303797467, "grad_norm": 9096.2890625, "learning_rate": 3.222972972972973e-05, "loss": 0.0566, "step": 627 }, { "epoch": 3.9746835443037973, "grad_norm": 9274.919921875, "learning_rate": 3.219594594594595e-05, "loss": 0.0463, "step": 628 }, { "epoch": 3.981012658227848, "grad_norm": 14988.7353515625, "learning_rate": 3.2162162162162165e-05, "loss": 0.0604, "step": 629 }, { "epoch": 3.9873417721518987, "grad_norm": 10277.8056640625, "learning_rate": 3.212837837837838e-05, "loss": 0.0352, "step": 630 }, { "epoch": 3.9936708860759493, "grad_norm": 11014.9443359375, "learning_rate": 3.20945945945946e-05, "loss": 0.0513, "step": 631 }, { "epoch": 4.0, "grad_norm": 11451.626953125, "learning_rate": 3.206081081081081e-05, "loss": 0.0548, "step": 632 }, { "epoch": 4.0, "eval_f1_macro": 0.4090525717962619, "eval_f1_micro": 0.6747252747252748, "eval_loss": 0.05690031498670578, "eval_precision": 0.8575418994413407, "eval_recall": 0.5561594202898551, "eval_runtime": 1.1703, "eval_samples_per_second": 359.736, "eval_steps_per_second": 15.381, "step": 632 }, { "epoch": 4.006329113924051, "grad_norm": 10997.3779296875, "learning_rate": 3.202702702702703e-05, "loss": 0.0468, "step": 633 }, { "epoch": 4.012658227848101, "grad_norm": 9440.734375, "learning_rate": 3.1993243243243246e-05, "loss": 0.0557, "step": 634 }, { "epoch": 4.018987341772152, "grad_norm": 13021.7578125, "learning_rate": 3.195945945945946e-05, "loss": 0.0641, "step": 635 }, { "epoch": 4.025316455696203, "grad_norm": 6062.69970703125, "learning_rate": 3.192567567567568e-05, "loss": 0.0441, "step": 636 }, { "epoch": 4.031645569620253, "grad_norm": 13082.333984375, "learning_rate": 3.1891891891891894e-05, "loss": 0.0575, "step": 637 }, { "epoch": 4.037974683544304, "grad_norm": 11378.2451171875, "learning_rate": 3.185810810810811e-05, "loss": 0.0608, "step": 638 }, { "epoch": 4.044303797468355, "grad_norm": 10331.8984375, "learning_rate": 3.1824324324324326e-05, "loss": 0.0447, "step": 639 }, { "epoch": 4.050632911392405, "grad_norm": 5609.83935546875, "learning_rate": 3.179054054054054e-05, "loss": 0.0527, "step": 640 }, { "epoch": 4.056962025316456, "grad_norm": 8994.7880859375, "learning_rate": 3.175675675675676e-05, "loss": 0.0436, "step": 641 }, { "epoch": 4.063291139240507, "grad_norm": 7765.244140625, "learning_rate": 3.1722972972972975e-05, "loss": 0.0532, "step": 642 }, { "epoch": 4.069620253164557, "grad_norm": 7181.189453125, "learning_rate": 3.168918918918919e-05, "loss": 0.0467, "step": 643 }, { "epoch": 4.075949367088608, "grad_norm": 6118.92724609375, "learning_rate": 3.165540540540541e-05, "loss": 0.0497, "step": 644 }, { "epoch": 4.082278481012658, "grad_norm": 7096.134765625, "learning_rate": 3.162162162162162e-05, "loss": 0.0532, "step": 645 }, { "epoch": 4.0886075949367084, "grad_norm": 15846.0224609375, "learning_rate": 3.158783783783784e-05, "loss": 0.0584, "step": 646 }, { "epoch": 4.094936708860759, "grad_norm": 6324.67626953125, "learning_rate": 3.1554054054054056e-05, "loss": 0.0507, "step": 647 }, { "epoch": 4.10126582278481, "grad_norm": 5261.75390625, "learning_rate": 3.152027027027027e-05, "loss": 0.0392, "step": 648 }, { "epoch": 4.1075949367088604, "grad_norm": 6921.0771484375, "learning_rate": 3.148648648648649e-05, "loss": 0.0655, "step": 649 }, { "epoch": 4.113924050632911, "grad_norm": 8186.12841796875, "learning_rate": 3.1452702702702704e-05, "loss": 0.0363, "step": 650 }, { "epoch": 4.120253164556962, "grad_norm": 8188.728515625, "learning_rate": 3.141891891891892e-05, "loss": 0.0422, "step": 651 }, { "epoch": 4.1265822784810124, "grad_norm": 7968.6455078125, "learning_rate": 3.1385135135135136e-05, "loss": 0.0439, "step": 652 }, { "epoch": 4.132911392405063, "grad_norm": 8850.1865234375, "learning_rate": 3.135135135135135e-05, "loss": 0.0568, "step": 653 }, { "epoch": 4.139240506329114, "grad_norm": 7348.0869140625, "learning_rate": 3.131756756756757e-05, "loss": 0.0395, "step": 654 }, { "epoch": 4.1455696202531644, "grad_norm": 8460.6416015625, "learning_rate": 3.1283783783783785e-05, "loss": 0.0372, "step": 655 }, { "epoch": 4.151898734177215, "grad_norm": 8838.3876953125, "learning_rate": 3.125e-05, "loss": 0.0591, "step": 656 }, { "epoch": 4.158227848101266, "grad_norm": 9124.9501953125, "learning_rate": 3.121621621621622e-05, "loss": 0.055, "step": 657 }, { "epoch": 4.1645569620253164, "grad_norm": 6832.74951171875, "learning_rate": 3.118243243243243e-05, "loss": 0.0362, "step": 658 }, { "epoch": 4.170886075949367, "grad_norm": 6187.7763671875, "learning_rate": 3.114864864864865e-05, "loss": 0.0415, "step": 659 }, { "epoch": 4.177215189873418, "grad_norm": 8622.8173828125, "learning_rate": 3.1114864864864865e-05, "loss": 0.0512, "step": 660 }, { "epoch": 4.1835443037974684, "grad_norm": 17032.814453125, "learning_rate": 3.108108108108108e-05, "loss": 0.0458, "step": 661 }, { "epoch": 4.189873417721519, "grad_norm": 5776.607421875, "learning_rate": 3.1047297297297304e-05, "loss": 0.0367, "step": 662 }, { "epoch": 4.19620253164557, "grad_norm": 9128.185546875, "learning_rate": 3.1013513513513514e-05, "loss": 0.0442, "step": 663 }, { "epoch": 4.2025316455696204, "grad_norm": 8221.7119140625, "learning_rate": 3.0979729729729736e-05, "loss": 0.05, "step": 664 }, { "epoch": 4.208860759493671, "grad_norm": 107356.15625, "learning_rate": 3.0945945945945946e-05, "loss": 0.0877, "step": 665 }, { "epoch": 4.215189873417722, "grad_norm": 7222.76953125, "learning_rate": 3.091216216216216e-05, "loss": 0.0413, "step": 666 }, { "epoch": 4.2215189873417724, "grad_norm": 9691.1396484375, "learning_rate": 3.087837837837838e-05, "loss": 0.0634, "step": 667 }, { "epoch": 4.227848101265823, "grad_norm": 8789.865234375, "learning_rate": 3.0844594594594594e-05, "loss": 0.0558, "step": 668 }, { "epoch": 4.234177215189874, "grad_norm": 9967.8515625, "learning_rate": 3.081081081081082e-05, "loss": 0.059, "step": 669 }, { "epoch": 4.2405063291139244, "grad_norm": 6880.11767578125, "learning_rate": 3.0777027027027026e-05, "loss": 0.0457, "step": 670 }, { "epoch": 4.246835443037975, "grad_norm": 11010.177734375, "learning_rate": 3.074324324324325e-05, "loss": 0.0468, "step": 671 }, { "epoch": 4.253164556962025, "grad_norm": 6721.37744140625, "learning_rate": 3.070945945945946e-05, "loss": 0.0474, "step": 672 }, { "epoch": 4.2594936708860756, "grad_norm": 7747.7275390625, "learning_rate": 3.0675675675675675e-05, "loss": 0.0431, "step": 673 }, { "epoch": 4.265822784810126, "grad_norm": 8913.4111328125, "learning_rate": 3.064189189189189e-05, "loss": 0.0433, "step": 674 }, { "epoch": 4.272151898734177, "grad_norm": 7080.31396484375, "learning_rate": 3.060810810810811e-05, "loss": 0.0597, "step": 675 }, { "epoch": 4.2784810126582276, "grad_norm": 6039.4228515625, "learning_rate": 3.057432432432433e-05, "loss": 0.0474, "step": 676 }, { "epoch": 4.284810126582278, "grad_norm": 6903.1904296875, "learning_rate": 3.054054054054054e-05, "loss": 0.0412, "step": 677 }, { "epoch": 4.291139240506329, "grad_norm": 7425.8564453125, "learning_rate": 3.050675675675676e-05, "loss": 0.0526, "step": 678 }, { "epoch": 4.2974683544303796, "grad_norm": 6692.85986328125, "learning_rate": 3.0472972972972975e-05, "loss": 0.0343, "step": 679 }, { "epoch": 4.30379746835443, "grad_norm": 8040.35498046875, "learning_rate": 3.0439189189189194e-05, "loss": 0.0432, "step": 680 }, { "epoch": 4.310126582278481, "grad_norm": 5882.66259765625, "learning_rate": 3.0405405405405407e-05, "loss": 0.0404, "step": 681 }, { "epoch": 4.3164556962025316, "grad_norm": 6225.2978515625, "learning_rate": 3.037162162162162e-05, "loss": 0.0378, "step": 682 }, { "epoch": 4.322784810126582, "grad_norm": 11462.9423828125, "learning_rate": 3.033783783783784e-05, "loss": 0.0443, "step": 683 }, { "epoch": 4.329113924050633, "grad_norm": 7344.65771484375, "learning_rate": 3.0304054054054056e-05, "loss": 0.0384, "step": 684 }, { "epoch": 4.3354430379746836, "grad_norm": 8084.49267578125, "learning_rate": 3.0270270270270272e-05, "loss": 0.0411, "step": 685 }, { "epoch": 4.341772151898734, "grad_norm": 7611.2880859375, "learning_rate": 3.0236486486486488e-05, "loss": 0.0376, "step": 686 }, { "epoch": 4.348101265822785, "grad_norm": 7097.18017578125, "learning_rate": 3.0202702702702707e-05, "loss": 0.047, "step": 687 }, { "epoch": 4.3544303797468356, "grad_norm": 9949.169921875, "learning_rate": 3.016891891891892e-05, "loss": 0.0641, "step": 688 }, { "epoch": 4.360759493670886, "grad_norm": 7348.31396484375, "learning_rate": 3.0135135135135133e-05, "loss": 0.0434, "step": 689 }, { "epoch": 4.367088607594937, "grad_norm": 5697.11962890625, "learning_rate": 3.0101351351351352e-05, "loss": 0.043, "step": 690 }, { "epoch": 4.3734177215189876, "grad_norm": 9205.546875, "learning_rate": 3.006756756756757e-05, "loss": 0.0431, "step": 691 }, { "epoch": 4.379746835443038, "grad_norm": 8709.1318359375, "learning_rate": 3.0033783783783788e-05, "loss": 0.041, "step": 692 }, { "epoch": 4.386075949367089, "grad_norm": 9211.4296875, "learning_rate": 3e-05, "loss": 0.0404, "step": 693 }, { "epoch": 4.3924050632911396, "grad_norm": 6616.51953125, "learning_rate": 2.996621621621622e-05, "loss": 0.0438, "step": 694 }, { "epoch": 4.39873417721519, "grad_norm": 10468.306640625, "learning_rate": 2.9932432432432433e-05, "loss": 0.0668, "step": 695 }, { "epoch": 4.405063291139241, "grad_norm": 11537.6640625, "learning_rate": 2.9898648648648653e-05, "loss": 0.0519, "step": 696 }, { "epoch": 4.4113924050632916, "grad_norm": 6648.3994140625, "learning_rate": 2.9864864864864865e-05, "loss": 0.0489, "step": 697 }, { "epoch": 4.417721518987342, "grad_norm": 12363.5537109375, "learning_rate": 2.983108108108108e-05, "loss": 0.0503, "step": 698 }, { "epoch": 4.424050632911392, "grad_norm": 10251.5107421875, "learning_rate": 2.97972972972973e-05, "loss": 0.0441, "step": 699 }, { "epoch": 4.430379746835443, "grad_norm": 5706.7109375, "learning_rate": 2.9763513513513514e-05, "loss": 0.0383, "step": 700 }, { "epoch": 4.436708860759493, "grad_norm": 5986.9462890625, "learning_rate": 2.9729729729729733e-05, "loss": 0.032, "step": 701 }, { "epoch": 4.443037974683544, "grad_norm": 11681.587890625, "learning_rate": 2.9695945945945946e-05, "loss": 0.0471, "step": 702 }, { "epoch": 4.449367088607595, "grad_norm": 11813.6162109375, "learning_rate": 2.9662162162162165e-05, "loss": 0.0625, "step": 703 }, { "epoch": 4.455696202531645, "grad_norm": 9749.1298828125, "learning_rate": 2.9628378378378378e-05, "loss": 0.0494, "step": 704 }, { "epoch": 4.462025316455696, "grad_norm": 9132.83203125, "learning_rate": 2.9594594594594594e-05, "loss": 0.0568, "step": 705 }, { "epoch": 4.468354430379747, "grad_norm": 7996.45263671875, "learning_rate": 2.9560810810810814e-05, "loss": 0.0523, "step": 706 }, { "epoch": 4.474683544303797, "grad_norm": 8587.306640625, "learning_rate": 2.9527027027027027e-05, "loss": 0.041, "step": 707 }, { "epoch": 4.481012658227848, "grad_norm": 10994.4951171875, "learning_rate": 2.9493243243243246e-05, "loss": 0.0384, "step": 708 }, { "epoch": 4.487341772151899, "grad_norm": 10991.349609375, "learning_rate": 2.945945945945946e-05, "loss": 0.06, "step": 709 }, { "epoch": 4.493670886075949, "grad_norm": 6595.40625, "learning_rate": 2.942567567567568e-05, "loss": 0.0439, "step": 710 }, { "epoch": 4.5, "grad_norm": 8146.27294921875, "learning_rate": 2.9391891891891894e-05, "loss": 0.048, "step": 711 }, { "epoch": 4.506329113924051, "grad_norm": 8883.908203125, "learning_rate": 2.935810810810811e-05, "loss": 0.0406, "step": 712 }, { "epoch": 4.512658227848101, "grad_norm": 10602.1904296875, "learning_rate": 2.9324324324324327e-05, "loss": 0.0425, "step": 713 }, { "epoch": 4.518987341772152, "grad_norm": 10199.419921875, "learning_rate": 2.929054054054054e-05, "loss": 0.0477, "step": 714 }, { "epoch": 4.525316455696203, "grad_norm": 7169.599609375, "learning_rate": 2.925675675675676e-05, "loss": 0.0394, "step": 715 }, { "epoch": 4.531645569620253, "grad_norm": 12651.5078125, "learning_rate": 2.9222972972972972e-05, "loss": 0.0357, "step": 716 }, { "epoch": 4.537974683544304, "grad_norm": 10456.5849609375, "learning_rate": 2.918918918918919e-05, "loss": 0.057, "step": 717 }, { "epoch": 4.544303797468355, "grad_norm": 8305.5, "learning_rate": 2.9155405405405407e-05, "loss": 0.0408, "step": 718 }, { "epoch": 4.550632911392405, "grad_norm": 11051.591796875, "learning_rate": 2.9121621621621627e-05, "loss": 0.0421, "step": 719 }, { "epoch": 4.556962025316456, "grad_norm": 7536.46630859375, "learning_rate": 2.908783783783784e-05, "loss": 0.0441, "step": 720 }, { "epoch": 4.563291139240507, "grad_norm": 8365.9033203125, "learning_rate": 2.9054054054054052e-05, "loss": 0.0373, "step": 721 }, { "epoch": 4.569620253164557, "grad_norm": 9909.716796875, "learning_rate": 2.9020270270270272e-05, "loss": 0.0457, "step": 722 }, { "epoch": 4.575949367088608, "grad_norm": 8759.39453125, "learning_rate": 2.8986486486486485e-05, "loss": 0.0495, "step": 723 }, { "epoch": 4.582278481012658, "grad_norm": 7634.19189453125, "learning_rate": 2.8952702702702704e-05, "loss": 0.0428, "step": 724 }, { "epoch": 4.588607594936709, "grad_norm": 7420.11572265625, "learning_rate": 2.891891891891892e-05, "loss": 0.0363, "step": 725 }, { "epoch": 4.594936708860759, "grad_norm": 8562.375, "learning_rate": 2.888513513513514e-05, "loss": 0.0513, "step": 726 }, { "epoch": 4.60126582278481, "grad_norm": 6980.2783203125, "learning_rate": 2.8851351351351352e-05, "loss": 0.0433, "step": 727 }, { "epoch": 4.6075949367088604, "grad_norm": 5367.28125, "learning_rate": 2.8817567567567572e-05, "loss": 0.0339, "step": 728 }, { "epoch": 4.613924050632911, "grad_norm": 8313.9580078125, "learning_rate": 2.8783783783783785e-05, "loss": 0.0351, "step": 729 }, { "epoch": 4.620253164556962, "grad_norm": 6639.298828125, "learning_rate": 2.8749999999999997e-05, "loss": 0.0371, "step": 730 }, { "epoch": 4.6265822784810124, "grad_norm": 6377.5634765625, "learning_rate": 2.8716216216216217e-05, "loss": 0.0278, "step": 731 }, { "epoch": 4.632911392405063, "grad_norm": 11055.9384765625, "learning_rate": 2.8682432432432433e-05, "loss": 0.0513, "step": 732 }, { "epoch": 4.639240506329114, "grad_norm": 9250.75, "learning_rate": 2.8648648648648653e-05, "loss": 0.0508, "step": 733 }, { "epoch": 4.6455696202531644, "grad_norm": 6888.50341796875, "learning_rate": 2.8614864864864865e-05, "loss": 0.034, "step": 734 }, { "epoch": 4.651898734177215, "grad_norm": 7488.60205078125, "learning_rate": 2.8581081081081085e-05, "loss": 0.0447, "step": 735 }, { "epoch": 4.658227848101266, "grad_norm": 8406.73828125, "learning_rate": 2.8547297297297298e-05, "loss": 0.0503, "step": 736 }, { "epoch": 4.6645569620253164, "grad_norm": 6598.59912109375, "learning_rate": 2.8513513513513514e-05, "loss": 0.0343, "step": 737 }, { "epoch": 4.670886075949367, "grad_norm": 8420.80078125, "learning_rate": 2.8479729729729733e-05, "loss": 0.0551, "step": 738 }, { "epoch": 4.677215189873418, "grad_norm": 11214.1796875, "learning_rate": 2.8445945945945946e-05, "loss": 0.0512, "step": 739 }, { "epoch": 4.6835443037974684, "grad_norm": 7545.01123046875, "learning_rate": 2.8412162162162166e-05, "loss": 0.0337, "step": 740 }, { "epoch": 4.689873417721519, "grad_norm": 7295.556640625, "learning_rate": 2.8378378378378378e-05, "loss": 0.0355, "step": 741 }, { "epoch": 4.69620253164557, "grad_norm": 5967.51123046875, "learning_rate": 2.8344594594594598e-05, "loss": 0.0208, "step": 742 }, { "epoch": 4.7025316455696204, "grad_norm": 8931.8935546875, "learning_rate": 2.831081081081081e-05, "loss": 0.0472, "step": 743 }, { "epoch": 4.708860759493671, "grad_norm": 6996.96630859375, "learning_rate": 2.827702702702703e-05, "loss": 0.0344, "step": 744 }, { "epoch": 4.715189873417722, "grad_norm": 9371.884765625, "learning_rate": 2.8243243243243246e-05, "loss": 0.056, "step": 745 }, { "epoch": 4.7215189873417724, "grad_norm": 6975.5634765625, "learning_rate": 2.820945945945946e-05, "loss": 0.0383, "step": 746 }, { "epoch": 4.727848101265823, "grad_norm": 9634.9619140625, "learning_rate": 2.817567567567568e-05, "loss": 0.0469, "step": 747 }, { "epoch": 4.734177215189874, "grad_norm": 8664.55859375, "learning_rate": 2.814189189189189e-05, "loss": 0.0362, "step": 748 }, { "epoch": 4.740506329113924, "grad_norm": 8140.240234375, "learning_rate": 2.810810810810811e-05, "loss": 0.0429, "step": 749 }, { "epoch": 4.746835443037975, "grad_norm": 10655.2490234375, "learning_rate": 2.8074324324324323e-05, "loss": 0.0496, "step": 750 }, { "epoch": 4.753164556962025, "grad_norm": 8171.65673828125, "learning_rate": 2.8040540540540543e-05, "loss": 0.0517, "step": 751 }, { "epoch": 4.759493670886076, "grad_norm": 8662.5390625, "learning_rate": 2.800675675675676e-05, "loss": 0.0548, "step": 752 }, { "epoch": 4.765822784810126, "grad_norm": 10266.0703125, "learning_rate": 2.7972972972972972e-05, "loss": 0.0494, "step": 753 }, { "epoch": 4.772151898734177, "grad_norm": 11253.0888671875, "learning_rate": 2.793918918918919e-05, "loss": 0.0417, "step": 754 }, { "epoch": 4.7784810126582276, "grad_norm": 8614.1044921875, "learning_rate": 2.7905405405405404e-05, "loss": 0.041, "step": 755 }, { "epoch": 4.784810126582278, "grad_norm": 13615.8740234375, "learning_rate": 2.7871621621621624e-05, "loss": 0.0467, "step": 756 }, { "epoch": 4.791139240506329, "grad_norm": 8073.25, "learning_rate": 2.7837837837837836e-05, "loss": 0.0497, "step": 757 }, { "epoch": 4.7974683544303796, "grad_norm": 10182.9951171875, "learning_rate": 2.7804054054054056e-05, "loss": 0.047, "step": 758 }, { "epoch": 4.80379746835443, "grad_norm": 10397.60546875, "learning_rate": 2.7770270270270272e-05, "loss": 0.0414, "step": 759 }, { "epoch": 4.810126582278481, "grad_norm": 8631.65625, "learning_rate": 2.773648648648649e-05, "loss": 0.0487, "step": 760 }, { "epoch": 4.8164556962025316, "grad_norm": 7660.07470703125, "learning_rate": 2.7702702702702704e-05, "loss": 0.0462, "step": 761 }, { "epoch": 4.822784810126582, "grad_norm": 10472.23828125, "learning_rate": 2.7668918918918917e-05, "loss": 0.0428, "step": 762 }, { "epoch": 4.829113924050633, "grad_norm": 8710.3515625, "learning_rate": 2.7635135135135136e-05, "loss": 0.0322, "step": 763 }, { "epoch": 4.8354430379746836, "grad_norm": 5946.4404296875, "learning_rate": 2.7601351351351353e-05, "loss": 0.0367, "step": 764 }, { "epoch": 4.841772151898734, "grad_norm": 7777.86376953125, "learning_rate": 2.7567567567567572e-05, "loss": 0.0374, "step": 765 }, { "epoch": 4.848101265822785, "grad_norm": 12082.22265625, "learning_rate": 2.7533783783783785e-05, "loss": 0.0436, "step": 766 }, { "epoch": 4.8544303797468356, "grad_norm": 7916.310546875, "learning_rate": 2.7500000000000004e-05, "loss": 0.0446, "step": 767 }, { "epoch": 4.860759493670886, "grad_norm": 7628.65576171875, "learning_rate": 2.7466216216216217e-05, "loss": 0.0389, "step": 768 }, { "epoch": 4.867088607594937, "grad_norm": 8458.556640625, "learning_rate": 2.743243243243243e-05, "loss": 0.0404, "step": 769 }, { "epoch": 4.8734177215189876, "grad_norm": 14158.23046875, "learning_rate": 2.739864864864865e-05, "loss": 0.0491, "step": 770 }, { "epoch": 4.879746835443038, "grad_norm": 15156.4462890625, "learning_rate": 2.7364864864864865e-05, "loss": 0.0312, "step": 771 }, { "epoch": 4.886075949367089, "grad_norm": 12796.4013671875, "learning_rate": 2.7331081081081085e-05, "loss": 0.0433, "step": 772 }, { "epoch": 4.8924050632911396, "grad_norm": 8927.6572265625, "learning_rate": 2.7297297297297298e-05, "loss": 0.0413, "step": 773 }, { "epoch": 4.89873417721519, "grad_norm": 7277.876953125, "learning_rate": 2.7263513513513517e-05, "loss": 0.0436, "step": 774 }, { "epoch": 4.905063291139241, "grad_norm": 9286.984375, "learning_rate": 2.722972972972973e-05, "loss": 0.0548, "step": 775 }, { "epoch": 4.911392405063291, "grad_norm": 7769.23681640625, "learning_rate": 2.719594594594595e-05, "loss": 0.0357, "step": 776 }, { "epoch": 4.917721518987342, "grad_norm": 9738.865234375, "learning_rate": 2.7162162162162162e-05, "loss": 0.0403, "step": 777 }, { "epoch": 4.924050632911392, "grad_norm": 9223.38671875, "learning_rate": 2.712837837837838e-05, "loss": 0.0403, "step": 778 }, { "epoch": 4.930379746835443, "grad_norm": 13988.603515625, "learning_rate": 2.7094594594594598e-05, "loss": 0.0522, "step": 779 }, { "epoch": 4.936708860759493, "grad_norm": 7779.23974609375, "learning_rate": 2.706081081081081e-05, "loss": 0.0385, "step": 780 }, { "epoch": 4.943037974683544, "grad_norm": 8951.58984375, "learning_rate": 2.702702702702703e-05, "loss": 0.0332, "step": 781 }, { "epoch": 4.949367088607595, "grad_norm": 10822.7275390625, "learning_rate": 2.6993243243243243e-05, "loss": 0.0379, "step": 782 }, { "epoch": 4.955696202531645, "grad_norm": 7082.67138671875, "learning_rate": 2.6959459459459462e-05, "loss": 0.0372, "step": 783 }, { "epoch": 4.962025316455696, "grad_norm": 10584.017578125, "learning_rate": 2.6925675675675675e-05, "loss": 0.0473, "step": 784 }, { "epoch": 4.968354430379747, "grad_norm": 9370.650390625, "learning_rate": 2.689189189189189e-05, "loss": 0.0287, "step": 785 }, { "epoch": 4.974683544303797, "grad_norm": 7702.18359375, "learning_rate": 2.685810810810811e-05, "loss": 0.0299, "step": 786 }, { "epoch": 4.981012658227848, "grad_norm": 10627.708984375, "learning_rate": 2.6824324324324324e-05, "loss": 0.0496, "step": 787 }, { "epoch": 4.987341772151899, "grad_norm": 14103.3076171875, "learning_rate": 2.6790540540540543e-05, "loss": 0.034, "step": 788 }, { "epoch": 4.993670886075949, "grad_norm": 5560.28515625, "learning_rate": 2.6756756756756756e-05, "loss": 0.0368, "step": 789 }, { "epoch": 5.0, "grad_norm": 10386.80078125, "learning_rate": 2.6722972972972975e-05, "loss": 0.0393, "step": 790 }, { "epoch": 5.0, "eval_f1_macro": 0.5855756927341754, "eval_f1_micro": 0.7699805068226121, "eval_loss": 0.046274758875370026, "eval_precision": 0.8333333333333334, "eval_recall": 0.7155797101449275, "eval_runtime": 1.1655, "eval_samples_per_second": 361.232, "eval_steps_per_second": 15.445, "step": 790 }, { "epoch": 5.006329113924051, "grad_norm": 12593.341796875, "learning_rate": 2.668918918918919e-05, "loss": 0.0414, "step": 791 }, { "epoch": 5.012658227848101, "grad_norm": 6522.4853515625, "learning_rate": 2.6655405405405408e-05, "loss": 0.0467, "step": 792 }, { "epoch": 5.018987341772152, "grad_norm": 11309.70703125, "learning_rate": 2.6621621621621624e-05, "loss": 0.0397, "step": 793 }, { "epoch": 5.025316455696203, "grad_norm": 6366.798828125, "learning_rate": 2.6587837837837836e-05, "loss": 0.0299, "step": 794 }, { "epoch": 5.031645569620253, "grad_norm": 6616.251953125, "learning_rate": 2.6554054054054056e-05, "loss": 0.0283, "step": 795 }, { "epoch": 5.037974683544304, "grad_norm": 5508.23583984375, "learning_rate": 2.652027027027027e-05, "loss": 0.0329, "step": 796 }, { "epoch": 5.044303797468355, "grad_norm": 6299.80810546875, "learning_rate": 2.6486486486486488e-05, "loss": 0.0363, "step": 797 }, { "epoch": 5.050632911392405, "grad_norm": 7451.53076171875, "learning_rate": 2.6452702702702704e-05, "loss": 0.039, "step": 798 }, { "epoch": 5.056962025316456, "grad_norm": 9284.0556640625, "learning_rate": 2.6418918918918924e-05, "loss": 0.035, "step": 799 }, { "epoch": 5.063291139240507, "grad_norm": 9438.8359375, "learning_rate": 2.6385135135135137e-05, "loss": 0.0336, "step": 800 }, { "epoch": 5.069620253164557, "grad_norm": 7013.9716796875, "learning_rate": 2.635135135135135e-05, "loss": 0.0322, "step": 801 }, { "epoch": 5.075949367088608, "grad_norm": 7698.412109375, "learning_rate": 2.631756756756757e-05, "loss": 0.0289, "step": 802 }, { "epoch": 5.082278481012658, "grad_norm": 5814.66162109375, "learning_rate": 2.628378378378378e-05, "loss": 0.0372, "step": 803 }, { "epoch": 5.0886075949367084, "grad_norm": 6100.14013671875, "learning_rate": 2.625e-05, "loss": 0.0307, "step": 804 }, { "epoch": 5.094936708860759, "grad_norm": 7859.7841796875, "learning_rate": 2.6216216216216217e-05, "loss": 0.0403, "step": 805 }, { "epoch": 5.10126582278481, "grad_norm": 9284.1767578125, "learning_rate": 2.6182432432432437e-05, "loss": 0.0424, "step": 806 }, { "epoch": 5.1075949367088604, "grad_norm": 6402.35791015625, "learning_rate": 2.614864864864865e-05, "loss": 0.0368, "step": 807 }, { "epoch": 5.113924050632911, "grad_norm": 5275.91796875, "learning_rate": 2.611486486486487e-05, "loss": 0.0292, "step": 808 }, { "epoch": 5.120253164556962, "grad_norm": 5919.50732421875, "learning_rate": 2.6081081081081082e-05, "loss": 0.0297, "step": 809 }, { "epoch": 5.1265822784810124, "grad_norm": 6436.8427734375, "learning_rate": 2.6047297297297298e-05, "loss": 0.0356, "step": 810 }, { "epoch": 5.132911392405063, "grad_norm": 6496.74609375, "learning_rate": 2.6013513513513514e-05, "loss": 0.0348, "step": 811 }, { "epoch": 5.139240506329114, "grad_norm": 11691.859375, "learning_rate": 2.597972972972973e-05, "loss": 0.0506, "step": 812 }, { "epoch": 5.1455696202531644, "grad_norm": 9779.119140625, "learning_rate": 2.594594594594595e-05, "loss": 0.0471, "step": 813 }, { "epoch": 5.151898734177215, "grad_norm": 6270.00732421875, "learning_rate": 2.5912162162162162e-05, "loss": 0.0335, "step": 814 }, { "epoch": 5.158227848101266, "grad_norm": 6758.7900390625, "learning_rate": 2.5878378378378382e-05, "loss": 0.0332, "step": 815 }, { "epoch": 5.1645569620253164, "grad_norm": 9958.078125, "learning_rate": 2.5844594594594595e-05, "loss": 0.0486, "step": 816 }, { "epoch": 5.170886075949367, "grad_norm": 7113.248046875, "learning_rate": 2.581081081081081e-05, "loss": 0.0335, "step": 817 }, { "epoch": 5.177215189873418, "grad_norm": 8138.22314453125, "learning_rate": 2.577702702702703e-05, "loss": 0.0435, "step": 818 }, { "epoch": 5.1835443037974684, "grad_norm": 4854.98779296875, "learning_rate": 2.5743243243243243e-05, "loss": 0.0383, "step": 819 }, { "epoch": 5.189873417721519, "grad_norm": 5897.86328125, "learning_rate": 2.5709459459459463e-05, "loss": 0.0278, "step": 820 }, { "epoch": 5.19620253164557, "grad_norm": 8125.529296875, "learning_rate": 2.5675675675675675e-05, "loss": 0.047, "step": 821 }, { "epoch": 5.2025316455696204, "grad_norm": 5742.8623046875, "learning_rate": 2.5641891891891895e-05, "loss": 0.0387, "step": 822 }, { "epoch": 5.208860759493671, "grad_norm": 5855.6357421875, "learning_rate": 2.5608108108108108e-05, "loss": 0.0381, "step": 823 }, { "epoch": 5.215189873417722, "grad_norm": 6269.19580078125, "learning_rate": 2.5574324324324327e-05, "loss": 0.0337, "step": 824 }, { "epoch": 5.2215189873417724, "grad_norm": 7474.1416015625, "learning_rate": 2.5540540540540543e-05, "loss": 0.0348, "step": 825 }, { "epoch": 5.227848101265823, "grad_norm": 6826.87109375, "learning_rate": 2.5506756756756756e-05, "loss": 0.0425, "step": 826 }, { "epoch": 5.234177215189874, "grad_norm": 7720.970703125, "learning_rate": 2.5472972972972975e-05, "loss": 0.0398, "step": 827 }, { "epoch": 5.2405063291139244, "grad_norm": 7963.91259765625, "learning_rate": 2.5439189189189188e-05, "loss": 0.0362, "step": 828 }, { "epoch": 5.246835443037975, "grad_norm": 6491.28076171875, "learning_rate": 2.5405405405405408e-05, "loss": 0.0357, "step": 829 }, { "epoch": 5.253164556962025, "grad_norm": 5566.71533203125, "learning_rate": 2.537162162162162e-05, "loss": 0.0335, "step": 830 }, { "epoch": 5.2594936708860756, "grad_norm": 6943.87109375, "learning_rate": 2.533783783783784e-05, "loss": 0.044, "step": 831 }, { "epoch": 5.265822784810126, "grad_norm": 6039.6279296875, "learning_rate": 2.5304054054054056e-05, "loss": 0.0294, "step": 832 }, { "epoch": 5.272151898734177, "grad_norm": 7632.47802734375, "learning_rate": 2.527027027027027e-05, "loss": 0.0337, "step": 833 }, { "epoch": 5.2784810126582276, "grad_norm": 6455.65673828125, "learning_rate": 2.5236486486486488e-05, "loss": 0.0411, "step": 834 }, { "epoch": 5.284810126582278, "grad_norm": 11528.9169921875, "learning_rate": 2.52027027027027e-05, "loss": 0.0465, "step": 835 }, { "epoch": 5.291139240506329, "grad_norm": 7994.81396484375, "learning_rate": 2.516891891891892e-05, "loss": 0.032, "step": 836 }, { "epoch": 5.2974683544303796, "grad_norm": 7460.7216796875, "learning_rate": 2.5135135135135133e-05, "loss": 0.034, "step": 837 }, { "epoch": 5.30379746835443, "grad_norm": 7139.52294921875, "learning_rate": 2.5101351351351353e-05, "loss": 0.0327, "step": 838 }, { "epoch": 5.310126582278481, "grad_norm": 5219.59423828125, "learning_rate": 2.506756756756757e-05, "loss": 0.0346, "step": 839 }, { "epoch": 5.3164556962025316, "grad_norm": 8553.697265625, "learning_rate": 2.503378378378379e-05, "loss": 0.0334, "step": 840 }, { "epoch": 5.322784810126582, "grad_norm": 9484.306640625, "learning_rate": 2.5e-05, "loss": 0.046, "step": 841 }, { "epoch": 5.329113924050633, "grad_norm": 8134.62060546875, "learning_rate": 2.4966216216216217e-05, "loss": 0.0421, "step": 842 }, { "epoch": 5.3354430379746836, "grad_norm": 11198.0615234375, "learning_rate": 2.4932432432432433e-05, "loss": 0.0432, "step": 843 }, { "epoch": 5.341772151898734, "grad_norm": 7134.146484375, "learning_rate": 2.489864864864865e-05, "loss": 0.0224, "step": 844 }, { "epoch": 5.348101265822785, "grad_norm": 7251.8720703125, "learning_rate": 2.486486486486487e-05, "loss": 0.0411, "step": 845 }, { "epoch": 5.3544303797468356, "grad_norm": 8283.4716796875, "learning_rate": 2.4831081081081082e-05, "loss": 0.0359, "step": 846 }, { "epoch": 5.360759493670886, "grad_norm": 7776.279296875, "learning_rate": 2.4797297297297298e-05, "loss": 0.0382, "step": 847 }, { "epoch": 5.367088607594937, "grad_norm": 10808.720703125, "learning_rate": 2.4763513513513514e-05, "loss": 0.0263, "step": 848 }, { "epoch": 5.3734177215189876, "grad_norm": 10174.880859375, "learning_rate": 2.472972972972973e-05, "loss": 0.0413, "step": 849 }, { "epoch": 5.379746835443038, "grad_norm": 6297.8896484375, "learning_rate": 2.4695945945945946e-05, "loss": 0.0409, "step": 850 }, { "epoch": 5.386075949367089, "grad_norm": 10160.265625, "learning_rate": 2.4662162162162162e-05, "loss": 0.0394, "step": 851 }, { "epoch": 5.3924050632911396, "grad_norm": 11262.28515625, "learning_rate": 2.4628378378378382e-05, "loss": 0.0441, "step": 852 }, { "epoch": 5.39873417721519, "grad_norm": 8249.0673828125, "learning_rate": 2.4594594594594598e-05, "loss": 0.023, "step": 853 }, { "epoch": 5.405063291139241, "grad_norm": 10288.6279296875, "learning_rate": 2.456081081081081e-05, "loss": 0.0466, "step": 854 }, { "epoch": 5.4113924050632916, "grad_norm": 10069.2626953125, "learning_rate": 2.4527027027027027e-05, "loss": 0.0424, "step": 855 }, { "epoch": 5.417721518987342, "grad_norm": 15838.0791015625, "learning_rate": 2.4493243243243243e-05, "loss": 0.0424, "step": 856 }, { "epoch": 5.424050632911392, "grad_norm": 6006.15869140625, "learning_rate": 2.445945945945946e-05, "loss": 0.0361, "step": 857 }, { "epoch": 5.430379746835443, "grad_norm": 5691.4404296875, "learning_rate": 2.442567567567568e-05, "loss": 0.0311, "step": 858 }, { "epoch": 5.436708860759493, "grad_norm": 10632.583984375, "learning_rate": 2.4391891891891895e-05, "loss": 0.0372, "step": 859 }, { "epoch": 5.443037974683544, "grad_norm": 5869.9248046875, "learning_rate": 2.435810810810811e-05, "loss": 0.0328, "step": 860 }, { "epoch": 5.449367088607595, "grad_norm": 8663.154296875, "learning_rate": 2.4324324324324327e-05, "loss": 0.0283, "step": 861 }, { "epoch": 5.455696202531645, "grad_norm": 6989.2490234375, "learning_rate": 2.429054054054054e-05, "loss": 0.0481, "step": 862 }, { "epoch": 5.462025316455696, "grad_norm": 10077.486328125, "learning_rate": 2.4256756756756756e-05, "loss": 0.0232, "step": 863 }, { "epoch": 5.468354430379747, "grad_norm": 8153.62744140625, "learning_rate": 2.4222972972972972e-05, "loss": 0.0339, "step": 864 }, { "epoch": 5.474683544303797, "grad_norm": 7247.41796875, "learning_rate": 2.418918918918919e-05, "loss": 0.0321, "step": 865 }, { "epoch": 5.481012658227848, "grad_norm": 8131.6650390625, "learning_rate": 