cysecbert-ttp-bert-50per_ood_data / trainer_state.json
CaffeineThief's picture
Upload source code
3440502 verified
{
"best_global_step": 1152,
"best_metric": 0.8085106382978723,
"best_model_checkpoint": "./cysecbert-ttp-bert-50per_ood_data/checkpoint-1152",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 1280,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0078125,
"grad_norm": 55668.671875,
"learning_rate": 0.0,
"loss": 0.6876,
"step": 1
},
{
"epoch": 0.015625,
"grad_norm": 54305.38671875,
"learning_rate": 5.000000000000001e-07,
"loss": 0.6896,
"step": 2
},
{
"epoch": 0.0234375,
"grad_norm": 52905.43359375,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.684,
"step": 3
},
{
"epoch": 0.03125,
"grad_norm": 45532.64453125,
"learning_rate": 1.5e-06,
"loss": 0.6859,
"step": 4
},
{
"epoch": 0.0390625,
"grad_norm": 52187.11328125,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.6884,
"step": 5
},
{
"epoch": 0.046875,
"grad_norm": 58894.85546875,
"learning_rate": 2.5e-06,
"loss": 0.6792,
"step": 6
},
{
"epoch": 0.0546875,
"grad_norm": 51014.00390625,
"learning_rate": 3e-06,
"loss": 0.6805,
"step": 7
},
{
"epoch": 0.0625,
"grad_norm": 45628.12890625,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.6767,
"step": 8
},
{
"epoch": 0.0703125,
"grad_norm": 54149.43359375,
"learning_rate": 4.000000000000001e-06,
"loss": 0.6735,
"step": 9
},
{
"epoch": 0.078125,
"grad_norm": 44958.18359375,
"learning_rate": 4.5e-06,
"loss": 0.6711,
"step": 10
},
{
"epoch": 0.0859375,
"grad_norm": 45974.5234375,
"learning_rate": 5e-06,
"loss": 0.6686,
"step": 11
},
{
"epoch": 0.09375,
"grad_norm": 44439.0703125,
"learning_rate": 5.500000000000001e-06,
"loss": 0.6612,
"step": 12
},
{
"epoch": 0.1015625,
"grad_norm": 45351.546875,
"learning_rate": 6e-06,
"loss": 0.654,
"step": 13
},
{
"epoch": 0.109375,
"grad_norm": 47393.2109375,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.6512,
"step": 14
},
{
"epoch": 0.1171875,
"grad_norm": 49049.2265625,
"learning_rate": 7.000000000000001e-06,
"loss": 0.6433,
"step": 15
},
{
"epoch": 0.125,
"grad_norm": 48351.69921875,
"learning_rate": 7.5e-06,
"loss": 0.64,
"step": 16
},
{
"epoch": 0.1328125,
"grad_norm": 47270.05859375,
"learning_rate": 8.000000000000001e-06,
"loss": 0.6345,
"step": 17
},
{
"epoch": 0.140625,
"grad_norm": 50813.23046875,
"learning_rate": 8.500000000000002e-06,
"loss": 0.6302,
"step": 18
},
{
"epoch": 0.1484375,
"grad_norm": 56025.51953125,
"learning_rate": 9e-06,
"loss": 0.6189,
"step": 19
},
{
"epoch": 0.15625,
"grad_norm": 56020.828125,
"learning_rate": 9.5e-06,
"loss": 0.6079,
"step": 20
},
{
"epoch": 0.1640625,
"grad_norm": 48963.8125,
"learning_rate": 1e-05,
"loss": 0.6007,
"step": 21
},
{
"epoch": 0.171875,
"grad_norm": 52089.5703125,
"learning_rate": 1.05e-05,
"loss": 0.5901,
"step": 22
},
{
"epoch": 0.1796875,
"grad_norm": 52101.33203125,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.5818,
"step": 23
},
{
"epoch": 0.1875,
"grad_norm": 58329.92578125,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.5737,
"step": 24
},
{
"epoch": 0.1953125,
"grad_norm": 49914.12109375,
"learning_rate": 1.2e-05,
"loss": 0.5584,
"step": 25
},
{
"epoch": 0.203125,