2.4155405405405408e-05, "loss": 0.0372, "step": 866 }, { "epoch": 5.487341772151899, "grad_norm": 5943.17236328125, "learning_rate": 2.4121621621621624e-05, "loss": 0.0361, "step": 867 }, { "epoch": 5.493670886075949, "grad_norm": 9122.0810546875, "learning_rate": 2.408783783783784e-05, "loss": 0.0433, "step": 868 }, { "epoch": 5.5, "grad_norm": 6291.15966796875, "learning_rate": 2.4054054054054056e-05, "loss": 0.0352, "step": 869 }, { "epoch": 5.506329113924051, "grad_norm": 7388.47314453125, "learning_rate": 2.402027027027027e-05, "loss": 0.0284, "step": 870 }, { "epoch": 5.512658227848101, "grad_norm": 5885.41552734375, "learning_rate": 2.398648648648649e-05, "loss": 0.0238, "step": 871 }, { "epoch": 5.518987341772152, "grad_norm": 6217.32763671875, "learning_rate": 2.3952702702702705e-05, "loss": 0.0317, "step": 872 }, { "epoch": 5.525316455696203, "grad_norm": 16539.173828125, "learning_rate": 2.391891891891892e-05, "loss": 0.0335, "step": 873 }, { "epoch": 5.531645569620253, "grad_norm": 8517.193359375, "learning_rate": 2.3885135135135137e-05, "loss": 0.0395, "step": 874 }, { "epoch": 5.537974683544304, "grad_norm": 5955.572265625, "learning_rate": 2.3851351351351353e-05, "loss": 0.036, "step": 875 }, { "epoch": 5.544303797468355, "grad_norm": 7439.87939453125, "learning_rate": 2.381756756756757e-05, "loss": 0.0236, "step": 876 }, { "epoch": 5.550632911392405, "grad_norm": 13412.345703125, "learning_rate": 2.3783783783783785e-05, "loss": 0.0433, "step": 877 }, { "epoch": 5.556962025316456, "grad_norm": 10835.359375, "learning_rate": 2.375e-05, "loss": 0.032, "step": 878 }, { "epoch": 5.563291139240507, "grad_norm": 6443.19921875, "learning_rate": 2.3716216216216217e-05, "loss": 0.0384, "step": 879 }, { "epoch": 5.569620253164557, "grad_norm": 7003.42333984375, "learning_rate": 2.3682432432432434e-05, "loss": 0.0353, "step": 880 }, { "epoch": 5.575949367088608, "grad_norm": 21326.369140625, "learning_rate": 2.364864864864865e-05, "loss": 0.0468, "step": 881 }, { "epoch": 5.582278481012658, "grad_norm": 18726.099609375, "learning_rate": 2.3614864864864866e-05, "loss": 0.0512, "step": 882 }, { "epoch": 5.588607594936709, "grad_norm": 11413.953125, "learning_rate": 2.3581081081081082e-05, "loss": 0.043, "step": 883 }, { "epoch": 5.594936708860759, "grad_norm": 7350.96923828125, "learning_rate": 2.3547297297297298e-05, "loss": 0.0375, "step": 884 }, { "epoch": 5.60126582278481, "grad_norm": 5975.85595703125, "learning_rate": 2.3513513513513518e-05, "loss": 0.0354, "step": 885 }, { "epoch": 5.6075949367088604, "grad_norm": 6052.8994140625, "learning_rate": 2.347972972972973e-05, "loss": 0.0261, "step": 886 }, { "epoch": 5.613924050632911, "grad_norm": 6177.92724609375, "learning_rate": 2.3445945945945946e-05, "loss": 0.0348, "step": 887 }, { "epoch": 5.620253164556962, "grad_norm": 5251.82861328125, "learning_rate": 2.3412162162162163e-05, "loss": 0.028, "step": 888 }, { "epoch": 5.6265822784810124, "grad_norm": 7077.78466796875, "learning_rate": 2.337837837837838e-05, "loss": 0.0274, "step": 889 }, { "epoch": 5.632911392405063, "grad_norm": 5749.53173828125, "learning_rate": 2.3344594594594595e-05, "loss": 0.0299, "step": 890 }, { "epoch": 5.639240506329114, "grad_norm": 6001.6572265625, "learning_rate": 2.331081081081081e-05, "loss": 0.0249, "step": 891 }, { "epoch": 5.6455696202531644, "grad_norm": 5857.076171875, "learning_rate": 2.327702702702703e-05, "loss": 0.027, "step": 892 }, { "epoch": 5.651898734177215, "grad_norm": 7598.8203125, "learning_rate": 2.3243243243243247e-05, "loss": 0.0225, "step": 893 }, { "epoch": 5.658227848101266, "grad_norm": 6442.87939453125, "learning_rate": 2.320945945945946e-05, "loss": 0.0289, "step": 894 }, { "epoch": 5.6645569620253164, "grad_norm": 11215.466796875, "learning_rate": 2.3175675675675675e-05, "loss": 0.0392, "step": 895 }, { "epoch": 5.670886075949367, "grad_norm": 7091.537109375, "learning_rate": 2.314189189189189e-05, "loss": 0.0379, "step": 896 }, { "epoch": 5.677215189873418, "grad_norm": 6646.45654296875, "learning_rate": 2.3108108108108108e-05, "loss": 0.0353, "step": 897 }, { "epoch": 5.6835443037974684, "grad_norm": 5704.23876953125, "learning_rate": 2.3074324324324327e-05, "loss": 0.0254, "step": 898 }, { "epoch": 5.689873417721519, "grad_norm": 10276.814453125, "learning_rate": 2.3040540540540543e-05, "loss": 0.0424, "step": 899 }, { "epoch": 5.69620253164557, "grad_norm": 8533.361328125, "learning_rate": 2.300675675675676e-05, "loss": 0.041, "step": 900 }, { "epoch": 5.7025316455696204, "grad_norm": 7203.5078125, "learning_rate": 2.2972972972972976e-05, "loss": 0.0354, "step": 901 }, { "epoch": 5.708860759493671, "grad_norm": 11462.4013671875, "learning_rate": 2.293918918918919e-05, "loss": 0.0477, "step": 902 }, { "epoch": 5.715189873417722, "grad_norm": 5360.1826171875, "learning_rate": 2.2905405405405404e-05, "loss": 0.0264, "step": 903 }, { "epoch": 5.7215189873417724, "grad_norm": 7976.76318359375, "learning_rate": 2.287162162162162e-05, "loss": 0.0403, "step": 904 }, { "epoch": 5.727848101265823, "grad_norm": 7507.7705078125, "learning_rate": 2.283783783783784e-05, "loss": 0.0276, "step": 905 }, { "epoch": 5.734177215189874, "grad_norm": 12380.6552734375, "learning_rate": 2.2804054054054056e-05, "loss": 0.037, "step": 906 }, { "epoch": 5.740506329113924, "grad_norm": 7732.59912109375, "learning_rate": 2.2770270270270272e-05, "loss": 0.0282, "step": 907 }, { "epoch": 5.746835443037975, "grad_norm": 6583.05224609375, "learning_rate": 2.273648648648649e-05, "loss": 0.0351, "step": 908 }, { "epoch": 5.753164556962025, "grad_norm": 7830.6318359375, "learning_rate": 2.2702702702702705e-05, "loss": 0.0454, "step": 909 }, { "epoch": 5.759493670886076, "grad_norm": 6017.78515625, "learning_rate": 2.2668918918918917e-05, "loss": 0.041, "step": 910 }, { "epoch": 5.765822784810126, "grad_norm": 5579.81103515625, "learning_rate": 2.2635135135135137e-05, "loss": 0.0346, "step": 911 }, { "epoch": 5.772151898734177, "grad_norm": 7272.892578125, "learning_rate": 2.2601351351351353e-05, "loss": 0.0431, "step": 912 }, { "epoch": 5.7784810126582276, "grad_norm": 15821.40625, "learning_rate": 2.256756756756757e-05, "loss": 0.0464, "step": 913 }, { "epoch": 5.784810126582278, "grad_norm": 5099.4013671875, "learning_rate": 2.2533783783783785e-05, "loss": 0.0233, "step": 914 }, { "epoch": 5.791139240506329, "grad_norm": 6060.462890625, "learning_rate": 2.25e-05, "loss": 0.0235, "step": 915 }, { "epoch": 5.7974683544303796, "grad_norm": 7990.74658203125, "learning_rate": 2.2466216216216218e-05, "loss": 0.0399, "step": 916 }, { "epoch": 5.80379746835443, "grad_norm": 8470.228515625, "learning_rate": 2.2432432432432434e-05, "loss": 0.0434, "step": 917 }, { "epoch": 5.810126582278481, "grad_norm": 8568.2197265625, "learning_rate": 2.239864864864865e-05, "loss": 0.0277, "step": 918 }, { "epoch": 5.8164556962025316, "grad_norm": 5338.2197265625, "learning_rate": 2.2364864864864866e-05, "loss": 0.0293, "step": 919 }, { "epoch": 5.822784810126582, "grad_norm": 5685.009765625, "learning_rate": 2.2331081081081082e-05, "loss": 0.0225, "step": 920 }, { "epoch": 5.829113924050633, "grad_norm": 6194.15673828125, "learning_rate": 2.2297297297297298e-05, "loss": 0.0278, "step": 921 }, { "epoch": 5.8354430379746836, "grad_norm": 6349.11328125, "learning_rate": 2.2263513513513514e-05, "loss": 0.0325, "step": 922 }, { "epoch": 5.841772151898734, "grad_norm": 12755.1630859375, "learning_rate": 2.222972972972973e-05, "loss": 0.0322, "step": 923 }, { "epoch": 5.848101265822785, "grad_norm": 6962.3115234375, "learning_rate": 2.2195945945945947e-05, "loss": 0.0326, "step": 924 }, { "epoch": 5.8544303797468356, "grad_norm": 6425.74169921875, "learning_rate": 2.2162162162162166e-05, "loss": 0.0417, "step": 925 }, { "epoch": 5.860759493670886, "grad_norm": 8318.158203125, "learning_rate": 2.212837837837838e-05, "loss": 0.0414, "step": 926 }, { "epoch": 5.867088607594937, "grad_norm": 8978.2236328125, "learning_rate": 2.2094594594594595e-05, "loss": 0.026, "step": 927 }, { "epoch": 5.8734177215189876, "grad_norm": 7477.10595703125, "learning_rate": 2.206081081081081e-05, "loss": 0.0296, "step": 928 }, { "epoch": 5.879746835443038, "grad_norm": 26162.3359375, "learning_rate": 2.2027027027027027e-05, "loss": 0.0465, "step": 929 }, { "epoch": 5.886075949367089, "grad_norm": 5630.24951171875, "learning_rate": 2.1993243243243243e-05, "loss": 0.027, "step": 930 }, { "epoch": 5.8924050632911396, "grad_norm": 7085.90380859375, "learning_rate": 2.195945945945946e-05, "loss": 0.0296, "step": 931 }, { "epoch": 5.89873417721519, "grad_norm": 5348.7431640625, "learning_rate": 2.192567567567568e-05, "loss": 0.0299, "step": 932 }, { "epoch": 5.905063291139241, "grad_norm": 7522.6875, "learning_rate": 2.1891891891891895e-05, "loss": 0.0381, "step": 933 }, { "epoch": 5.911392405063291, "grad_norm": 9386.744140625, "learning_rate": 2.1858108108108108e-05, "loss": 0.0273, "step": 934 }, { "epoch": 5.917721518987342, "grad_norm": 6911.54150390625, "learning_rate": 2.1824324324324324e-05, "loss": 0.0291, "step": 935 }, { "epoch": 5.924050632911392, "grad_norm": 9124.8369140625, "learning_rate": 2.179054054054054e-05, "loss": 0.0355, "step": 936 }, { "epoch": 5.930379746835443, "grad_norm": 8668.4541015625, "learning_rate": 2.1756756756756756e-05, "loss": 0.0325, "step": 937 }, { "epoch": 5.936708860759493, "grad_norm": 6246.01904296875, "learning_rate": 2.1722972972972976e-05, "loss": 0.0325, "step": 938 }, { "epoch": 5.943037974683544, "grad_norm": 7460.083984375, "learning_rate": 2.1689189189189192e-05, "loss": 0.0471, "step": 939 }, { "epoch": 5.949367088607595, "grad_norm": 8504.8388671875, "learning_rate": 2.1655405405405408e-05, "loss": 0.0372, "step": 940 }, { "epoch": 5.955696202531645, "grad_norm": 8776.802734375, "learning_rate": 2.1621621621621624e-05, "loss": 0.0401, "step": 941 }, { "epoch": 5.962025316455696, "grad_norm": 6373.88818359375, "learning_rate": 2.1587837837837837e-05, "loss": 0.0325, "step": 942 }, { "epoch": 5.968354430379747, "grad_norm": 7281.73095703125, "learning_rate": 2.1554054054054053e-05, "loss": 0.0293, "step": 943 }, { "epoch": 5.974683544303797, "grad_norm": 10783.6943359375, "learning_rate": 2.152027027027027e-05, "loss": 0.0357, "step": 944 }, { "epoch": 5.981012658227848, "grad_norm": 5237.654296875, "learning_rate": 2.148648648648649e-05, "loss": 0.024, "step": 945 }, { "epoch": 5.987341772151899, "grad_norm": 6816.08642578125, "learning_rate": 2.1452702702702705e-05, "loss": 0.0331, "step": 946 }, { "epoch": 5.993670886075949, "grad_norm": 9649.99609375, "learning_rate": 2.141891891891892e-05, "loss": 0.0282, "step": 947 }, { "epoch": 6.0, "grad_norm": 13890.794921875, "learning_rate": 2.1385135135135137e-05, "loss": 0.0446, "step": 948 }, { "epoch": 6.0, "eval_f1_macro": 0.6356682275412926, "eval_f1_micro": 0.8007554296506137, "eval_loss": 0.040821027010679245, "eval_precision": 0.8362919132149902, "eval_recall": 0.7681159420289855, "eval_runtime": 1.1667, "eval_samples_per_second": 360.838, "eval_steps_per_second": 15.428, "step": 948 }, { "epoch": 6.006329113924051, "grad_norm": 5162.45703125, "learning_rate": 2.1351351351351353e-05, "loss": 0.023, "step": 949 }, { "epoch": 6.012658227848101, "grad_norm": 6269.974609375, "learning_rate": 2.1317567567567566e-05, "loss": 0.0267, "step": 950 }, { "epoch": 6.018987341772152, "grad_norm": 5501.2392578125, "learning_rate": 2.1283783783783785e-05, "loss": 0.0302, "step": 951 }, { "epoch": 6.025316455696203, "grad_norm": 6543.5625, "learning_rate": 2.125e-05, "loss": 0.0342, "step": 952 }, { "epoch": 6.031645569620253, "grad_norm": 7088.62255859375, "learning_rate": 2.1216216216216218e-05, "loss": 0.0286, "step": 953 }, { "epoch": 6.037974683544304, "grad_norm": 3823.706787109375, "learning_rate": 2.1182432432432434e-05, "loss": 0.024, "step": 954 }, { "epoch": 6.044303797468355, "grad_norm": 10338.7216796875, "learning_rate": 2.114864864864865e-05, "loss": 0.0338, "step": 955 }, { "epoch": 6.050632911392405, "grad_norm": 6003.23974609375, "learning_rate": 2.1114864864864866e-05, "loss": 0.027, "step": 956 }, { "epoch": 6.056962025316456, "grad_norm": 8177.53662109375, "learning_rate": 2.1081081081081082e-05, "loss": 0.0266, "step": 957 }, { "epoch": 6.063291139240507, "grad_norm": 7944.0380859375, "learning_rate": 2.1047297297297298e-05, "loss": 0.0365, "step": 958 }, { "epoch": 6.069620253164557, "grad_norm": 6394.24462890625, "learning_rate": 2.1013513513513514e-05, "loss": 0.0319, "step": 959 }, { "epoch": 6.075949367088608, "grad_norm": 9142.2080078125, "learning_rate": 2.097972972972973e-05, "loss": 0.0364, "step": 960 }, { "epoch": 6.082278481012658, "grad_norm": 5044.3369140625, "learning_rate": 2.0945945945945947e-05, "loss": 0.0283, "step": 961 }, { "epoch": 6.0886075949367084, "grad_norm": 7193.0927734375, "learning_rate": 2.0912162162162163e-05, "loss": 0.0309, "step": 962 }, { "epoch": 6.094936708860759, "grad_norm": 5678.775390625, "learning_rate": 2.087837837837838e-05, "loss": 0.0415, "step": 963 }, { "epoch": 6.10126582278481, "grad_norm": 7892.87744140625, "learning_rate": 2.0844594594594595e-05, "loss": 0.0384, "step": 964 }, { "epoch": 6.1075949367088604, "grad_norm": 5430.375, "learning_rate": 2.0810810810810815e-05, "loss": 0.0341, "step": 965 }, { "epoch": 6.113924050632911, "grad_norm": 6808.18896484375, "learning_rate": 2.0777027027027027e-05, "loss": 0.0278, "step": 966 }, { "epoch": 6.120253164556962, "grad_norm": 9654.5703125, "learning_rate": 2.0743243243243243e-05, "loss": 0.034, "step": 967 }, { "epoch": 6.1265822784810124, "grad_norm": 5235.857421875, "learning_rate": 2.070945945945946e-05, "loss": 0.0178, "step": 968 }, { "epoch": 6.132911392405063, "grad_norm": 8648.6259765625, "learning_rate": 2.0675675675675676e-05, "loss": 0.0359, "step": 969 }, { "epoch": 6.139240506329114, "grad_norm": 6204.19287109375, "learning_rate": 2.0641891891891892e-05, "loss": 0.0247, "step": 970 }, { "epoch": 6.1455696202531644, "grad_norm": 3959.73876953125, "learning_rate": 2.0608108108108108e-05, "loss": 0.0222, "step": 971 }, { "epoch": 6.151898734177215, "grad_norm": 5239.728515625, "learning_rate": 2.0574324324324327e-05, "loss": 0.0253, "step": 972 }, { "epoch": 6.158227848101266, "grad_norm": 7631.638671875, "learning_rate": 2.0540540540540544e-05, "loss": 0.0317, "step": 973 }, { "epoch": 6.1645569620253164, "grad_norm": 7115.0185546875, "learning_rate": 2.0506756756756756e-05, "loss": 0.0228, "step": 974 }, { "epoch": 6.170886075949367, "grad_norm": 10385.6435546875, "learning_rate": 2.0472972972972972e-05, "loss": 0.0332, "step": 975 }, { "epoch": 6.177215189873418, "grad_norm": 8513.7626953125, "learning_rate": 2.043918918918919e-05, "loss": 0.0242, "step": 976 }, { "epoch": 6.1835443037974684, "grad_norm": 4110.232421875, "learning_rate": 2.0405405405405405e-05, "loss": 0.0238, "step": 977 }, { "epoch": 6.189873417721519, "grad_norm": 7776.81298828125, "learning_rate": 2.0371621621621624e-05, "loss": 0.043, "step": 978 }, { "epoch": 6.19620253164557, "grad_norm": 11860.2451171875, "learning_rate": 2.033783783783784e-05, "loss": 0.0498, "step": 979 }, { "epoch": 6.2025316455696204, "grad_norm": 6123.6533203125, "learning_rate": 2.0304054054054056e-05, "loss": 0.0273, "step": 980 }, { "epoch": 6.208860759493671, "grad_norm": 7156.1787109375, "learning_rate": 2.0270270270270273e-05, "loss": 0.0287, "step": 981 }, { "epoch": 6.215189873417722, "grad_norm": 14460.8662109375, "learning_rate": 2.0236486486486485e-05, "loss": 0.0321, "step": 982 }, { "epoch": 6.2215189873417724, "grad_norm": 11623.4091796875, "learning_rate": 2.02027027027027e-05, "loss": 0.025, "step": 983 }, { "epoch": 6.227848101265823, "grad_norm": 8383.8466796875, "learning_rate": 2.0168918918918918e-05, "loss": 0.0347, "step": 984 }, { "epoch": 6.234177215189874, "grad_norm": 7060.86669921875, "learning_rate": 2.0135135135135137e-05, "loss": 0.0287, "step": 985 }, { "epoch": 6.2405063291139244, "grad_norm": 5367.98486328125, "learning_rate": 2.0101351351351353e-05, "loss": 0.0342, "step": 986 }, { "epoch": 6.246835443037975, "grad_norm": 7567.27587890625, "learning_rate": 2.006756756756757e-05, "loss": 0.0234, "step": 987 }, { "epoch": 6.253164556962025, "grad_norm": 7659.52734375, "learning_rate": 2.0033783783783786e-05, "loss": 0.0359, "step": 988 }, { "epoch": 6.2594936708860756, "grad_norm": 6609.671875, "learning_rate": 2e-05, "loss": 0.0357, "step": 989 }, { "epoch": 6.265822784810126, "grad_norm": 7370.65625, "learning_rate": 1.9966216216216214e-05, "loss": 0.0271, "step": 990 }, { "epoch": 6.272151898734177, "grad_norm": 6125.25927734375, "learning_rate": 1.9932432432432434e-05, "loss": 0.0257, "step": 991 }, { "epoch": 6.2784810126582276, "grad_norm": 5304.35791015625, "learning_rate": 1.989864864864865e-05, "loss": 0.0237, "step": 992 }, { "epoch": 6.284810126582278, "grad_norm": 5053.59619140625, "learning_rate": 1.9864864864864866e-05, "loss": 0.031, "step": 993 }, { "epoch": 6.291139240506329, "grad_norm": 7419.26806640625, "learning_rate": 1.9831081081081082e-05, "loss": 0.0176, "step": 994 }, { "epoch": 6.2974683544303796, "grad_norm": 6453.99755859375, "learning_rate": 1.97972972972973e-05, "loss": 0.0288, "step": 995 }, { "epoch": 6.30379746835443, "grad_norm": 7959.060546875, "learning_rate": 1.9763513513513515e-05, "loss": 0.0327, "step": 996 }, { "epoch": 6.310126582278481, "grad_norm": 10662.0546875, "learning_rate": 1.972972972972973e-05, "loss": 0.0294, "step": 997 }, { "epoch": 6.3164556962025316, "grad_norm": 6681.01953125, "learning_rate": 1.9695945945945947e-05, "loss": 0.0288, "step": 998 }, { "epoch": 6.322784810126582, "grad_norm": 7212.6474609375, "learning_rate": 1.9662162162162163e-05, "loss": 0.0368, "step": 999 }, { "epoch": 6.329113924050633, "grad_norm": 7251.8173828125, "learning_rate": 1.962837837837838e-05, "loss": 0.0291, "step": 1000 }, { "epoch": 6.3354430379746836, "grad_norm": 4028.050537109375, "learning_rate": 1.9594594594594595e-05, "loss": 0.0226, "step": 1001 }, { "epoch": 6.341772151898734, "grad_norm": 8590.1044921875, "learning_rate": 1.956081081081081e-05, "loss": 0.0309, "step": 1002 }, { "epoch": 6.348101265822785, "grad_norm": 4919.44140625, "learning_rate": 1.9527027027027027e-05, "loss": 0.0339, "step": 1003 }, { "epoch": 6.3544303797468356, "grad_norm": 7062.23974609375, "learning_rate": 1.9493243243243244e-05, "loss": 0.0299, "step": 1004 }, { "epoch": 6.360759493670886, "grad_norm": 3468.474853515625, "learning_rate": 1.9459459459459463e-05, "loss": 0.0204, "step": 1005 }, { "epoch": 6.367088607594937, "grad_norm": 6867.73779296875, "learning_rate": 1.9425675675675676e-05, "loss": 0.0305, "step": 1006 }, { "epoch": 6.3734177215189876, "grad_norm": 6084.25390625, "learning_rate": 1.9391891891891892e-05, "loss": 0.0325, "step": 1007 }, { "epoch": 6.379746835443038, "grad_norm": 6507.97412109375, "learning_rate": 1.9358108108108108e-05, "loss": 0.0229, "step": 1008 }, { "epoch": 6.386075949367089, "grad_norm": 6572.8896484375, "learning_rate": 1.9324324324324324e-05, "loss": 0.0276, "step": 1009 }, { "epoch": 6.3924050632911396, "grad_norm": 5036.154296875, "learning_rate": 1.929054054054054e-05, "loss": 0.0199, "step": 1010 }, { "epoch": 6.39873417721519, "grad_norm": 5992.015625, "learning_rate": 1.9256756756756756e-05, "loss": 0.028, "step": 1011 }, { "epoch": 6.405063291139241, "grad_norm": 5647.94482421875, "learning_rate": 1.9222972972972976e-05, "loss": 0.0249, "step": 1012 }, { "epoch": 6.4113924050632916, "grad_norm": 5896.36962890625, "learning_rate": 1.9189189189189192e-05, "loss": 0.0288, "step": 1013 }, { "epoch": 6.417721518987342, "grad_norm": 10249.21875, "learning_rate": 1.9155405405405405e-05, "loss": 0.0293, "step": 1014 }, { "epoch": 6.424050632911392, "grad_norm": 8031.904296875, "learning_rate": 1.912162162162162e-05, "loss": 0.0398, "step": 1015 }, { "epoch": 6.430379746835443, "grad_norm": 4945.5595703125, "learning_rate": 1.9087837837837837e-05, "loss": 0.0277, "step": 1016 }, { "epoch": 6.436708860759493, "grad_norm": 8857.3916015625, "learning_rate": 1.9054054054054053e-05, "loss": 0.042, "step": 1017 }, { "epoch": 6.443037974683544, "grad_norm": 8686.9794921875, "learning_rate": 1.9020270270270273e-05, "loss": 0.0339, "step": 1018 }, { "epoch": 6.449367088607595, "grad_norm": 4716.8544921875, "learning_rate": 1.898648648648649e-05, "loss": 0.0288, "step": 1019 }, { "epoch": 6.455696202531645, "grad_norm": 7329.61865234375, "learning_rate": 1.8952702702702705e-05, "loss": 0.0213, "step": 1020 }, { "epoch": 6.462025316455696, "grad_norm": 9528.583984375, "learning_rate": 1.891891891891892e-05, "loss": 0.0382, "step": 1021 }, { "epoch": 6.468354430379747, "grad_norm": 11963.216796875, "learning_rate": 1.8885135135135134e-05, "loss": 0.0374, "step": 1022 }, { "epoch": 6.474683544303797, "grad_norm": 6676.12939453125, "learning_rate": 1.885135135135135e-05, "loss": 0.0252, "step": 1023 }, { "epoch": 6.481012658227848, "grad_norm": 5442.97509765625, "learning_rate": 1.8817567567567566e-05, "loss": 0.0201, "step": 1024 }, { "epoch": 6.487341772151899, "grad_norm": 6295.1220703125, "learning_rate": 1.8783783783783786e-05, "loss": 0.0323, "step": 1025 }, { "epoch": 6.493670886075949, "grad_norm": 9997.45703125, "learning_rate": 1.8750000000000002e-05, "loss": 0.0298, "step": 1026 }, { "epoch": 6.5, "grad_norm": 7555.07275390625, "learning_rate": 1.8716216216216218e-05, "loss": 0.0218, "step": 1027 }, { "epoch": 6.506329113924051, "grad_norm": 5705.05419921875, "learning_rate": 1.8682432432432434e-05, "loss": 0.0273, "step": 1028 }, { "epoch": 6.512658227848101, "grad_norm": 6639.59619140625, "learning_rate": 1.864864864864865e-05, "loss": 0.0331, "step": 1029 }, { "epoch": 6.518987341772152, "grad_norm": 4917.77587890625, "learning_rate": 1.8614864864864866e-05, "loss": 0.0217, "step": 1030 }, { "epoch": 6.525316455696203, "grad_norm": 6664.1435546875, "learning_rate": 1.8581081081081082e-05, "loss": 0.0252, "step": 1031 }, { "epoch": 6.531645569620253, "grad_norm": 8505.53515625, "learning_rate": 1.85472972972973e-05, "loss": 0.0354, "step": 1032 }, { "epoch": 6.537974683544304, "grad_norm": 9378.5693359375, "learning_rate": 1.8513513513513515e-05, "loss": 0.0364, "step": 1033 }, { "epoch": 6.544303797468355, "grad_norm": 7275.66943359375, "learning_rate": 1.847972972972973e-05, "loss": 0.0343, "step": 1034 }, { "epoch": 6.550632911392405, "grad_norm": 8461.931640625, "learning_rate": 1.8445945945945947e-05, "loss": 0.0208, "step": 1035 }, { "epoch": 6.556962025316456, "grad_norm": 3462.453125, "learning_rate": 1.8412162162162163e-05, "loss": 0.0192, "step": 1036 }, { "epoch": 6.563291139240507, "grad_norm": 9324.345703125, "learning_rate": 1.837837837837838e-05, "loss": 0.0232, "step": 1037 }, { "epoch": 6.569620253164557, "grad_norm": 8942.736328125, "learning_rate": 1.8344594594594595e-05, "loss": 0.0362, "step": 1038 }, { "epoch": 6.575949367088608, "grad_norm": 8678.634765625, "learning_rate": 1.831081081081081e-05, "loss": 0.0257, "step": 1039 }, { "epoch": 6.582278481012658, "grad_norm": 6006.193359375, "learning_rate": 1.8277027027027028e-05, "loss": 0.0254, "step": 1040 }, { "epoch": 6.588607594936709, "grad_norm": 5598.16650390625, "learning_rate": 1.8243243243243244e-05, "loss": 0.0251, "step": 1041 }, { "epoch": 6.594936708860759, "grad_norm": 6959.369140625, "learning_rate": 1.820945945945946e-05, "loss": 0.0249, "step": 1042 }, { "epoch": 6.60126582278481, "grad_norm": 4690.28271484375, "learning_rate": 1.8175675675675676e-05, "loss": 0.0207, "step": 1043 }, { "epoch": 6.6075949367088604, "grad_norm": 5924.2314453125, "learning_rate": 1.8141891891891892e-05, "loss": 0.0351, "step": 1044 }, { "epoch": 6.613924050632911, "grad_norm": 11452.9990234375, "learning_rate": 1.810810810810811e-05, "loss": 0.0379, "step": 1045 }, { "epoch": 6.620253164556962, "grad_norm": 6196.2578125, "learning_rate": 1.8074324324324328e-05, "loss": 0.0312, "step": 1046 }, { "epoch": 6.6265822784810124, "grad_norm": 4878.1845703125, "learning_rate": 1.804054054054054e-05, "loss": 0.0209, "step": 1047 }, { "epoch": 6.632911392405063, "grad_norm": 5891.654296875, "learning_rate": 1.8006756756756757e-05, "loss": 0.0296, "step": 1048 }, { "epoch": 6.639240506329114, "grad_norm": 6810.9296875, "learning_rate": 1.7972972972972973e-05, "loss": 0.0217, "step": 1049 }, { "epoch": 6.6455696202531644, "grad_norm": 7346.94091796875, "learning_rate": 1.793918918918919e-05, "loss": 0.0363, "step": 1050 }, { "epoch": 6.651898734177215, "grad_norm": 8679.9208984375, "learning_rate": 1.7905405405405405e-05, "loss": 0.0344, "step": 1051 }, { "epoch": 6.658227848101266, "grad_norm": 6543.111328125, "learning_rate": 1.7871621621621624e-05, "loss": 0.0291, "step": 1052 }, { "epoch": 6.6645569620253164, "grad_norm": 5140.9853515625, "learning_rate": 1.783783783783784e-05, "loss": 0.019, "step": 1053 }, { "epoch": 6.670886075949367, "grad_norm": 6945.2783203125, "learning_rate": 1.7804054054054057e-05, "loss": 0.0309, "step": 1054 }, { "epoch": 6.677215189873418, "grad_norm": 6589.2099609375, "learning_rate": 1.777027027027027e-05, "loss": 0.0288, "step": 1055 }, { "epoch": 6.6835443037974684, "grad_norm": 5529.06005859375, "learning_rate": 1.7736486486486486e-05, "loss": 0.027, "step": 1056 }, { "epoch": 6.689873417721519, "grad_norm": 7734.51318359375, "learning_rate": 1.7702702702702702e-05, "loss": 0.0262, "step": 1057 }, { "epoch": 6.69620253164557, "grad_norm": 9768.234375, "learning_rate": 1.766891891891892e-05, "loss": 0.0332, "step": 1058 }, { "epoch": 6.7025316455696204, "grad_norm": 6620.69384765625, "learning_rate": 1.7635135135135137e-05, "loss": 0.035, "step": 1059 }, { "epoch": 6.708860759493671, "grad_norm": 3254.31298828125, "learning_rate": 1.7601351351351353e-05, "loss": 0.0158, "step": 1060 }, { "epoch": 6.715189873417722, "grad_norm": 8772.951171875, "learning_rate": 1.756756756756757e-05, "loss": 0.04, "step": 1061 }, { "epoch": 6.7215189873417724, "grad_norm": 8529.99609375, "learning_rate": 1.7533783783783786e-05, "loss": 0.026, "step": 1062 }, { "epoch": 6.727848101265823, "grad_norm": 7466.1142578125, "learning_rate": 1.75e-05, "loss": 0.0312, "step": 1063 }, { "epoch": 6.734177215189874, "grad_norm": 6064.8515625, "learning_rate": 1.7466216216216215e-05, "loss": 0.0285, "step": 1064 }, { "epoch": 6.740506329113924, "grad_norm": 4553.1826171875, "learning_rate": 1.7432432432432434e-05, "loss": 0.0228, "step": 1065 }, { "epoch": 6.746835443037975, "grad_norm": 4970.33056640625, "learning_rate": 1.739864864864865e-05, "loss": 0.0293, "step": 1066 }, { "epoch": 6.753164556962025, "grad_norm": 6065.2373046875, "learning_rate": 1.7364864864864866e-05, "loss": 0.0287, "step": 1067 }, { "epoch": 6.759493670886076, "grad_norm": 7425.73828125, "learning_rate": 1.7331081081081082e-05, "loss": 0.031, "step": 1068 }, { "epoch": 6.765822784810126, "grad_norm": 15052.712890625, "learning_rate": 1.72972972972973e-05, "loss": 0.0297, "step": 1069 }, { "epoch": 6.772151898734177, "grad_norm": 7619.421875, "learning_rate": 1.7263513513513515e-05, "loss": 0.0245, "step": 1070 }, { "epoch": 6.7784810126582276, "grad_norm": 6253.7880859375, "learning_rate": 1.722972972972973e-05, "loss": 0.022, "step": 1071 }, { "epoch": 6.784810126582278, "grad_norm": 10794.689453125, "learning_rate": 1.7195945945945947e-05, "loss": 0.0385, "step": 1072 }, { "epoch": 6.791139240506329, "grad_norm": 4665.92333984375, "learning_rate": 1.7162162162162163e-05, "loss": 0.0208, "step": 1073 }, { "epoch": 6.7974683544303796, "grad_norm": 5459.45068359375, "learning_rate": 1.712837837837838e-05, "loss": 0.0308, "step": 1074 }, { "epoch": 6.80379746835443, "grad_norm": 5131.21875, "learning_rate": 1.7094594594594595e-05, "loss": 0.0183, "step": 1075 }, { "epoch": 6.810126582278481, "grad_norm": 11873.8623046875, "learning_rate": 1.706081081081081e-05, "loss": 0.0306, "step": 1076 }, { "epoch": 6.8164556962025316, "grad_norm": 5770.78955078125, "learning_rate": 1.7027027027027028e-05, "loss": 0.0238, "step": 1077 }, { "epoch": 6.822784810126582, "grad_norm": 5699.8603515625, "learning_rate": 1.6993243243243244e-05, "loss": 0.0224, "step": 1078 }, { "epoch": 6.829113924050633, "grad_norm": 10186.60546875, "learning_rate": 1.695945945945946e-05, "loss": 0.0303, "step": 1079 }, { "epoch": 6.8354430379746836, "grad_norm": 6485.85302734375, "learning_rate": 1.6925675675675676e-05, "loss": 0.0224, "step": 1080 }, { "epoch": 6.841772151898734, "grad_norm": 9121.13671875, "learning_rate": 1.6891891891891892e-05, "loss": 0.03, "step": 1081 }, { "epoch": 6.848101265822785, "grad_norm": 8347.6572265625, "learning_rate": 1.6858108108108108e-05, "loss": 0.034, "step": 1082 }, { "epoch": 6.8544303797468356, "grad_norm": 6150.92138671875, "learning_rate": 1.6824324324324324e-05, "loss": 0.0276, "step": 1083 }, { "epoch": 6.860759493670886, "grad_norm": 4387.03271484375, "learning_rate": 1.679054054054054e-05, "loss": 0.0229, "step": 1084 }, { "epoch": 6.867088607594937, "grad_norm": 5958.5595703125, "learning_rate": 1.675675675675676e-05, "loss": 0.0283, "step": 1085 }, { "epoch": 6.8734177215189876, "grad_norm": 6165.71240234375, "learning_rate": 1.6722972972972976e-05, "loss": 0.0274, "step": 1086 }, { "epoch": 6.879746835443038, "grad_norm": 7887.6357421875, "learning_rate": 1.668918918918919e-05, "loss": 0.013, "step": 1087 }, { "epoch": 6.886075949367089, "grad_norm": 9181.763671875, "learning_rate": 1.6655405405405405e-05, "loss": 0.0329, "step": 1088 }, { "epoch": 6.8924050632911396, "grad_norm": 5707.31591796875, "learning_rate": 1.662162162162162e-05, "loss": 0.0224, "step": 1089 }, { "epoch": 6.89873417721519, "grad_norm": 4694.6708984375, "learning_rate": 1.6587837837837837e-05, "loss": 0.0214, "step": 1090 }, { "epoch": 6.905063291139241, "grad_norm": 10019.0556640625, "learning_rate": 1.6554054054054053e-05, "loss": 0.0281, "step": 1091 }, { "epoch": 6.911392405063291, "grad_norm": 10597.2177734375, "learning_rate": 1.6520270270270273e-05, "loss": 0.0325, "step": 1092 }, { "epoch": 6.917721518987342, "grad_norm": 7919.712890625, "learning_rate": 1.648648648648649e-05, "loss": 0.0272, "step": 1093 }, { "epoch": 6.924050632911392, "grad_norm": 5981.3046875, "learning_rate": 1.6452702702702705e-05, "loss": 0.0272, "step": 1094 }, { "epoch": 6.930379746835443, "grad_norm": 6846.9443359375, "learning_rate": 1.6418918918918918e-05, "loss": 0.0267, "step": 1095 }, { "epoch": 6.936708860759493, "grad_norm": 3109.099853515625, "learning_rate": 1.6385135135135134e-05, "loss": 0.0147, "step": 1096 }, { "epoch": 6.943037974683544, "grad_norm": 6997.63037109375, "learning_rate": 1.635135135135135e-05, "loss": 0.027, "step": 1097 }, { "epoch": 6.949367088607595, "grad_norm": 5917.50634765625, "learning_rate": 1.631756756756757e-05, "loss": 0.0254, "step": 1098 }, { "epoch": 6.955696202531645, "grad_norm": 6562.890625, "learning_rate": 1.6283783783783786e-05, "loss": 0.0327, "step": 1099 }, { "epoch": 6.962025316455696, "grad_norm": 6403.4873046875, "learning_rate": 1.6250000000000002e-05, "loss": 0.0197, "step": 1100 }, { "epoch": 6.968354430379747, "grad_norm": 4348.3896484375, "learning_rate": 1.6216216216216218e-05, "loss": 0.0233, "step": 1101 }, { "epoch": 6.974683544303797, "grad_norm": 8530.4560546875, "learning_rate": 1.6182432432432434e-05, "loss": 0.0213, "step": 1102 }, { "epoch": 6.981012658227848, "grad_norm": 21737.796875, "learning_rate": 1.6148648648648647e-05, "loss": 0.0457, "step": 1103 }, { "epoch": 6.987341772151899, "grad_norm": 7495.23193359375, "learning_rate": 1.6114864864864866e-05, "loss": 0.0364, "step": 1104 }, { "epoch": 6.993670886075949, "grad_norm": 4258.98095703125, "learning_rate": 1.6081081081081083e-05, "loss": 0.019, "step": 1105 }, { "epoch": 7.0, "grad_norm": 10607.5283203125, "learning_rate": 1.60472972972973e-05, "loss": 0.0259, "step": 1106 }, { "epoch": 7.0, "eval_f1_macro": 0.6763285097496297, "eval_f1_micro": 0.8434197886647454, "eval_loss": 0.03649517521262169, "eval_precision": 0.8977505112474438, "eval_recall": 0.7952898550724637, "eval_runtime": 1.1545, "eval_samples_per_second": 364.665, "eval_steps_per_second": 15.591, "step": 1106 }, { "epoch": 7.006329113924051, "grad_norm": 4317.11572265625, "learning_rate": 1.6013513513513515e-05, "loss": 0.0193, "step": 1107 }, { "epoch": 7.012658227848101, "grad_norm": 5655.6796875, "learning_rate": 1.597972972972973e-05, "loss": 0.0232, "step": 1108 }, { "epoch": 7.018987341772152, "grad_norm": 6184.93896484375, "learning_rate": 1.5945945945945947e-05, "loss": 0.0214, "step": 1109 }, { "epoch": 7.025316455696203, "grad_norm": 3420.451416015625, "learning_rate": 1.5912162162162163e-05, "loss": 0.0176, "step": 1110 }, { "epoch": 7.031645569620253, "grad_norm": 5488.08544921875, "learning_rate": 1.587837837837838e-05, "loss": 0.0256, "step": 1111 }, { "epoch": 7.037974683544304, "grad_norm": 7130.646484375, "learning_rate": 1.5844594594594595e-05, "loss": 0.0251, "step": 1112 }, { "epoch": 7.044303797468355, "grad_norm": 4347.517578125, "learning_rate": 1.581081081081081e-05, "loss": 0.0177, "step": 1113 }, { "epoch": 7.050632911392405, "grad_norm": 5294.326171875, "learning_rate": 1.5777027027027028e-05, "loss": 0.0187, "step": 1114 }, { "epoch": 7.056962025316456, "grad_norm": 4780.115234375, "learning_rate": 1.5743243243243244e-05, "loss": 0.0287, "step": 1115 }, { "epoch": 7.063291139240507, "grad_norm": 5874.2470703125, "learning_rate": 1.570945945945946e-05, "loss": 0.0218, "step": 1116 }, { "epoch": 7.069620253164557, "grad_norm": 11274.4443359375, "learning_rate": 1.5675675675675676e-05, "loss": 0.0293, "step": 1117 }, { "epoch": 7.075949367088608, "grad_norm": 4603.64990234375, "learning_rate": 1.5641891891891892e-05, "loss": 0.0259, "step": 1118 }, { "epoch": 7.082278481012658, "grad_norm": 5824.20703125, "learning_rate": 1.560810810810811e-05, "loss": 0.0354, "step": 1119 }, { "epoch": 7.0886075949367084, "grad_norm": 6256.078125, "learning_rate": 1.5574324324324325e-05, "loss": 0.0265, "step": 1120 }, { "epoch": 7.094936708860759, "grad_norm": 9517.498046875, "learning_rate": 1.554054054054054e-05, "loss": 0.0292, "step": 1121 }, { "epoch": 7.10126582278481, "grad_norm": 7112.796875, "learning_rate": 1.5506756756756757e-05, "loss": 0.0239, "step": 1122 }, { "epoch": 7.1075949367088604, "grad_norm": 5786.52197265625, "learning_rate": 1.5472972972972973e-05, "loss": 0.0168, "step": 1123 }, { "epoch": 7.113924050632911, "grad_norm": 7533.62109375, "learning_rate": 1.543918918918919e-05, "loss": 0.0209, "step": 1124 }, { "epoch": 7.120253164556962, "grad_norm": 5884.11279296875, "learning_rate": 1.540540540540541e-05, "loss": 0.024, "step": 1125 }, { "epoch": 7.1265822784810124, "grad_norm": 4860.662109375, "learning_rate": 1.5371621621621625e-05, "loss": 0.0208, "step": 1126 }, { "epoch": 7.132911392405063, "grad_norm": 7841.10400390625, "learning_rate": 1.5337837837837837e-05, "loss": 0.0241, "step": 1127 }, { "epoch": 7.139240506329114, "grad_norm": 3476.1162109375, "learning_rate": 1.5304054054054054e-05, "loss": 0.0162, "step": 1128 }, { "epoch": 7.1455696202531644, "grad_norm": 5169.34814453125, "learning_rate": 1.527027027027027e-05, "loss": 0.0216, "step": 1129 }, { "epoch": 7.151898734177215, "grad_norm": 4159.12451171875, "learning_rate": 1.5236486486486487e-05, "loss": 0.0204, "step": 1130 }, { "epoch": 7.158227848101266, "grad_norm": 5752.75927734375, "learning_rate": 1.5202702702702704e-05, "loss": 0.0211, "step": 1131 }, { "epoch": 7.1645569620253164, "grad_norm": 6537.82470703125, "learning_rate": 1.516891891891892e-05, "loss": 0.0224, "step": 1132 }, { "epoch": 7.170886075949367, "grad_norm": 4356.46826171875, "learning_rate": 1.5135135135135136e-05, "loss": 0.0201, "step": 1133 }, { "epoch": 7.177215189873418, "grad_norm": 9949.51953125, "learning_rate": 1.5101351351351354e-05, "loss": 0.0379, "step": 1134 }, { "epoch": 7.1835443037974684, "grad_norm": 5897.0546875, "learning_rate": 1.5067567567567566e-05, "loss": 0.022, "step": 1135 }, { "epoch": 7.189873417721519, "grad_norm": 4187.01904296875, "learning_rate": 1.5033783783783784e-05, "loss": 0.0223, "step": 1136 }, { "epoch": 7.19620253164557, "grad_norm": 3501.06787109375, "learning_rate": 1.5e-05, "loss": 0.0184, "step": 1137 }, { "epoch": 7.2025316455696204, "grad_norm": 5080.38134765625, "learning_rate": 1.4966216216216217e-05, "loss": 0.0185, "step": 1138 }, { "epoch": 7.208860759493671, "grad_norm": 7461.14208984375, "learning_rate": 1.4932432432432433e-05, "loss": 0.0331, "step": 1139 }, { "epoch": 7.215189873417722, "grad_norm": 4786.00537109375, "learning_rate": 1.489864864864865e-05, "loss": 0.0219, "step": 1140 }, { "epoch": 7.2215189873417724, "grad_norm": 7090.0751953125, "learning_rate": 1.4864864864864867e-05, "loss": 0.0278, "step": 1141 }, { "epoch": 7.227848101265823, "grad_norm": 6065.13427734375, "learning_rate": 1.4831081081081083e-05, "loss": 0.0319, "step": 1142 }, { "epoch": 7.234177215189874, "grad_norm": 7555.384765625, "learning_rate": 1.4797297297297297e-05, "loss": 0.0334, "step": 1143 }, { "epoch": 7.2405063291139244, "grad_norm": 6092.70263671875, "learning_rate": 1.4763513513513513e-05, "loss": 0.019, "step": 1144 }, { "epoch": 7.246835443037975, "grad_norm": 6428.009765625, "learning_rate": 1.472972972972973e-05, "loss": 0.0191, "step": 1145 }, { "epoch": 7.253164556962025, "grad_norm": 6381.32080078125, "learning_rate": 1.4695945945945947e-05, "loss": 0.0226, "step": 1146 }, { "epoch": 7.2594936708860756, "grad_norm": 10831.2978515625, "learning_rate": 1.4662162162162163e-05, "loss": 0.0298, "step": 1147 }, { "epoch": 7.265822784810126, "grad_norm": 13558.4130859375, "learning_rate": 1.462837837837838e-05, "loss": 0.0344, "step": 1148 }, { "epoch": 7.272151898734177, "grad_norm": 13457.5234375, "learning_rate": 1.4594594594594596e-05, "loss": 0.0364, "step": 1149 }, { "epoch": 7.2784810126582276, "grad_norm": 7736.28564453125, "learning_rate": 1.4560810810810813e-05, "loss": 0.025, "step": 1150 }, { "epoch": 7.284810126582278, "grad_norm": 5257.45703125, "learning_rate": 1.4527027027027026e-05, "loss": 0.0259, "step": 1151 }, { "epoch": 7.291139240506329, "grad_norm": 4364.10791015625, "learning_rate": 1.4493243243243242e-05, "loss": 0.0296, "step": 1152 }, { "epoch": 7.2974683544303796, "grad_norm": 9060.2509765625, "learning_rate": 1.445945945945946e-05, "loss": 0.0365, "step": 1153 }, { "epoch": 7.30379746835443, "grad_norm": 8449.4208984375, "learning_rate": 1.4425675675675676e-05, "loss": 0.021, "step": 1154 }, { "epoch": 7.310126582278481, "grad_norm": 6180.5908203125, "learning_rate": 1.4391891891891892e-05, "loss": 0.0206, "step": 1155 }, { "epoch": 7.3164556962025316, "grad_norm": 6230.439453125, "learning_rate": 1.4358108108108108e-05, "loss": 0.0286, "step": 1156 }, { "epoch": 7.322784810126582, "grad_norm": 6625.00732421875, "learning_rate": 1.4324324324324326e-05, "loss": 0.0337, "step": 1157 }, { "epoch": 7.329113924050633, "grad_norm": 6445.51123046875, "learning_rate": 1.4290540540540542e-05, "loss": 0.024, "step": 1158 }, { "epoch": 7.3354430379746836, "grad_norm": 3202.01416015625, "learning_rate": 1.4256756756756757e-05, "loss": 0.0172, "step": 1159 }, { "epoch": 7.341772151898734, "grad_norm": 4798.38671875, "learning_rate": 1.4222972972972973e-05, "loss": 0.0169, "step": 1160 }, { "epoch": 7.348101265822785, "grad_norm": 5303.47119140625, "learning_rate": 1.4189189189189189e-05, "loss": 0.0243, "step": 1161 }, { "epoch": 7.3544303797468356, "grad_norm": 4792.1640625, "learning_rate": 1.4155405405405405e-05, "loss": 0.0225, "step": 1162 }, { "epoch": 7.360759493670886, "grad_norm": 8275.748046875, "learning_rate": 1.4121621621621623e-05, "loss": 0.031, "step": 1163 }, { "epoch": 7.367088607594937, "grad_norm": 3717.321044921875, "learning_rate": 1.408783783783784e-05, "loss": 0.0171, "step": 1164 }, { "epoch": 7.3734177215189876, "grad_norm": 5055.89794921875, "learning_rate": 1.4054054054054055e-05, "loss": 0.0268, "step": 1165 }, { "epoch": 7.379746835443038, "grad_norm": 4934.8359375, "learning_rate": 1.4020270270270271e-05, "loss": 0.0229, "step": 1166 }, { "epoch": 7.386075949367089, "grad_norm": 4650.546875, "learning_rate": 1.3986486486486486e-05, "loss": 0.0198, "step": 1167 }, { "epoch": 7.3924050632911396, "grad_norm": 6913.75537109375, "learning_rate": 1.3952702702702702e-05, "loss": 0.0217, "step": 1168 }, { "epoch": 7.39873417721519, "grad_norm": 3669.60693359375, "learning_rate": 1.3918918918918918e-05, "loss": 0.0206, "step": 1169 }, { "epoch": 7.405063291139241, "grad_norm": 4916.8056640625, "learning_rate": 1.3885135135135136e-05, "loss": 0.0176, "step": 1170 }, { "epoch": 7.4113924050632916, "grad_norm": 10858.3232421875, "learning_rate": 1.3851351351351352e-05, "loss": 0.0304, "step": 1171 }, { "epoch": 7.417721518987342, "grad_norm": 7505.04638671875, "learning_rate": 1.3817567567567568e-05, "loss": 0.0266, "step": 1172 }, { "epoch": 7.424050632911392, "grad_norm": 3445.171875, "learning_rate": 1.3783783783783786e-05, "loss": 0.018, "step": 1173 }, { "epoch": 7.430379746835443, "grad_norm": 3508.795654296875, "learning_rate": 1.3750000000000002e-05, "loss": 0.0164, "step": 1174 }, { "epoch": 7.436708860759493, "grad_norm": 5829.900390625, "learning_rate": 1.3716216216216215e-05, "loss": 0.0241, "step": 1175 }, { "epoch": 7.443037974683544, "grad_norm": 4618.060546875, "learning_rate": 1.3682432432432433e-05, "loss": 0.0178, "step": 1176 }, { "epoch": 7.449367088607595, "grad_norm": 5760.419921875, "learning_rate": 1.3648648648648649e-05, "loss": 0.027, "step": 1177 }, { "epoch": 7.455696202531645, "grad_norm": 5266.9375, "learning_rate": 1.3614864864864865e-05, "loss": 0.0154, "step": 1178 }, { "epoch": 7.462025316455696, "grad_norm": 8991.4228515625, "learning_rate": 1.3581081081081081e-05, "loss": 0.0312, "step": 1179 }, { "epoch": 7.468354430379747, "grad_norm": 8776.4169921875, "learning_rate": 1.3547297297297299e-05, "loss": 0.0251, "step": 1180 }, { "epoch": 7.474683544303797, "grad_norm": 4396.8642578125, "learning_rate": 1.3513513513513515e-05, "loss": 0.026, "step": 1181 }, { "epoch": 7.481012658227848, "grad_norm": 5281.12255859375, "learning_rate": 1.3479729729729731e-05, "loss": 0.0184, "step": 1182 }, { "epoch": 7.487341772151899, "grad_norm": 6282.3125, "learning_rate": 1.3445945945945946e-05, "loss": 0.0232, "step": 1183 }, { "epoch": 7.493670886075949, "grad_norm": 4317.55224609375, "learning_rate": 1.3412162162162162e-05, "loss": 0.0281, "step": 1184 }, { "epoch": 7.5, "grad_norm": 8394.677734375, "learning_rate": 1.3378378378378378e-05, "loss": 0.021, "step": 1185 }, { "epoch": 7.506329113924051, "grad_norm": 9033.75390625, "learning_rate": 1.3344594594594596e-05, "loss": 0.0262, "step": 1186 }, { "epoch": 7.512658227848101, "grad_norm": 5897.38232421875, "learning_rate": 1.3310810810810812e-05, "loss": 0.022, "step": 1187 }, { "epoch": 7.518987341772152, "grad_norm": 4326.5263671875, "learning_rate": 1.3277027027027028e-05, "loss": 0.0177, "step": 1188 }, { "epoch": 7.525316455696203, "grad_norm": 9064.7900390625, "learning_rate": 1.3243243243243244e-05, "loss": 0.0297, "step": 1189 }, { "epoch": 7.531645569620253, "grad_norm": 5134.25439453125, "learning_rate": 1.3209459459459462e-05, "loss": 0.0189, "step": 1190 }, { "epoch": 7.537974683544304, "grad_norm": 8714.390625, "learning_rate": 1.3175675675675675e-05, "loss": 0.0286, "step": 1191 }, { "epoch": 7.544303797468355, "grad_norm": 7985.7763671875, "learning_rate": 1.314189189189189e-05, "loss": 0.0286, "step": 1192 }, { "epoch": 7.550632911392405, "grad_norm": 8856.0703125, "learning_rate": 1.3108108108108109e-05, "loss": 0.0293, "step": 1193 }, { "epoch": 7.556962025316456, "grad_norm": 6290.51708984375, "learning_rate": 1.3074324324324325e-05, "loss": 0.028, "step": 1194 }, { "epoch": 7.563291139240507, "grad_norm": 4465.8212890625, "learning_rate": 1.3040540540540541e-05, "loss": 0.0216, "step": 1195 }, { "epoch": 7.569620253164557, "grad_norm": 6981.341796875, "learning_rate": 1.3006756756756757e-05, "loss": 0.0269, "step": 1196 }, { "epoch": 7.575949367088608, "grad_norm": 7262.0068359375, "learning_rate": 1.2972972972972975e-05, "loss": 0.0243, "step": 1197 }, { "epoch": 7.582278481012658, "grad_norm": 5128.63525390625, "learning_rate": 1.2939189189189191e-05, "loss": 0.017, "step": 1198 }, { "epoch": 7.588607594936709, "grad_norm": 3502.91943359375, "learning_rate": 1.2905405405405405e-05, "loss": 0.023, "step": 1199 }, { "epoch": 7.594936708860759, "grad_norm": 5042.21484375, "learning_rate": 1.2871621621621622e-05, "loss": 0.0236, "step": 1200 }, { "epoch": 7.60126582278481, "grad_norm": 6604.43408203125, "learning_rate": 1.2837837837837838e-05, "loss": 0.0285, "step": 1201 }, { "epoch": 7.6075949367088604, "grad_norm": 7683.4921875, "learning_rate": 1.2804054054054054e-05, "loss": 0.0255, "step": 1202 }, { "epoch": 7.613924050632911, "grad_norm": 5012.38330078125, "learning_rate": 1.2770270270270272e-05, "loss": 0.0199, "step": 1203 }, { "epoch": 7.620253164556962, "grad_norm": 4991.177734375, "learning_rate": 1.2736486486486488e-05, "loss": 0.0192, "step": 1204 }, { "epoch": 7.6265822784810124, "grad_norm": 4268.22705078125, "learning_rate": 1.2702702702702704e-05, "loss": 0.0176, "step": 1205 }, { "epoch": 7.632911392405063, "grad_norm": 7672.58349609375, "learning_rate": 1.266891891891892e-05, "loss": 0.0203, "step": 1206 }, { "epoch": 7.639240506329114, "grad_norm": 4775.37255859375, "learning_rate": 1.2635135135135134e-05, "loss": 0.0288, "step": 1207 }, { "epoch": 7.6455696202531644, "grad_norm": 8219.275390625, "learning_rate": 1.260135135135135e-05, "loss": 0.0306, "step": 1208 }, { "epoch": 7.651898734177215, "grad_norm": 6861.22412109375, "learning_rate": 1.2567567567567567e-05, "loss": 0.0373, "step": 1209 }, { "epoch": 7.658227848101266, "grad_norm": 5375.45703125, "learning_rate": 1.2533783783783784e-05, "loss": 0.0234, "step": 1210 }, { "epoch": 7.6645569620253164, "grad_norm": 6431.12109375, "learning_rate": 1.25e-05, "loss": 0.0233, "step": 1211 }, { "epoch": 7.670886075949367, "grad_norm": 7036.2529296875, "learning_rate": 1.2466216216216217e-05, "loss": 0.0282, "step": 1212 }, { "epoch": 7.677215189873418, "grad_norm": 7220.4833984375, "learning_rate": 1.2432432432432435e-05, "loss": 0.0205, "step": 1213 }, { "epoch": 7.6835443037974684, "grad_norm": 5838.2041015625, "learning_rate": 1.2398648648648649e-05, "loss": 0.02, "step": 1214 }, { "epoch": 7.689873417721519, "grad_norm": 5694.2265625, "learning_rate": 1.2364864864864865e-05, "loss": 0.0249, "step": 1215 }, { "epoch": 7.69620253164557, "grad_norm": 4972.7451171875, "learning_rate": 1.2331081081081081e-05, "loss": 0.019, "step": 1216 }, { "epoch": 7.7025316455696204, "grad_norm": 9346.7607421875, "learning_rate": 1.2297297297297299e-05, "loss": 0.0221, "step": 1217 }, { "epoch": 7.708860759493671, "grad_norm": 5184.693359375, "learning_rate": 1.2263513513513513e-05, "loss": 0.0219, "step": 1218 }, { "epoch": 7.715189873417722, "grad_norm": 3893.41943359375, "learning_rate": 1.222972972972973e-05, "loss": 0.0173, "step": 1219 }, { "epoch": 7.7215189873417724, "grad_norm": 7347.62890625, "learning_rate": 1.2195945945945947e-05, "loss": 0.033, "step": 1220 }, { "epoch": 7.727848101265823, "grad_norm": 3181.66064453125, "learning_rate": 1.2162162162162164e-05, "loss": 0.0209, "step": 1221 }, { "epoch": 7.734177215189874, "grad_norm": 6682.25048828125, "learning_rate": 1.2128378378378378e-05, "loss": 0.027, "step": 1222 }, { "epoch": 7.740506329113924, "grad_norm": 4449.6044921875, "learning_rate": 1.2094594594594596e-05, "loss": 0.0233, "step": 1223 }, { "epoch": 7.746835443037975, "grad_norm": 8566.3056640625, "learning_rate": 1.2060810810810812e-05, "loss": 0.0326, "step": 1224 }, { "epoch": 7.753164556962025, "grad_norm": 7454.62744140625, "learning_rate": 