"grad_norm": 49887.83984375,
"learning_rate": 1.25e-05,
"loss": 0.5501,
"step": 26
},
{
"epoch": 0.2109375,
"grad_norm": 49875.3359375,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.5374,
"step": 27
},
{
"epoch": 0.21875,
"grad_norm": 49134.87890625,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.5312,
"step": 28
},
{
"epoch": 0.2265625,
"grad_norm": 46689.9921875,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.5167,
"step": 29
},
{
"epoch": 0.234375,
"grad_norm": 44872.390625,
"learning_rate": 1.45e-05,
"loss": 0.5132,
"step": 30
},
{
"epoch": 0.2421875,
"grad_norm": 46215.8046875,
"learning_rate": 1.5e-05,
"loss": 0.5,
"step": 31
},
{
"epoch": 0.25,
"grad_norm": 46433.52734375,
"learning_rate": 1.55e-05,
"loss": 0.4946,
"step": 32
},
{
"epoch": 0.2578125,
"grad_norm": 45792.24609375,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.484,
"step": 33
},
{
"epoch": 0.265625,
"grad_norm": 43506.98046875,
"learning_rate": 1.65e-05,
"loss": 0.4758,
"step": 34
},
{
"epoch": 0.2734375,
"grad_norm": 44020.75390625,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.4648,
"step": 35
},
{
"epoch": 0.28125,
"grad_norm": 43306.37109375,
"learning_rate": 1.75e-05,
"loss": 0.4603,
"step": 36
},
{
"epoch": 0.2890625,
"grad_norm": 42601.17578125,
"learning_rate": 1.8e-05,
"loss": 0.4503,
"step": 37
},
{
"epoch": 0.296875,
"grad_norm": 42370.3359375,
"learning_rate": 1.85e-05,
"loss": 0.4413,
"step": 38
},
{
"epoch": 0.3046875,
"grad_norm": 41585.7421875,
"learning_rate": 1.9e-05,
"loss": 0.4326,
"step": 39
},
{
"epoch": 0.3125,
"grad_norm": 40901.296875,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.4251,
"step": 40
},
{
"epoch": 0.3203125,
"grad_norm": 40876.171875,
"learning_rate": 2e-05,
"loss": 0.4198,
"step": 41
},
{
"epoch": 0.328125,
"grad_norm": 40226.203125,
"learning_rate": 2.05e-05,
"loss": 0.4139,
"step": 42
},
{
"epoch": 0.3359375,
"grad_norm": 39622.68359375,
"learning_rate": 2.1e-05,
"loss": 0.4058,
"step": 43
},
{
"epoch": 0.34375,
"grad_norm": 39098.74609375,
"learning_rate": 2.15e-05,
"loss": 0.402,
"step": 44
},
{
"epoch": 0.3515625,
"grad_norm": 38880.91015625,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.3905,
"step": 45
},
{
"epoch": 0.359375,
"grad_norm": 37930.79296875,
"learning_rate": 2.25e-05,
"loss": 0.3845,
"step": 46
},
{
"epoch": 0.3671875,
"grad_norm": 37853.7578125,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.3757,
"step": 47
},
{
"epoch": 0.375,
"grad_norm": 37796.65234375,
"learning_rate": 2.35e-05,
"loss": 0.3709,
"step": 48
},
{
"epoch": 0.3828125,
"grad_norm": 37163.0390625,
"learning_rate": 2.4e-05,
"loss": 0.3649,
"step": 49
},
{
"epoch": 0.390625,
"grad_norm": 37407.69921875,
"learning_rate": 2.45e-05,
"loss": 0.3577,
"step": 50
},
{
"epoch": 0.3984375,
"grad_norm": 36178.72265625,
"learning_rate": 2.5e-05,
"loss": 0.3518,
"step": 51
},
{
"epoch": 0.40625,
"grad_norm": 36030.1328125,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.3456,
"step": 52
},
{
"epoch": 0.4140625,
"grad_norm": 35844.57421875,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.3379,
"step": 53
},
{
"epoch": 0.421875,
"grad_norm": 35432.890625,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.3304,
"step": 54
},
{
"epoch": 0.4296875,
"grad_norm": 35154.703125,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.3218,
"step": 55
},
{
"epoch": 0.4375,
"grad_norm": 33791.19921875,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.322,
"step": 56
},
{
"epoch": 0.4453125,
"grad_norm": 34268.578125,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.3111,
"step": 57
},
{
"epoch": 0.453125,
"grad_norm": 33365.875,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.3082,
"step": 58
},
{
"epoch": 0.4609375,
"grad_norm": 33085.83984375,
"learning_rate": 2.9e-05,
"loss": 0.294,
"step": 59
},
{
"epoch": 0.46875,
"grad_norm": 32478.9140625,
"learning_rate": 2.95e-05,
"loss": 0.2946,
"step": 60
},
{
"epoch": 0.4765625,
"grad_norm": 32312.76953125,
"learning_rate": 3e-05,
"loss": 0.286,
"step": 61
},
{
"epoch": 0.484375,
"grad_norm": 32114.9140625,
"learning_rate": 3.05e-05,
"loss": 0.2761,
"step": 62
},
{
"epoch": 0.4921875,
"grad_norm": 31435.890625,
"learning_rate": 3.1e-05,
"loss": 0.2679,
"step": 63
},
{
"epoch": 0.5,
"grad_norm": 30849.7734375,
"learning_rate": 3.15e-05,
"loss": 0.2646,
"step": 64
},
{
"epoch": 0.5078125,
"grad_norm": 30095.158203125,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.2594,
"step": 65
},
{
"epoch": 0.515625,
"grad_norm": 27830.8046875,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.274,
"step": 66
},
{
"epoch": 0.5234375,
"grad_norm": 29145.755859375,
"learning_rate": 3.3e-05,
"loss": 0.2477,
"step": 67
},
{
"epoch": 0.53125,
"grad_norm": 28059.30859375,
"learning_rate": 3.35e-05,
"loss": 0.2466,
"step": 68
},
{
"epoch": 0.5390625,
"grad_norm": 28038.697265625,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.2422,
"step": 69
},
{
"epoch": 0.546875,
"grad_norm": 27342.951171875,
"learning_rate": 3.45e-05,
"loss": 0.2307,
"step": 70
},
{
"epoch": 0.5546875,
"grad_norm": 26588.15625,
"learning_rate": 3.5e-05,
"loss": 0.2268,
"step": 71
},
{
"epoch": 0.5625,
"grad_norm": 25811.8203125,
"learning_rate": 3.55e-05,
"loss": 0.2215,
"step": 72
},
{
"epoch": 0.5703125,
"grad_norm": 25670.798828125,
"learning_rate": 3.6e-05,
"loss": 0.2122,
"step": 73
},
{
"epoch": 0.578125,
"grad_norm": 24893.369140625,
"learning_rate": 3.65e-05,
"loss": 0.2076,
"step": 74
},
{
"epoch": 0.5859375,
"grad_norm": 24229.35546875,
"learning_rate": 3.7e-05,
"loss": 0.2082,
"step": 75
},
{
"epoch": 0.59375,
"grad_norm": 23527.16015625,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.2005,
"step": 76
},
{
"epoch": 0.6015625,
"grad_norm": 22385.921875,
"learning_rate": 3.8e-05,
"loss": 0.2,
"step": 77
},
{
"epoch": 0.609375,
"grad_norm": 23028.015625,
"learning_rate": 3.85e-05,
"loss": 0.1903,
"step": 78
},
{
"epoch": 0.6171875,
"grad_norm": 21341.5625,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.1834,
"step": 79
},
{
"epoch": 0.625,
"grad_norm": 20680.935546875,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.1828,
"step": 80
},
{
"epoch": 0.6328125,
"grad_norm": 17881.48828125,
"learning_rate": 4e-05,
"loss": 0.1981,
"step": 81
},
{
"epoch": 0.640625,
"grad_norm": 19924.009765625,
"learning_rate": 4.05e-05,
"loss": 0.1688,
"step": 82
},
{
"epoch": 0.6484375,
"grad_norm": 18512.25,