1.2027027027027028e-05, "loss": 0.0139, "step": 1225 }, { "epoch": 7.759493670886076, "grad_norm": 5011.7841796875, "learning_rate": 1.1993243243243244e-05, "loss": 0.0246, "step": 1226 }, { "epoch": 7.765822784810126, "grad_norm": 29494.767578125, "learning_rate": 1.195945945945946e-05, "loss": 0.0497, "step": 1227 }, { "epoch": 7.772151898734177, "grad_norm": 5362.9970703125, "learning_rate": 1.1925675675675676e-05, "loss": 0.0233, "step": 1228 }, { "epoch": 7.7784810126582276, "grad_norm": 6121.9658203125, "learning_rate": 1.1891891891891893e-05, "loss": 0.0232, "step": 1229 }, { "epoch": 7.784810126582278, "grad_norm": 7992.64404296875, "learning_rate": 1.1858108108108109e-05, "loss": 0.0213, "step": 1230 }, { "epoch": 7.791139240506329, "grad_norm": 9134.84765625, "learning_rate": 1.1824324324324325e-05, "loss": 0.0275, "step": 1231 }, { "epoch": 7.7974683544303796, "grad_norm": 6206.009765625, "learning_rate": 1.1790540540540541e-05, "loss": 0.0258, "step": 1232 }, { "epoch": 7.80379746835443, "grad_norm": 8990.939453125, "learning_rate": 1.1756756756756759e-05, "loss": 0.0252, "step": 1233 }, { "epoch": 7.810126582278481, "grad_norm": 6405.14599609375, "learning_rate": 1.1722972972972973e-05, "loss": 0.0165, "step": 1234 }, { "epoch": 7.8164556962025316, "grad_norm": 3886.363525390625, "learning_rate": 1.168918918918919e-05, "loss": 0.0177, "step": 1235 }, { "epoch": 7.822784810126582, "grad_norm": 4601.81494140625, "learning_rate": 1.1655405405405405e-05, "loss": 0.0179, "step": 1236 }, { "epoch": 7.829113924050633, "grad_norm": 6129.6337890625, "learning_rate": 1.1621621621621623e-05, "loss": 0.0256, "step": 1237 }, { "epoch": 7.8354430379746836, "grad_norm": 9171.2236328125, "learning_rate": 1.1587837837837838e-05, "loss": 0.0184, "step": 1238 }, { "epoch": 7.841772151898734, "grad_norm": 4650.60302734375, "learning_rate": 1.1554054054054054e-05, "loss": 0.0198, "step": 1239 }, { "epoch": 7.848101265822785, "grad_norm": 5152.72607421875, "learning_rate": 1.1520270270270272e-05, "loss": 0.02, "step": 1240 }, { "epoch": 7.8544303797468356, "grad_norm": 4649.12255859375, "learning_rate": 1.1486486486486488e-05, "loss": 0.019, "step": 1241 }, { "epoch": 7.860759493670886, "grad_norm": 5440.6015625, "learning_rate": 1.1452702702702702e-05, "loss": 0.0258, "step": 1242 }, { "epoch": 7.867088607594937, "grad_norm": 8034.716796875, "learning_rate": 1.141891891891892e-05, "loss": 0.0228, "step": 1243 }, { "epoch": 7.8734177215189876, "grad_norm": 7539.39453125, "learning_rate": 1.1385135135135136e-05, "loss": 0.022, "step": 1244 }, { "epoch": 7.879746835443038, "grad_norm": 11478.5859375, "learning_rate": 1.1351351351351352e-05, "loss": 0.0174, "step": 1245 }, { "epoch": 7.886075949367089, "grad_norm": 5070.85302734375, "learning_rate": 1.1317567567567568e-05, "loss": 0.0242, "step": 1246 }, { "epoch": 7.8924050632911396, "grad_norm": 5761.96826171875, "learning_rate": 1.1283783783783785e-05, "loss": 0.0243, "step": 1247 }, { "epoch": 7.89873417721519, "grad_norm": 4078.016845703125, "learning_rate": 1.125e-05, "loss": 0.022, "step": 1248 }, { "epoch": 7.905063291139241, "grad_norm": 7163.3154296875, "learning_rate": 1.1216216216216217e-05, "loss": 0.0275, "step": 1249 }, { "epoch": 7.911392405063291, "grad_norm": 5797.52392578125, "learning_rate": 1.1182432432432433e-05, "loss": 0.0187, "step": 1250 }, { "epoch": 7.917721518987342, "grad_norm": 4323.74755859375, "learning_rate": 1.1148648648648649e-05, "loss": 0.0197, "step": 1251 }, { "epoch": 7.924050632911392, "grad_norm": 7542.8671875, "learning_rate": 1.1114864864864865e-05, "loss": 0.029, "step": 1252 }, { "epoch": 7.930379746835443, "grad_norm": 6522.87841796875, "learning_rate": 1.1081081081081083e-05, "loss": 0.0277, "step": 1253 }, { "epoch": 7.936708860759493, "grad_norm": 5580.0546875, "learning_rate": 1.1047297297297297e-05, "loss": 0.0294, "step": 1254 }, { "epoch": 7.943037974683544, "grad_norm": 6112.79443359375, "learning_rate": 1.1013513513513514e-05, "loss": 0.0257, "step": 1255 }, { "epoch": 7.949367088607595, "grad_norm": 8886.1083984375, "learning_rate": 1.097972972972973e-05, "loss": 0.0279, "step": 1256 }, { "epoch": 7.955696202531645, "grad_norm": 7403.3642578125, "learning_rate": 1.0945945945945948e-05, "loss": 0.031, "step": 1257 }, { "epoch": 7.962025316455696, "grad_norm": 5678.19921875, "learning_rate": 1.0912162162162162e-05, "loss": 0.026, "step": 1258 }, { "epoch": 7.968354430379747, "grad_norm": 7671.17236328125, "learning_rate": 1.0878378378378378e-05, "loss": 0.0223, "step": 1259 }, { "epoch": 7.974683544303797, "grad_norm": 5454.4140625, "learning_rate": 1.0844594594594596e-05, "loss": 0.0177, "step": 1260 }, { "epoch": 7.981012658227848, "grad_norm": 6206.50439453125, "learning_rate": 1.0810810810810812e-05, "loss": 0.0241, "step": 1261 }, { "epoch": 7.987341772151899, "grad_norm": 4794.0244140625, "learning_rate": 1.0777027027027026e-05, "loss": 0.0231, "step": 1262 }, { "epoch": 7.993670886075949, "grad_norm": 4481.72705078125, "learning_rate": 1.0743243243243244e-05, "loss": 0.0217, "step": 1263 }, { "epoch": 8.0, "grad_norm": 6399.46240234375, "learning_rate": 1.070945945945946e-05, "loss": 0.017, "step": 1264 }, { "epoch": 8.0, "eval_f1_macro": 0.7215640325392577, "eval_f1_micro": 0.8549905838041432, "eval_loss": 0.03310660272836685, "eval_precision": 0.8901960784313725, "eval_recall": 0.822463768115942, "eval_runtime": 1.1646, "eval_samples_per_second": 361.511, "eval_steps_per_second": 15.457, "step": 1264 }, { "epoch": 8.00632911392405, "grad_norm": 5647.59423828125, "learning_rate": 1.0675675675675677e-05, "loss": 0.0244, "step": 1265 }, { "epoch": 8.012658227848101, "grad_norm": 5589.98876953125, "learning_rate": 1.0641891891891893e-05, "loss": 0.0228, "step": 1266 }, { "epoch": 8.018987341772151, "grad_norm": 6176.2353515625, "learning_rate": 1.0608108108108109e-05, "loss": 0.0152, "step": 1267 }, { "epoch": 8.025316455696203, "grad_norm": 4878.0673828125, "learning_rate": 1.0574324324324325e-05, "loss": 0.0251, "step": 1268 }, { "epoch": 8.031645569620252, "grad_norm": 7009.849609375, "learning_rate": 1.0540540540540541e-05, "loss": 0.0221, "step": 1269 }, { "epoch": 8.037974683544304, "grad_norm": 5215.99462890625, "learning_rate": 1.0506756756756757e-05, "loss": 0.0186, "step": 1270 }, { "epoch": 8.044303797468354, "grad_norm": 4296.912109375, "learning_rate": 1.0472972972972973e-05, "loss": 0.0206, "step": 1271 }, { "epoch": 8.050632911392405, "grad_norm": 8234.05078125, "learning_rate": 1.043918918918919e-05, "loss": 0.0195, "step": 1272 }, { "epoch": 8.056962025316455, "grad_norm": 4824.54443359375, "learning_rate": 1.0405405405405407e-05, "loss": 0.02, "step": 1273 }, { "epoch": 8.063291139240507, "grad_norm": 5695.56689453125, "learning_rate": 1.0371621621621622e-05, "loss": 0.0237, "step": 1274 }, { "epoch": 8.069620253164556, "grad_norm": 4870.4853515625, "learning_rate": 1.0337837837837838e-05, "loss": 0.0219, "step": 1275 }, { "epoch": 8.075949367088608, "grad_norm": 5927.701171875, "learning_rate": 1.0304054054054054e-05, "loss": 0.0239, "step": 1276 }, { "epoch": 8.082278481012658, "grad_norm": 5866.9267578125, "learning_rate": 1.0270270270270272e-05, "loss": 0.0324, "step": 1277 }, { "epoch": 8.08860759493671, "grad_norm": 7914.6015625, "learning_rate": 1.0236486486486486e-05, "loss": 0.0239, "step": 1278 }, { "epoch": 8.094936708860759, "grad_norm": 4056.978271484375, "learning_rate": 1.0202702702702702e-05, "loss": 0.0175, "step": 1279 }, { "epoch": 8.10126582278481, "grad_norm": 5229.30419921875, "learning_rate": 1.016891891891892e-05, "loss": 0.0225, "step": 1280 }, { "epoch": 8.10759493670886, "grad_norm": 4975.7216796875, "learning_rate": 1.0135135135135136e-05, "loss": 0.0219, "step": 1281 }, { "epoch": 8.113924050632912, "grad_norm": 5240.029296875, "learning_rate": 1.010135135135135e-05, "loss": 0.0214, "step": 1282 }, { "epoch": 8.120253164556962, "grad_norm": 6327.25830078125, "learning_rate": 1.0067567567567569e-05, "loss": 0.0248, "step": 1283 }, { "epoch": 8.126582278481013, "grad_norm": 6728.1494140625, "learning_rate": 1.0033783783783785e-05, "loss": 0.0215, "step": 1284 }, { "epoch": 8.132911392405063, "grad_norm": 6960.4443359375, "learning_rate": 1e-05, "loss": 0.0225, "step": 1285 }, { "epoch": 8.139240506329115, "grad_norm": 6017.5556640625, "learning_rate": 9.966216216216217e-06, "loss": 0.0283, "step": 1286 }, { "epoch": 8.145569620253164, "grad_norm": 6566.35546875, "learning_rate": 9.932432432432433e-06, "loss": 0.0177, "step": 1287 }, { "epoch": 8.151898734177216, "grad_norm": 4447.50390625, "learning_rate": 9.89864864864865e-06, "loss": 0.017, "step": 1288 }, { "epoch": 8.158227848101266, "grad_norm": 8874.767578125, "learning_rate": 9.864864864864865e-06, "loss": 0.0266, "step": 1289 }, { "epoch": 8.164556962025316, "grad_norm": 4782.44775390625, "learning_rate": 9.831081081081081e-06, "loss": 0.0197, "step": 1290 }, { "epoch": 8.170886075949367, "grad_norm": 2300.00146484375, "learning_rate": 9.797297297297298e-06, "loss": 0.0135, "step": 1291 }, { "epoch": 8.177215189873417, "grad_norm": 5375.01123046875, "learning_rate": 9.763513513513514e-06, "loss": 0.0129, "step": 1292 }, { "epoch": 8.183544303797468, "grad_norm": 6993.380859375, "learning_rate": 9.729729729729732e-06, "loss": 0.0354, "step": 1293 }, { "epoch": 8.189873417721518, "grad_norm": 6940.9375, "learning_rate": 9.695945945945946e-06, "loss": 0.0179, "step": 1294 }, { "epoch": 8.19620253164557, "grad_norm": 8571.3681640625, "learning_rate": 9.662162162162162e-06, "loss": 0.0263, "step": 1295 }, { "epoch": 8.20253164556962, "grad_norm": 5860.38818359375, "learning_rate": 9.628378378378378e-06, "loss": 0.0318, "step": 1296 }, { "epoch": 8.208860759493671, "grad_norm": 4950.62744140625, "learning_rate": 9.594594594594596e-06, "loss": 0.0166, "step": 1297 }, { "epoch": 8.215189873417721, "grad_norm": 4604.68896484375, "learning_rate": 9.56081081081081e-06, "loss": 0.0176, "step": 1298 }, { "epoch": 8.221518987341772, "grad_norm": 5221.3037109375, "learning_rate": 9.527027027027027e-06, "loss": 0.0186, "step": 1299 }, { "epoch": 8.227848101265822, "grad_norm": 8125.89111328125, "learning_rate": 9.493243243243244e-06, "loss": 0.029, "step": 1300 }, { "epoch": 8.234177215189874, "grad_norm": 3220.805908203125, "learning_rate": 9.45945945945946e-06, "loss": 0.015, "step": 1301 }, { "epoch": 8.240506329113924, "grad_norm": 4724.55078125, "learning_rate": 9.425675675675675e-06, "loss": 0.0171, "step": 1302 }, { "epoch": 8.246835443037975, "grad_norm": 7514.62841796875, "learning_rate": 9.391891891891893e-06, "loss": 0.024, "step": 1303 }, { "epoch": 8.253164556962025, "grad_norm": 4717.1962890625, "learning_rate": 9.358108108108109e-06, "loss": 0.018, "step": 1304 }, { "epoch": 8.259493670886076, "grad_norm": 8132.68359375, "learning_rate": 9.324324324324325e-06, "loss": 0.0344, "step": 1305 }, { "epoch": 8.265822784810126, "grad_norm": 5622.11865234375, "learning_rate": 9.290540540540541e-06, "loss": 0.0198, "step": 1306 }, { "epoch": 8.272151898734178, "grad_norm": 4189.1142578125, "learning_rate": 9.256756756756757e-06, "loss": 0.021, "step": 1307 }, { "epoch": 8.278481012658228, "grad_norm": 9814.9169921875, "learning_rate": 9.222972972972973e-06, "loss": 0.0246, "step": 1308 }, { "epoch": 8.284810126582279, "grad_norm": 4268.13330078125, "learning_rate": 9.18918918918919e-06, "loss": 0.0153, "step": 1309 }, { "epoch": 8.291139240506329, "grad_norm": 4028.20556640625, "learning_rate": 9.155405405405406e-06, "loss": 0.0199, "step": 1310 }, { "epoch": 8.29746835443038, "grad_norm": 4279.7158203125, "learning_rate": 9.121621621621622e-06, "loss": 0.0202, "step": 1311 }, { "epoch": 8.30379746835443, "grad_norm": 6971.779296875, "learning_rate": 9.087837837837838e-06, "loss": 0.0298, "step": 1312 }, { "epoch": 8.310126582278482, "grad_norm": 5055.56103515625, "learning_rate": 9.054054054054056e-06, "loss": 0.024, "step": 1313 }, { "epoch": 8.316455696202532, "grad_norm": 6544.1787109375, "learning_rate": 9.02027027027027e-06, "loss": 0.02, "step": 1314 }, { "epoch": 8.322784810126583, "grad_norm": 3330.90478515625, "learning_rate": 8.986486486486486e-06, "loss": 0.0162, "step": 1315 }, { "epoch": 8.329113924050633, "grad_norm": 3687.6689453125, "learning_rate": 8.952702702702702e-06, "loss": 0.0159, "step": 1316 }, { "epoch": 8.335443037974684, "grad_norm": 3616.333740234375, "learning_rate": 8.91891891891892e-06, "loss": 0.0208, "step": 1317 }, { "epoch": 8.341772151898734, "grad_norm": 5983.85546875, "learning_rate": 8.885135135135135e-06, "loss": 0.0204, "step": 1318 }, { "epoch": 8.348101265822784, "grad_norm": 4073.32421875, "learning_rate": 8.851351351351351e-06, "loss": 0.0205, "step": 1319 }, { "epoch": 8.354430379746836, "grad_norm": 6215.05859375, "learning_rate": 8.817567567567569e-06, "loss": 0.0224, "step": 1320 }, { "epoch": 8.360759493670885, "grad_norm": 8402.2861328125, "learning_rate": 8.783783783783785e-06, "loss": 0.0253, "step": 1321 }, { "epoch": 8.367088607594937, "grad_norm": 4852.43359375, "learning_rate": 8.75e-06, "loss": 0.022, "step": 1322 }, { "epoch": 8.373417721518987, "grad_norm": 5392.61474609375, "learning_rate": 8.716216216216217e-06, "loss": 0.0195, "step": 1323 }, { "epoch": 8.379746835443038, "grad_norm": 6234.06201171875, "learning_rate": 8.682432432432433e-06, "loss": 0.019, "step": 1324 }, { "epoch": 8.386075949367088, "grad_norm": 5082.53857421875, "learning_rate": 8.64864864864865e-06, "loss": 0.0159, "step": 1325 }, { "epoch": 8.39240506329114, "grad_norm": 2662.1494140625, "learning_rate": 8.614864864864865e-06, "loss": 0.0119, "step": 1326 }, { "epoch": 8.39873417721519, "grad_norm": 3734.44970703125, "learning_rate": 8.581081081081082e-06, "loss": 0.0163, "step": 1327 }, { "epoch": 8.405063291139241, "grad_norm": 11851.0478515625, "learning_rate": 8.547297297297298e-06, "loss": 0.0249, "step": 1328 }, { "epoch": 8.41139240506329, "grad_norm": 5123.53369140625, "learning_rate": 8.513513513513514e-06, "loss": 0.022, "step": 1329 }, { "epoch": 8.417721518987342, "grad_norm": 4642.662109375, "learning_rate": 8.47972972972973e-06, "loss": 0.0189, "step": 1330 }, { "epoch": 8.424050632911392, "grad_norm": 8042.7060546875, "learning_rate": 8.445945945945946e-06, "loss": 0.0174, "step": 1331 }, { "epoch": 8.430379746835444, "grad_norm": 18392.326171875, "learning_rate": 8.412162162162162e-06, "loss": 0.0174, "step": 1332 }, { "epoch": 8.436708860759493, "grad_norm": 6654.130859375, "learning_rate": 8.37837837837838e-06, "loss": 0.0276, "step": 1333 }, { "epoch": 8.443037974683545, "grad_norm": 4685.6708984375, "learning_rate": 8.344594594594594e-06, "loss": 0.0179, "step": 1334 }, { "epoch": 8.449367088607595, "grad_norm": 7222.75, "learning_rate": 8.31081081081081e-06, "loss": 0.03, "step": 1335 }, { "epoch": 8.455696202531646, "grad_norm": 9362.232421875, "learning_rate": 8.277027027027027e-06, "loss": 0.0183, "step": 1336 }, { "epoch": 8.462025316455696, "grad_norm": 4254.2548828125, "learning_rate": 8.243243243243245e-06, "loss": 0.0188, "step": 1337 }, { "epoch": 8.468354430379748, "grad_norm": 4444.57958984375, "learning_rate": 8.209459459459459e-06, "loss": 0.0191, "step": 1338 }, { "epoch": 8.474683544303797, "grad_norm": 2235.60546875, "learning_rate": 8.175675675675675e-06, "loss": 0.0114, "step": 1339 }, { "epoch": 8.481012658227849, "grad_norm": 3785.566650390625, "learning_rate": 8.141891891891893e-06, "loss": 0.0181, "step": 1340 }, { "epoch": 8.487341772151899, "grad_norm": 4391.71533203125, "learning_rate": 8.108108108108109e-06, "loss": 0.0191, "step": 1341 }, { "epoch": 8.49367088607595, "grad_norm": 6779.94091796875, "learning_rate": 8.074324324324323e-06, "loss": 0.0256, "step": 1342 }, { "epoch": 8.5, "grad_norm": 2840.234619140625, "learning_rate": 8.040540540540541e-06, "loss": 0.0118, "step": 1343 }, { "epoch": 8.50632911392405, "grad_norm": 8080.37255859375, "learning_rate": 8.006756756756757e-06, "loss": 