"learning_rate": 4.1e-05,
"loss": 0.1707,
"step": 83
},
{
"epoch": 0.65625,
"grad_norm": 17983.96484375,
"learning_rate": 4.15e-05,
"loss": 0.1699,
"step": 84
},
{
"epoch": 0.6640625,
"grad_norm": 17348.62109375,
"learning_rate": 4.2e-05,
"loss": 0.1699,
"step": 85
},
{
"epoch": 0.671875,
"grad_norm": 16668.841796875,
"learning_rate": 4.25e-05,
"loss": 0.1667,
"step": 86
},
{
"epoch": 0.6796875,
"grad_norm": 16411.626953125,
"learning_rate": 4.3e-05,
"loss": 0.1587,
"step": 87
},
{
"epoch": 0.6875,
"grad_norm": 15639.9931640625,
"learning_rate": 4.35e-05,
"loss": 0.1623,
"step": 88
},
{
"epoch": 0.6953125,
"grad_norm": 15759.373046875,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.1479,
"step": 89
},
{
"epoch": 0.703125,
"grad_norm": 15354.939453125,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.1433,
"step": 90
},
{
"epoch": 0.7109375,
"grad_norm": 14111.619140625,
"learning_rate": 4.5e-05,
"loss": 0.1482,
"step": 91
},
{
"epoch": 0.71875,
"grad_norm": 13127.49609375,
"learning_rate": 4.55e-05,
"loss": 0.1465,
"step": 92
},
{
"epoch": 0.7265625,
"grad_norm": 13378.869140625,
"learning_rate": 4.600000000000001e-05,
"loss": 0.1342,
"step": 93
},
{
"epoch": 0.734375,
"grad_norm": 13125.0732421875,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.1311,
"step": 94
},
{
"epoch": 0.7421875,
"grad_norm": 12960.5986328125,
"learning_rate": 4.7e-05,
"loss": 0.1314,
"step": 95
},
{
"epoch": 0.75,
"grad_norm": 12390.8349609375,
"learning_rate": 4.75e-05,
"loss": 0.1315,
"step": 96
},
{
"epoch": 0.7578125,
"grad_norm": 11555.1982421875,
"learning_rate": 4.8e-05,
"loss": 0.1279,
"step": 97
},
{
"epoch": 0.765625,
"grad_norm": 10925.654296875,
"learning_rate": 4.85e-05,
"loss": 0.1286,
"step": 98
},
{
"epoch": 0.7734375,
"grad_norm": 10972.08203125,
"learning_rate": 4.9e-05,
"loss": 0.1254,
"step": 99
},
{
"epoch": 0.78125,
"grad_norm": 10296.7119140625,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.1252,
"step": 100
},
{
"epoch": 0.7890625,
"grad_norm": 10050.1923828125,
"learning_rate": 5e-05,
"loss": 0.1182,
"step": 101
},
{
"epoch": 0.796875,
"grad_norm": 9236.580078125,
"learning_rate": 4.9957627118644066e-05,
"loss": 0.1107,
"step": 102
},
{
"epoch": 0.8046875,
"grad_norm": 10439.6806640625,
"learning_rate": 4.991525423728814e-05,
"loss": 0.1198,
"step": 103
},
{
"epoch": 0.8125,
"grad_norm": 8587.60546875,
"learning_rate": 4.9872881355932206e-05,
"loss": 0.1164,
"step": 104
},
{
"epoch": 0.8203125,
"grad_norm": 8959.42578125,
"learning_rate": 4.9830508474576276e-05,
"loss": 0.1073,
"step": 105
},
{
"epoch": 0.828125,
"grad_norm": 9593.640625,
"learning_rate": 4.978813559322034e-05,
"loss": 0.1145,
"step": 106
},
{
"epoch": 0.8359375,
"grad_norm": 11947.474609375,
"learning_rate": 4.974576271186441e-05,
"loss": 0.137,
"step": 107
},
{
"epoch": 0.84375,
"grad_norm": 8182.53515625,
"learning_rate": 4.970338983050848e-05,
"loss": 0.1109,
"step": 108
},
{
"epoch": 0.8515625,
"grad_norm": 8539.568359375,
"learning_rate": 4.966101694915254e-05,
"loss": 0.1235,
"step": 109
},
{
"epoch": 0.859375,
"grad_norm": 8396.740234375,
"learning_rate": 4.961864406779661e-05,
"loss": 0.1198,
"step": 110
},
{
"epoch": 0.8671875,
"grad_norm": 7636.1650390625,
"learning_rate": 4.957627118644068e-05,
"loss": 0.1181,
"step": 111
},
{
"epoch": 0.875,
"grad_norm": 7661.5224609375,
"learning_rate": 4.9533898305084745e-05,
"loss": 0.1054,
"step": 112
},
{
"epoch": 0.8828125,
"grad_norm": 8134.7294921875,
"learning_rate": 4.9491525423728815e-05,
"loss": 0.1165,
"step": 113
},
{
"epoch": 0.890625,
"grad_norm": 7441.43701171875,
"learning_rate": 4.9449152542372885e-05,
"loss": 0.1061,
"step": 114
},
{
"epoch": 0.8984375,
"grad_norm": 6899.25537109375,
"learning_rate": 4.940677966101695e-05,
"loss": 0.1032,
"step": 115
},
{
"epoch": 0.90625,
"grad_norm": 7467.376953125,
"learning_rate": 4.936440677966102e-05,
"loss": 0.1172,
"step": 116
},
{
"epoch": 0.9140625,
"grad_norm": 8015.62451171875,
"learning_rate": 4.932203389830509e-05,
"loss": 0.1019,
"step": 117
},
{
"epoch": 0.921875,
"grad_norm": 7589.8828125,
"learning_rate": 4.927966101694915e-05,
"loss": 0.1064,
"step": 118
},
{
"epoch": 0.9296875,
"grad_norm": 9230.873046875,
"learning_rate": 4.923728813559322e-05,
"loss": 0.1231,
"step": 119
},
{
"epoch": 0.9375,
"grad_norm": 8068.7724609375,
"learning_rate": 4.919491525423729e-05,
"loss": 0.1143,
"step": 120
},
{
"epoch": 0.9453125,
"grad_norm": 6723.79443359375,
"learning_rate": 4.915254237288136e-05,
"loss": 0.0977,
"step": 121
},
{
"epoch": 0.953125,
"grad_norm": 8523.982421875,
"learning_rate": 4.9110169491525425e-05,
"loss": 0.1091,
"step": 122
},
{
"epoch": 0.9609375,
"grad_norm": 9381.0009765625,
"learning_rate": 4.9067796610169495e-05,
"loss": 0.1222,
"step": 123
},
{
"epoch": 0.96875,
"grad_norm": 8387.267578125,
"learning_rate": 4.9025423728813565e-05,
"loss": 0.1043,
"step": 124
},
{
"epoch": 0.9765625,
"grad_norm": 7342.51220703125,
"learning_rate": 4.898305084745763e-05,
"loss": 0.1009,
"step": 125
},
{
"epoch": 0.984375,
"grad_norm": 6146.8720703125,
"learning_rate": 4.89406779661017e-05,
"loss": 0.0921,
"step": 126
},
{
"epoch": 0.9921875,
"grad_norm": 8314.63671875,
"learning_rate": 4.889830508474577e-05,
"loss": 0.103,
"step": 127
},
{
"epoch": 1.0,
"grad_norm": 8018.51025390625,
"learning_rate": 4.885593220338983e-05,
"loss": 0.1147,
"step": 128
},
{
"epoch": 1.0,
"eval_f1_macro": 0.0,
"eval_f1_micro": 0.0,
"eval_loss": 0.10611323267221451,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 0.9598,
"eval_samples_per_second": 356.328,
"eval_steps_per_second": 15.628,
"step": 128
},
{
"epoch": 1.0078125,
"grad_norm": 7556.15771484375,
"learning_rate": 4.88135593220339e-05,
"loss": 0.0971,
"step": 129
},
{
"epoch": 1.015625,
"grad_norm": 6538.84716796875,
"learning_rate": 4.877118644067797e-05,
"loss": 0.1145,
"step": 130
},
{
"epoch": 1.0234375,
"grad_norm": 8680.9228515625,
"learning_rate": 4.8728813559322034e-05,
"loss": 0.1163,
"step": 131
},
{
"epoch": 1.03125,
"grad_norm": 7672.6435546875,
"learning_rate": 4.8686440677966104e-05,
"loss": 0.1003,
"step": 132
},
{
"epoch": 1.0390625,
"grad_norm": 7352.6484375,
"learning_rate": 4.8644067796610174e-05,
"loss": 0.1095,
"step": 133
},
{
"epoch": 1.046875,
"grad_norm": 7447.30810546875,
"learning_rate": 4.8601694915254244e-05,
"loss": 0.1134,
"step": 134
},
{
"epoch": 1.0546875,
"grad_norm": 6873.4970703125,