0.0334, "step": 1344 }, { "epoch": 8.512658227848101, "grad_norm": 4465.9296875, "learning_rate": 7.972972972972974e-06, "loss": 0.0188, "step": 1345 }, { "epoch": 8.518987341772151, "grad_norm": 5907.90380859375, "learning_rate": 7.93918918918919e-06, "loss": 0.0291, "step": 1346 }, { "epoch": 8.525316455696203, "grad_norm": 5400.7744140625, "learning_rate": 7.905405405405406e-06, "loss": 0.0201, "step": 1347 }, { "epoch": 8.531645569620252, "grad_norm": 5629.095703125, "learning_rate": 7.871621621621622e-06, "loss": 0.0154, "step": 1348 }, { "epoch": 8.537974683544304, "grad_norm": 5443.7138671875, "learning_rate": 7.837837837837838e-06, "loss": 0.0236, "step": 1349 }, { "epoch": 8.544303797468354, "grad_norm": 7719.79296875, "learning_rate": 7.804054054054054e-06, "loss": 0.028, "step": 1350 }, { "epoch": 8.550632911392405, "grad_norm": 5954.8271484375, "learning_rate": 7.77027027027027e-06, "loss": 0.017, "step": 1351 }, { "epoch": 8.556962025316455, "grad_norm": 9069.267578125, "learning_rate": 7.736486486486486e-06, "loss": 0.0201, "step": 1352 }, { "epoch": 8.563291139240507, "grad_norm": 8610.8076171875, "learning_rate": 7.702702702702704e-06, "loss": 0.0389, "step": 1353 }, { "epoch": 8.569620253164556, "grad_norm": 6526.51416015625, "learning_rate": 7.668918918918919e-06, "loss": 0.0171, "step": 1354 }, { "epoch": 8.575949367088608, "grad_norm": 4550.98486328125, "learning_rate": 7.635135135135135e-06, "loss": 0.0212, "step": 1355 }, { "epoch": 8.582278481012658, "grad_norm": 9158.904296875, "learning_rate": 7.601351351351352e-06, "loss": 0.0299, "step": 1356 }, { "epoch": 8.58860759493671, "grad_norm": 3118.699462890625, "learning_rate": 7.567567567567568e-06, "loss": 0.0148, "step": 1357 }, { "epoch": 8.594936708860759, "grad_norm": 3467.841796875, "learning_rate": 7.533783783783783e-06, "loss": 0.0211, "step": 1358 }, { "epoch": 8.60126582278481, "grad_norm": 5226.2939453125, "learning_rate": 7.5e-06, "loss": 0.0207, "step": 1359 }, { "epoch": 8.60759493670886, "grad_norm": 14713.0244140625, "learning_rate": 7.466216216216216e-06, "loss": 0.0253, "step": 1360 }, { "epoch": 8.613924050632912, "grad_norm": 3984.876220703125, "learning_rate": 7.432432432432433e-06, "loss": 0.0188, "step": 1361 }, { "epoch": 8.620253164556962, "grad_norm": 6351.97314453125, "learning_rate": 7.3986486486486486e-06, "loss": 0.0231, "step": 1362 }, { "epoch": 8.626582278481013, "grad_norm": 4950.03564453125, "learning_rate": 7.364864864864865e-06, "loss": 0.0151, "step": 1363 }, { "epoch": 8.632911392405063, "grad_norm": 5117.7216796875, "learning_rate": 7.331081081081082e-06, "loss": 0.0159, "step": 1364 }, { "epoch": 8.639240506329115, "grad_norm": 7496.697265625, "learning_rate": 7.297297297297298e-06, "loss": 0.0229, "step": 1365 }, { "epoch": 8.645569620253164, "grad_norm": 8397.1025390625, "learning_rate": 7.263513513513513e-06, "loss": 0.0256, "step": 1366 }, { "epoch": 8.651898734177216, "grad_norm": 6140.5322265625, "learning_rate": 7.22972972972973e-06, "loss": 0.0216, "step": 1367 }, { "epoch": 8.658227848101266, "grad_norm": 5110.48095703125, "learning_rate": 7.195945945945946e-06, "loss": 0.019, "step": 1368 }, { "epoch": 8.664556962025316, "grad_norm": 8486.859375, "learning_rate": 7.162162162162163e-06, "loss": 0.0222, "step": 1369 }, { "epoch": 8.670886075949367, "grad_norm": 4600.76025390625, "learning_rate": 7.1283783783783784e-06, "loss": 0.0196, "step": 1370 }, { "epoch": 8.677215189873417, "grad_norm": 4485.80029296875, "learning_rate": 7.0945945945945946e-06, "loss": 0.017, "step": 1371 }, { "epoch": 8.683544303797468, "grad_norm": 5346.259765625, "learning_rate": 7.0608108108108115e-06, "loss": 0.0293, "step": 1372 }, { "epoch": 8.689873417721518, "grad_norm": 6091.9833984375, "learning_rate": 7.027027027027028e-06, "loss": 0.0206, "step": 1373 }, { "epoch": 8.69620253164557, "grad_norm": 5004.16455078125, "learning_rate": 6.993243243243243e-06, "loss": 0.018, "step": 1374 }, { "epoch": 8.70253164556962, "grad_norm": 4575.29638671875, "learning_rate": 6.959459459459459e-06, "loss": 0.0188, "step": 1375 }, { "epoch": 8.708860759493671, "grad_norm": 5226.37353515625, "learning_rate": 6.925675675675676e-06, "loss": 0.0145, "step": 1376 }, { "epoch": 8.715189873417721, "grad_norm": 7544.9833984375, "learning_rate": 6.891891891891893e-06, "loss": 0.0216, "step": 1377 }, { "epoch": 8.721518987341772, "grad_norm": 4806.31396484375, "learning_rate": 6.8581081081081075e-06, "loss": 0.0186, "step": 1378 }, { "epoch": 8.727848101265822, "grad_norm": 8074.03125, "learning_rate": 6.8243243243243244e-06, "loss": 0.0173, "step": 1379 }, { "epoch": 8.734177215189874, "grad_norm": 4020.315673828125, "learning_rate": 6.7905405405405406e-06, "loss": 0.0144, "step": 1380 }, { "epoch": 8.740506329113924, "grad_norm": 9086.4267578125, "learning_rate": 6.7567567567567575e-06, "loss": 0.0297, "step": 1381 }, { "epoch": 8.746835443037975, "grad_norm": 8407.779296875, "learning_rate": 6.722972972972973e-06, "loss": 0.0223, "step": 1382 }, { "epoch": 8.753164556962025, "grad_norm": 3631.96630859375, "learning_rate": 6.689189189189189e-06, "loss": 0.0154, "step": 1383 }, { "epoch": 8.759493670886076, "grad_norm": 4968.0380859375, "learning_rate": 6.655405405405406e-06, "loss": 0.0201, "step": 1384 }, { "epoch": 8.765822784810126, "grad_norm": 4131.43896484375, "learning_rate": 6.621621621621622e-06, "loss": 0.0182, "step": 1385 }, { "epoch": 8.772151898734178, "grad_norm": 5505.75390625, "learning_rate": 6.587837837837837e-06, "loss": 0.0183, "step": 1386 }, { "epoch": 8.778481012658228, "grad_norm": 6223.2080078125, "learning_rate": 6.554054054054054e-06, "loss": 0.0236, "step": 1387 }, { "epoch": 8.784810126582279, "grad_norm": 6905.80224609375, "learning_rate": 6.5202702702702704e-06, "loss": 0.0227, "step": 1388 }, { "epoch": 8.791139240506329, "grad_norm": 2980.259033203125, "learning_rate": 6.486486486486487e-06, "loss": 0.013, "step": 1389 }, { "epoch": 8.79746835443038, "grad_norm": 6401.7392578125, "learning_rate": 6.452702702702703e-06, "loss": 0.0145, "step": 1390 }, { "epoch": 8.80379746835443, "grad_norm": 4488.6064453125, "learning_rate": 6.418918918918919e-06, "loss": 0.0186, "step": 1391 }, { "epoch": 8.810126582278482, "grad_norm": 5790.84716796875, "learning_rate": 6.385135135135136e-06, "loss": 0.0224, "step": 1392 }, { "epoch": 8.816455696202532, "grad_norm": 3087.257568359375, "learning_rate": 6.351351351351352e-06, "loss": 0.0147, "step": 1393 }, { "epoch": 8.822784810126583, "grad_norm": 4499.32421875, "learning_rate": 6.317567567567567e-06, "loss": 0.0177, "step": 1394 }, { "epoch": 8.829113924050633, "grad_norm": 4949.1328125, "learning_rate": 6.283783783783783e-06, "loss": 0.025, "step": 1395 }, { "epoch": 8.835443037974684, "grad_norm": 3662.805908203125, "learning_rate": 6.25e-06, "loss": 0.0123, "step": 1396 }, { "epoch": 8.841772151898734, "grad_norm": 5202.138671875, "learning_rate": 6.216216216216217e-06, "loss": 0.0184, "step": 1397 }, { "epoch": 8.848101265822784, "grad_norm": 4380.07373046875, "learning_rate": 6.1824324324324326e-06, "loss": 0.0233, "step": 1398 }, { "epoch": 8.854430379746836, "grad_norm": 5282.400390625, "learning_rate": 6.1486486486486495e-06, "loss": 0.0186, "step": 1399 }, { "epoch": 8.860759493670885, "grad_norm": 5572.75830078125, "learning_rate": 6.114864864864865e-06, "loss": 0.0191, "step": 1400 }, { "epoch": 8.867088607594937, "grad_norm": 6147.54052734375, "learning_rate": 6.081081081081082e-06, "loss": 0.0311, "step": 1401 }, { "epoch": 8.873417721518987, "grad_norm": 6690.7548828125, "learning_rate": 6.047297297297298e-06, "loss": 0.0194, "step": 1402 }, { "epoch": 8.879746835443038, "grad_norm": 3350.921142578125, "learning_rate": 6.013513513513514e-06, "loss": 0.0192, "step": 1403 }, { "epoch": 8.886075949367088, "grad_norm": 5318.12890625, "learning_rate": 5.97972972972973e-06, "loss": 0.0232, "step": 1404 }, { "epoch": 8.89240506329114, "grad_norm": 8900.2421875, "learning_rate": 5.945945945945946e-06, "loss": 0.0308, "step": 1405 }, { "epoch": 8.89873417721519, "grad_norm": 4855.9921875, "learning_rate": 5.912162162162162e-06, "loss": 0.0203, "step": 1406 }, { "epoch": 8.905063291139241, "grad_norm": 7150.3115234375, "learning_rate": 5.878378378378379e-06, "loss": 0.0178, "step": 1407 }, { "epoch": 8.91139240506329, "grad_norm": 4022.42578125, "learning_rate": 5.844594594594595e-06, "loss": 0.0154, "step": 1408 }, { "epoch": 8.917721518987342, "grad_norm": 4469.34716796875, "learning_rate": 5.810810810810812e-06, "loss": 0.0151, "step": 1409 }, { "epoch": 8.924050632911392, "grad_norm": 6137.98779296875, "learning_rate": 5.777027027027027e-06, "loss": 0.0192, "step": 1410 }, { "epoch": 8.930379746835444, "grad_norm": 10462.580078125, "learning_rate": 5.743243243243244e-06, "loss": 0.0222, "step": 1411 }, { "epoch": 8.936708860759493, "grad_norm": 12617.376953125, "learning_rate": 5.70945945945946e-06, "loss": 0.0387, "step": 1412 }, { "epoch": 8.943037974683545, "grad_norm": 4043.99267578125, "learning_rate": 5.675675675675676e-06, "loss": 0.0188, "step": 1413 }, { "epoch": 8.949367088607595, "grad_norm": 5247.42626953125, "learning_rate": 5.641891891891892e-06, "loss": 0.0243, "step": 1414 }, { "epoch": 8.955696202531646, "grad_norm": 7718.373046875, "learning_rate": 5.608108108108108e-06, "loss": 0.0223, "step": 1415 }, { "epoch": 8.962025316455696, "grad_norm": 6378.3818359375, "learning_rate": 5.5743243243243245e-06, "loss": 0.0212, "step": 1416 }, { "epoch": 8.968354430379748, "grad_norm": 3553.639404296875, "learning_rate": 5.5405405405405415e-06, "loss": 0.0138, "step": 1417 }, { "epoch": 8.974683544303797, "grad_norm": 3565.91845703125, "learning_rate": 5.506756756756757e-06, "loss": 0.0146, "step": 1418 }, { "epoch": 8.981012658227849, "grad_norm": 5839.60595703125, "learning_rate": 5.472972972972974e-06, "loss": 0.0245, "step": 1419 }, { "epoch": 8.987341772151899, "grad_norm": 4001.90966796875, "learning_rate": 5.439189189189189e-06, "loss": 0.0171, "step": 1420 }, { "epoch": 8.99367088607595, "grad_norm": 4000.567626953125, "learning_rate": 5.405405405405406e-06, "loss": 0.0178, "step": 1421 }, { "epoch": 9.0, "grad_norm": 3347.4599609375, "learning_rate": 5.371621621621622e-06, "loss": 0.0147, "step": 1422 }, { "epoch": 9.0, "eval_f1_macro": 0.7643975778317821, "eval_f1_micro": 0.8710280373831776, "eval_loss": 0.0312948077917099, "eval_precision": 0.8996138996138996, "eval_recall": 0.8442028985507246, "eval_runtime": 1.1538, "eval_samples_per_second": 364.878, "eval_steps_per_second": 15.6, "step": 1422 }, { "epoch": 9.00632911392405, "grad_norm": 4195.5302734375, "learning_rate": 5.337837837837838e-06, "loss": 0.0175, "step": 1423 }, { "epoch": 9.012658227848101, "grad_norm": 4963.3232421875, "learning_rate": 5.304054054054054e-06, "loss": 0.0229, "step": 1424 }, { "epoch": 9.018987341772151, "grad_norm": 3389.2451171875, "learning_rate": 5.2702702702702705e-06, "loss": 0.0123, "step": 1425 }, { "epoch": 9.025316455696203, "grad_norm": 4169.0341796875, "learning_rate": 5.236486486486487e-06, "loss": 0.0196, "step": 1426 }, { "epoch": 9.031645569620252, "grad_norm": 4081.445556640625, "learning_rate": 5.202702702702704e-06, "loss": 0.018, "step": 1427 }, { "epoch": 9.037974683544304, "grad_norm": 6959.91015625, "learning_rate": 5.168918918918919e-06, "loss": 0.0217, "step": 1428 }, { "epoch": 9.044303797468354, "grad_norm": 3914.58447265625, "learning_rate": 5.135135135135136e-06, "loss": 0.0143, "step": 1429 }, { "epoch": 9.050632911392405, "grad_norm": 4396.8525390625, "learning_rate": 5.101351351351351e-06, "loss": 0.0236, "step": 1430 }, { "epoch": 9.056962025316455, "grad_norm": 3571.96923828125, "learning_rate": 5.067567567567568e-06, "loss": 0.0182, "step": 1431 }, { "epoch": 9.063291139240507, "grad_norm": 4088.5419921875, "learning_rate": 5.033783783783784e-06, "loss": 0.0194, "step": 1432 }, { "epoch": 9.069620253164556, "grad_norm": 11015.2822265625, "learning_rate": 5e-06, "loss": 0.024, "step": 1433 }, { "epoch": 9.075949367088608, "grad_norm": 3175.188720703125, "learning_rate": 4.9662162162162165e-06, "loss": 0.0155, "step": 1434 }, { "epoch": 9.082278481012658, "grad_norm": 4003.810791015625, "learning_rate": 4.932432432432433e-06, "loss": 0.0223, "step": 1435 }, { "epoch": 9.08860759493671, "grad_norm": 2876.060791015625, "learning_rate": 4.898648648648649e-06, "loss": 0.0139, "step": 1436 }, { "epoch": 9.094936708860759, "grad_norm": 4895.52587890625, "learning_rate": 4.864864864864866e-06, "loss": 0.0295, "step": 1437 }, { "epoch": 9.10126582278481, "grad_norm": 5374.94873046875, "learning_rate": 4.831081081081081e-06, "loss": 0.0276, "step": 1438 }, { "epoch": 9.10759493670886, "grad_norm": 5826.67919921875, "learning_rate": 4.797297297297298e-06, "loss": 0.0242, "step": 1439 }, { "epoch": 9.113924050632912, "grad_norm": 12613.74609375, "learning_rate": 4.763513513513513e-06, "loss": 0.0232, "step": 1440 }, { "epoch": 9.120253164556962, "grad_norm": 4181.39794921875, "learning_rate": 4.72972972972973e-06, "loss": 0.0146, "step": 1441 }, { "epoch": 9.126582278481013, "grad_norm": 5596.11328125, "learning_rate": 4.695945945945946e-06, "loss": 0.0226, "step": 1442 }, { "epoch": 9.132911392405063, "grad_norm": 3730.248046875, "learning_rate": 4.6621621621621625e-06, "loss": 0.0164, "step": 1443 }, { "epoch": 9.139240506329115, "grad_norm": 5458.3515625, "learning_rate": 4.628378378378379e-06, "loss": 0.0257, "step": 1444 }, { "epoch": 9.145569620253164, "grad_norm": 4022.319091796875, "learning_rate": 4.594594594594595e-06, "loss": 0.0203, "step": 1445 }, { "epoch": 9.151898734177216, "grad_norm": 5645.58203125, "learning_rate": 4.560810810810811e-06, "loss": 0.0169, "step": 1446 }, { "epoch": 9.158227848101266, "grad_norm": 4179.24658203125, "learning_rate": 4.527027027027028e-06, "loss": 0.0224, "step": 1447 }, { "epoch": 9.164556962025316, "grad_norm": 5925.15771484375, "learning_rate": 4.493243243243243e-06, "loss": 0.0268, "step": 1448 }, { "epoch": 9.170886075949367, "grad_norm": 5621.4453125, "learning_rate": 4.45945945945946e-06, "loss": 0.0223, "step": 1449 }, { "epoch": 9.177215189873417, "grad_norm": 4678.9912109375, "learning_rate": 4.4256756756756754e-06, "loss": 0.0212, "step": 1450 }, { "epoch": 9.183544303797468, "grad_norm": 4384.37255859375, "learning_rate": 4.391891891891892e-06, "loss": 0.0144, "step": 1451 }, { "epoch": 9.189873417721518, "grad_norm": 3452.24853515625, "learning_rate": 4.3581081081081085e-06, "loss": 0.0174, "step": 1452 }, { "epoch": 9.19620253164557, "grad_norm": 4592.26025390625, "learning_rate": 4.324324324324325e-06, "loss": 0.0229, "step": 1453 }, { "epoch": 9.20253164556962, "grad_norm": 3615.19091796875, "learning_rate": 4.290540540540541e-06, "loss": 0.0179, "step": 1454 }, { "epoch": 9.208860759493671, "grad_norm": 2296.385986328125, "learning_rate": 4.256756756756757e-06, "loss": 0.0114, "step": 1455 }, { "epoch": 9.215189873417721, "grad_norm": 4357.5244140625, "learning_rate": 4.222972972972973e-06, "loss": 0.0156, "step": 1456 }, { "epoch": 9.221518987341772, "grad_norm": 5695.57275390625, "learning_rate": 4.18918918918919e-06, "loss": 0.0187, "step": 1457 }, { "epoch": 9.227848101265822, "grad_norm": 5027.3935546875, "learning_rate": 4.155405405405405e-06, "loss": 0.0204, "step": 1458 }, { "epoch": 9.234177215189874, "grad_norm": 3897.61083984375, "learning_rate": 4.121621621621622e-06, "loss": 0.0189, "step": 1459 }, { "epoch": 9.240506329113924, "grad_norm": 6646.19873046875, "learning_rate": 4.0878378378378375e-06, "loss": 0.0281, "step": 1460 }, { "epoch": 9.246835443037975, "grad_norm": 5761.47119140625, "learning_rate": 4.0540540540540545e-06, "loss": 0.0222, "step": 1461 }, { "epoch": 9.253164556962025, "grad_norm": 6726.2392578125, "learning_rate": 4.020270270270271e-06, "loss": 0.0184, "step": 1462 }, { "epoch": 9.259493670886076, "grad_norm": 6107.423828125, "learning_rate": 3.986486486486487e-06, "loss": 0.0232, "step": 1463 }, { "epoch": 9.265822784810126, "grad_norm": 8094.17236328125, "learning_rate": 3.952702702702703e-06, "loss": 0.0225, "step": 1464 }, { "epoch": 9.272151898734178, "grad_norm": 6746.9169921875, "learning_rate": 3.918918918918919e-06, "loss": 0.0363, "step": 1465 }, { "epoch": 9.278481012658228, "grad_norm": 3979.628662109375, "learning_rate": 3.885135135135135e-06, "loss": 0.0156, "step": 1466 }, { "epoch": 9.284810126582279, "grad_norm": 9875.8779296875, "learning_rate": 3.851351351351352e-06, "loss": 0.0233, "step": 1467 }, { "epoch": 9.291139240506329, "grad_norm": 4386.0009765625, "learning_rate": 3.817567567567567e-06, "loss": 0.0167, "step": 1468 }, { "epoch": 9.29746835443038, "grad_norm": 5169.7578125, "learning_rate": 3.783783783783784e-06, "loss": 0.0171, "step": 1469 }, { "epoch": 9.30379746835443, "grad_norm": 2713.2353515625, "learning_rate": 3.75e-06, "loss": 0.0124, "step": 1470 }, { "epoch": 9.310126582278482, "grad_norm": 5376.27880859375, "learning_rate": 3.7162162162162166e-06, "loss": 0.0173, "step": 1471 }, { "epoch": 9.316455696202532, "grad_norm": 9090.0712890625, "learning_rate": 3.6824324324324324e-06, "loss": 0.0241, "step": 1472 }, { "epoch": 9.322784810126583, "grad_norm": 4424.85595703125, "learning_rate": 3.648648648648649e-06, "loss": 0.0221, "step": 1473 }, { "epoch": 9.329113924050633, "grad_norm": 5778.306640625, "learning_rate": 3.614864864864865e-06, "loss": 0.0232, "step": 1474 }, { "epoch": 9.335443037974684, "grad_norm": 3224.90185546875, "learning_rate": 3.5810810810810816e-06, "loss": 0.0155, "step": 1475 }, { "epoch": 9.341772151898734, "grad_norm": 5951.39111328125, "learning_rate": 3.5472972972972973e-06, "loss": 0.0228, "step": 1476 }, { "epoch": 9.348101265822784, "grad_norm": 4975.4140625, "learning_rate": 3.513513513513514e-06, "loss": 0.0234, "step": 1477 }, { "epoch": 9.354430379746836, "grad_norm": 8235.3330078125, "learning_rate": 3.4797297297297295e-06, "loss": 0.0317, "step": 1478 }, { "epoch": 9.360759493670885, "grad_norm": 3810.461181640625, "learning_rate": 3.4459459459459465e-06, "loss": 0.0187, "step": 1479 }, { "epoch": 9.367088607594937, "grad_norm": 4247.85400390625, "learning_rate": 3.4121621621621622e-06, "loss": 0.0188, "step": 1480 }, { "epoch": 9.373417721518987, "grad_norm": 6260.369140625, "learning_rate": 3.3783783783783788e-06, "loss": 0.0236, "step": 1481 }, { "epoch": 9.379746835443038, "grad_norm": 4260.41943359375, "learning_rate": 3.3445945945945945e-06, "loss": 0.0139, "step": 1482 }, { "epoch": 9.386075949367088, "grad_norm": 3206.26171875, "learning_rate": 3.310810810810811e-06, "loss": 0.014, "step": 1483 }, { "epoch": 9.39240506329114, "grad_norm": 6610.3916015625, "learning_rate": 3.277027027027027e-06, "loss": 0.0167, "step": 1484 }, { "epoch": 9.39873417721519, "grad_norm": 5394.169921875, "learning_rate": 3.2432432432432437e-06, "loss": 0.0256, "step": 1485 }, { "epoch": 9.405063291139241, "grad_norm": 2113.685546875, "learning_rate": 3.2094594594594594e-06, "loss": 0.0129, "step": 1486 }, { "epoch": 9.41139240506329, "grad_norm": 6425.41943359375, "learning_rate": 3.175675675675676e-06, "loss": 0.0192, "step": 1487 }, { "epoch": 9.417721518987342, "grad_norm": 3725.0966796875, "learning_rate": 3.1418918918918917e-06, "loss": 0.0154, "step": 1488 }, { "epoch": 9.424050632911392, "grad_norm": 8484.1962890625, "learning_rate": 3.1081081081081086e-06, "loss": 0.0255, "step": 1489 }, { "epoch": 9.430379746835444, "grad_norm": 3161.779296875, "learning_rate": 3.0743243243243248e-06, "loss": 0.0198, "step": 1490 }, { "epoch": 9.436708860759493, "grad_norm": 8524.9697265625, "learning_rate": 3.040540540540541e-06, "loss": 0.0302, "step": 1491 }, { "epoch": 9.443037974683545, "grad_norm": 3389.587646484375, "learning_rate": 3.006756756756757e-06, "loss": 0.0169, "step": 1492 }, { "epoch": 9.449367088607595, "grad_norm": 7398.10986328125, "learning_rate": 2.972972972972973e-06, "loss": 0.0244, "step": 1493 }, { "epoch": 9.455696202531646, "grad_norm": 4673.8701171875, "learning_rate": 2.9391891891891897e-06, "loss": 0.0193, "step": 1494 }, { "epoch": 9.462025316455696, "grad_norm": 8592.9091796875, "learning_rate": 2.905405405405406e-06, "loss": 0.0223, "step": 1495 }, { "epoch": 9.468354430379748, "grad_norm": 7458.6845703125, "learning_rate": 2.871621621621622e-06, "loss": 0.0171, "step": 1496 }, { "epoch": 9.474683544303797, "grad_norm": 4682.17236328125, "learning_rate": 2.837837837837838e-06, "loss": 0.0189, "step": 1497 }, { "epoch": 9.481012658227849, "grad_norm": 5256.11474609375, "learning_rate": 2.804054054054054e-06, "loss": 0.0208, "step": 1498 }, { "epoch": 9.487341772151899, "grad_norm": 5500.7880859375, "learning_rate": 2.7702702702702708e-06, "loss": 0.0263, "step": 1499 }, { "epoch": 9.49367088607595, "grad_norm": 4562.2705078125, "learning_rate": 2.736486486486487e-06, "loss": 0.0172, "step": 1500 }, { "epoch": 9.5, "grad_norm": 4849.03125, "learning_rate": 2.702702702702703e-06, "loss": 0.0169, "step": 1501 }, { "epoch": 9.50632911392405, "grad_norm": 5646.50439453125, "learning_rate": 2.668918918918919e-06, "loss": 0.0185, "step": 1502 }, { "epoch": 9.512658227848101, "grad_norm": 8630.474609375, "learning_rate": 2.6351351351351353e-06, "loss": 0.0206, "step": 1503 }, { "epoch": 9.518987341772151, "grad_norm": 7163.75732421875, "learning_rate": 2.601351351351352e-06, "loss": 0.0189, "step": 1504 }, { "epoch": 9.525316455696203, "grad_norm": 7227.0380859375, "learning_rate": 2.567567567567568e-06, "loss": 0.0205, "step": 1505 }, { "epoch": 9.531645569620252, "grad_norm": 4288.09619140625, "learning_rate": 2.533783783783784e-06, "loss": 0.0236, "step": 1506 }, { "epoch": 9.537974683544304, "grad_norm": 8326.962890625, "learning_rate": 2.5e-06, "loss": 0.0215, "step": 1507 }, { "epoch": 9.544303797468354, "grad_norm": 5769.83447265625, "learning_rate": 2.4662162162162163e-06, "loss": 0.0165, "step": 1508 }, { "epoch": 9.550632911392405, "grad_norm": 3040.544677734375, "learning_rate": 2.432432432432433e-06, "loss": 0.0153, "step": 1509 }, { "epoch": 9.556962025316455, "grad_norm": 5413.25, "learning_rate": 2.398648648648649e-06, "loss": 0.0211, "step": 1510 }, { "epoch": 9.563291139240507, "grad_norm": 4846.06787109375, "learning_rate": 2.364864864864865e-06, "loss": 0.0188, "step": 1511 }, { "epoch": 9.569620253164556, "grad_norm": 4603.5244140625, "learning_rate": 2.3310810810810813e-06, "loss": 0.0221, "step": 1512 }, { "epoch": 9.575949367088608, "grad_norm": 2935.1943359375, "learning_rate": 2.2972972972972974e-06, "loss": 0.0144, "step": 1513 }, { "epoch": 9.582278481012658, "grad_norm": 9194.966796875, "learning_rate": 2.263513513513514e-06, "loss": 0.0259, "step": 1514 }, { "epoch": 9.58860759493671, "grad_norm": 5734.80224609375, "learning_rate": 2.22972972972973e-06, "loss": 0.029, "step": 1515 }, { "epoch": 9.594936708860759, "grad_norm": 3625.7802734375, "learning_rate": 2.195945945945946e-06, "loss": 0.0191, "step": 1516 }, { "epoch": 9.60126582278481, "grad_norm": 5501.451171875, "learning_rate": 2.1621621621621623e-06, "loss": 0.0224, "step": 1517 }, { "epoch": 9.60759493670886, "grad_norm": 4303.3818359375, "learning_rate": 2.1283783783783785e-06, "loss": 0.0169, "step": 1518 }, { "epoch": 9.613924050632912, "grad_norm": 3775.665283203125, "learning_rate": 2.094594594594595e-06, "loss": 0.0158, "step": 1519 }, { "epoch": 9.620253164556962, "grad_norm": 5485.66650390625, "learning_rate": 2.060810810810811e-06, "loss": 0.0211, "step": 1520 }, { "epoch": 9.626582278481013, "grad_norm": 5090.89501953125, "learning_rate": 2.0270270270270273e-06, "loss": 0.0158, "step": 1521 }, { "epoch": 9.632911392405063, "grad_norm": 7354.7939453125, "learning_rate": 1.9932432432432434e-06, "loss": 0.0157, "step": 1522 }, { "epoch": 9.639240506329115, "grad_norm": 7369.857421875, "learning_rate": 1.9594594594594595e-06, "loss": 0.023, "step": 1523 }, { "epoch": 9.645569620253164, "grad_norm": 3120.089599609375, "learning_rate": 1.925675675675676e-06, "loss": 0.0114, "step": 1524 }, { "epoch": 9.651898734177216, "grad_norm": 3964.743408203125, "learning_rate": 1.891891891891892e-06, "loss": 0.0138, "step": 1525 }, { "epoch": 9.658227848101266, "grad_norm": 6079.36767578125, "learning_rate": 1.8581081081081083e-06, "loss": 0.0199, "step": 1526 }, { "epoch": 9.664556962025316, "grad_norm": 3716.937255859375, "learning_rate": 1.8243243243243245e-06, "loss": 0.0153, "step": 1527 }, { "epoch": 9.670886075949367, "grad_norm": 5259.61328125, "learning_rate": 1.7905405405405408e-06, "loss": 0.0199, "step": 1528 }, { "epoch": 9.677215189873417, "grad_norm": 3041.345703125, "learning_rate": 1.756756756756757e-06, "loss": 0.0169, "step": 1529 }, { "epoch": 9.683544303797468, "grad_norm": 3909.370361328125, "learning_rate": 1.7229729729729733e-06, "loss": 0.0172, "step": 1530 }, { "epoch": 9.689873417721518, "grad_norm": 4826.62060546875, "learning_rate": 1.6891891891891894e-06, "loss": 0.0183, "step": 1531 }, { "epoch": 9.69620253164557, "grad_norm": 3565.88818359375, "learning_rate": 1.6554054054054055e-06, "loss": 0.0189, "step": 1532 }, { "epoch": 9.70253164556962, "grad_norm": 3870.014404296875, "learning_rate": 1.6216216216216219e-06, "loss": 0.0194, "step": 1533 }, { "epoch": 9.708860759493671, "grad_norm": 2452.5361328125, "learning_rate": 1.587837837837838e-06, "loss": 0.0112, "step": 1534 }, { "epoch": 9.715189873417721, "grad_norm": 4296.7529296875, "learning_rate": 1.5540540540540543e-06, "loss": 0.0239, "step": 1535 }, { "epoch": 9.721518987341772, "grad_norm": 4108.4462890625, "learning_rate": 1.5202702702702704e-06, "loss": 0.0204, "step": 1536 }, { "epoch": 9.727848101265822, "grad_norm": 7633.20166015625, "learning_rate": 1.4864864864864866e-06, "loss": 0.0199, "step": 1537 }, { "epoch": 9.734177215189874, "grad_norm": 4186.79736328125, "learning_rate": 1.452702702702703e-06, "loss": 0.0186, "step": 1538 }, { "epoch": 9.740506329113924, "grad_norm": 4036.449951171875, "learning_rate": 1.418918918918919e-06, "loss": 0.0163, "step": 1539 }, { "epoch": 9.746835443037975, "grad_norm": 4892.92919921875, "learning_rate": 1.3851351351351354e-06, "loss": 0.0155, "step": 1540 }, { "epoch": 9.753164556962025, "grad_norm": 7105.88623046875, "learning_rate": 1.3513513513513515e-06, "loss": 0.0239, "step": 1541 }, { "epoch": 9.759493670886076, "grad_norm": 5368.95068359375, "learning_rate": 1.3175675675675676e-06, "loss": 0.0133, "step": 1542 }, { "epoch": 9.765822784810126, "grad_norm": 4700.662109375, "learning_rate": 1.283783783783784e-06, "loss": 0.0176, "step": 1543 }, { "epoch": 9.772151898734178, "grad_norm": 7632.470703125, "learning_rate": 1.25e-06, "loss": 0.0225, "step": 1544 }, { "epoch": 9.778481012658228, "grad_norm": 4770.4833984375, "learning_rate": 1.2162162162162164e-06, "loss": 0.0171, "step": 1545 }, { "epoch": 9.784810126582279, "grad_norm": 3933.305419921875, "learning_rate": 1.1824324324324326e-06, "loss": 0.0179, "step": 1546 }, { "epoch": 9.791139240506329, "grad_norm": 5989.0341796875, "learning_rate": 1.1486486486486487e-06, "loss": 0.0265, "step": 1547 }, { "epoch": 9.79746835443038, "grad_norm": 3373.62890625, "learning_rate": 1.114864864864865e-06, "loss": 0.0146, "step": 1548 }, { "epoch": 9.80379746835443, "grad_norm": 4427.24755859375, "learning_rate": 1.0810810810810812e-06, "loss": 0.0146, "step": 1549 }, { "epoch": 9.810126582278482, "grad_norm": 3706.365234375, "learning_rate": 1.0472972972972975e-06, "loss": 0.015, "step": 1550 }, { "epoch": 9.816455696202532, "grad_norm": 4094.35693359375, "learning_rate": 1.0135135135135136e-06, "loss": 0.0121, "step": 1551 }, { "epoch": 9.822784810126583, "grad_norm": 6252.4150390625, "learning_rate": 9.797297297297298e-07, "loss": 0.0158, "step": 1552 }, { "epoch": 9.829113924050633, "grad_norm": 8649.5888671875, "learning_rate": 9.45945945945946e-07, "loss": 0.0168, "step": 1553 }, { "epoch": 9.835443037974684, "grad_norm": 6174.6318359375, "learning_rate": 9.121621621621622e-07, "loss": 0.0239, "step": 1554 }, { "epoch": 9.841772151898734, "grad_norm": 6660.65185546875, "learning_rate": 8.783783783783785e-07, "loss": 0.0199, "step": 1555 }, { "epoch": 9.848101265822784, "grad_norm": 2908.96630859375, "learning_rate": 8.445945945945947e-07, "loss": 0.0116, "step": 1556 }, { "epoch": 9.854430379746836, "grad_norm": 5173.4794921875, "learning_rate": 8.108108108108109e-07, "loss": 0.0194, "step": 1557 }, { "epoch": 9.860759493670885, "grad_norm": 4101.8818359375, "learning_rate": 7.770270270270272e-07, "loss": 0.0173, "step": 1558 }, { "epoch": 9.867088607594937, "grad_norm": 3504.860595703125, "learning_rate": 7.432432432432433e-07, "loss": 0.0231, "step": 1559 }, { "epoch": 9.873417721518987, "grad_norm": 2868.59521484375, "learning_rate": 7.094594594594595e-07, "loss": 0.0161, "step": 1560 }, { "epoch": 9.879746835443038, "grad_norm": 6072.94970703125, "learning_rate": 6.756756756756758e-07, "loss": 0.0259, "step": 1561 }, { "epoch": 9.886075949367088, "grad_norm": 6917.45166015625, "learning_rate": 6.41891891891892e-07, "loss": 0.0133, "step": 1562 }, { "epoch": 9.89240506329114, "grad_norm": 4718.0712890625, "learning_rate": 6.081081081081082e-07, "loss": 0.0123, "step": 1563 }, { "epoch": 9.89873417721519, "grad_norm": 6167.46630859375, "learning_rate": 5.743243243243243e-07, "loss": 0.0207, "step": 1564 }, { "epoch": 9.905063291139241, "grad_norm": 3247.37646484375, "learning_rate": 5.405405405405406e-07, "loss": 0.0166, "step": 1565 }, { "epoch": 9.91139240506329, "grad_norm": 5509.14794921875, "learning_rate": 5.067567567567568e-07, "loss": 0.0167, "step": 1566 }, { "epoch": 9.917721518987342, "grad_norm": 5141.52099609375, "learning_rate": 4.72972972972973e-07, "loss": 0.0274, "step": 1567 }, { "epoch": 9.924050632911392, "grad_norm": 3038.513427734375, "learning_rate": 4.3918918918918923e-07, "loss": 0.0168, "step": 1568 }, { "epoch": 9.930379746835444, "grad_norm": 2700.086181640625, "learning_rate": 4.0540540540540546e-07, "loss": 0.0111, "step": 1569 }, { "epoch": 9.936708860759493, "grad_norm": 3634.914794921875, "learning_rate": 3.7162162162162164e-07, "loss": 0.0143, "step": 1570 }, { "epoch": 9.943037974683545, "grad_norm": 2785.677490234375, "learning_rate": 3.378378378378379e-07, "loss": 0.0134, "step": 1571 }, { "epoch": 9.949367088607595, "grad_norm": 4169.0908203125, "learning_rate": 3.040540540540541e-07, "loss": 0.0203, "step": 1572 }, { "epoch": 9.955696202531646, "grad_norm": 2966.724365234375, "learning_rate": 2.702702702702703e-07, "loss": 0.0149, "step": 1573 }, { "epoch": 9.962025316455696, "grad_norm": 3966.356201171875, "learning_rate": 2.364864864864865e-07, "loss": 0.0168, "step": 1574 }, { "epoch": 9.968354430379748, "grad_norm": 5572.5703125, "learning_rate": 2.0270270270270273e-07, "loss": 0.0172, "step": 1575 }, { "epoch": 9.974683544303797, "grad_norm": 4076.649169921875, "learning_rate": 1.6891891891891894e-07, "loss": 0.0134, "step": 1576 }, { "epoch": 9.981012658227849, "grad_norm": 5989.73095703125, "learning_rate": 1.3513513513513515e-07, "loss": 0.0199, "step": 1577 }, { "epoch": 9.987341772151899, "grad_norm": 3346.826904296875, "learning_rate": 1.0135135135135137e-07, "loss": 0.0156, "step": 1578 }, { "epoch": 9.99367088607595, "grad_norm": 2837.311279296875, "learning_rate": 6.756756756756757e-08, "loss": 0.0144, "step": 1579 }, { "epoch": 10.0, "grad_norm": 3395.75, "learning_rate": 3.3783783783783786e-08, "loss": 0.0132, "step": 1580 }, { "epoch": 10.0, "eval_f1_macro": 0.768472164028105, "eval_f1_micro": 0.8760484622553588, "eval_loss": 0.03074106015264988, "eval_precision": 0.9021113243761996, "eval_recall": 0.8514492753623188, "eval_runtime": 1.1659, "eval_samples_per_second": 361.08, "eval_steps_per_second": 15.438, "step": 1580 } ], "logging_steps": 1, "max_steps": 1580, "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": 9952516417597440.0, "train_batch_size": 24, "trial_name": null, "trial_params": null }