"learning_rate": 4.855932203389831e-05,
"loss": 0.1087,
"step": 135
},
{
"epoch": 1.0625,
"grad_norm": 7183.4052734375,
"learning_rate": 4.851694915254237e-05,
"loss": 0.0987,
"step": 136
},
{
"epoch": 1.0703125,
"grad_norm": 6831.9658203125,
"learning_rate": 4.847457627118645e-05,
"loss": 0.1153,
"step": 137
},
{
"epoch": 1.078125,
"grad_norm": 7811.3916015625,
"learning_rate": 4.843220338983051e-05,
"loss": 0.1135,
"step": 138
},
{
"epoch": 1.0859375,
"grad_norm": 7770.50634765625,
"learning_rate": 4.8389830508474574e-05,
"loss": 0.1024,
"step": 139
},
{
"epoch": 1.09375,
"grad_norm": 7272.15380859375,
"learning_rate": 4.834745762711865e-05,
"loss": 0.1028,
"step": 140
},
{
"epoch": 1.1015625,
"grad_norm": 7142.5166015625,
"learning_rate": 4.8305084745762714e-05,
"loss": 0.0956,
"step": 141
},
{
"epoch": 1.109375,
"grad_norm": 7740.5498046875,
"learning_rate": 4.8262711864406784e-05,
"loss": 0.0877,
"step": 142
},
{
"epoch": 1.1171875,
"grad_norm": 7699.705078125,
"learning_rate": 4.822033898305085e-05,
"loss": 0.1078,
"step": 143
},
{
"epoch": 1.125,
"grad_norm": 7899.3955078125,
"learning_rate": 4.817796610169492e-05,
"loss": 0.1102,
"step": 144
},
{
"epoch": 1.1328125,
"grad_norm": 10785.546875,
"learning_rate": 4.813559322033899e-05,
"loss": 0.1191,
"step": 145
},
{
"epoch": 1.140625,
"grad_norm": 8644.9541015625,
"learning_rate": 4.809322033898305e-05,
"loss": 0.0976,
"step": 146
},
{
"epoch": 1.1484375,
"grad_norm": 6031.7578125,
"learning_rate": 4.805084745762712e-05,
"loss": 0.0952,
"step": 147
},
{
"epoch": 1.15625,
"grad_norm": 7142.24072265625,
"learning_rate": 4.800847457627119e-05,
"loss": 0.1158,
"step": 148
},
{
"epoch": 1.1640625,
"grad_norm": 7586.95263671875,
"learning_rate": 4.796610169491525e-05,
"loss": 0.1114,
"step": 149
},
{
"epoch": 1.171875,
"grad_norm": 7032.32177734375,
"learning_rate": 4.792372881355933e-05,
"loss": 0.1024,
"step": 150
},
{
"epoch": 1.1796875,
"grad_norm": 6257.09228515625,
"learning_rate": 4.788135593220339e-05,
"loss": 0.0985,
"step": 151
},
{
"epoch": 1.1875,
"grad_norm": 7367.0595703125,
"learning_rate": 4.7838983050847456e-05,
"loss": 0.0943,
"step": 152
},
{
"epoch": 1.1953125,
"grad_norm": 6662.88427734375,
"learning_rate": 4.7796610169491526e-05,
"loss": 0.1016,
"step": 153
},
{
"epoch": 1.203125,
"grad_norm": 7876.6220703125,
"learning_rate": 4.7754237288135596e-05,
"loss": 0.1154,
"step": 154
},
{
"epoch": 1.2109375,
"grad_norm": 8781.62890625,
"learning_rate": 4.7711864406779666e-05,
"loss": 0.0999,
"step": 155
},
{
"epoch": 1.21875,
"grad_norm": 7283.0224609375,
"learning_rate": 4.766949152542373e-05,
"loss": 0.1097,
"step": 156
},
{
"epoch": 1.2265625,
"grad_norm": 7731.20263671875,
"learning_rate": 4.76271186440678e-05,
"loss": 0.0972,
"step": 157
},
{
"epoch": 1.234375,
"grad_norm": 6939.77880859375,
"learning_rate": 4.758474576271187e-05,
"loss": 0.1024,
"step": 158
},
{
"epoch": 1.2421875,
"grad_norm": 7066.3779296875,
"learning_rate": 4.754237288135593e-05,
"loss": 0.0943,
"step": 159
},
{
"epoch": 1.25,
"grad_norm": 8837.0771484375,
"learning_rate": 4.75e-05,
"loss": 0.1123,
"step": 160
},
{
"epoch": 1.2578125,
"grad_norm": 6900.9228515625,
"learning_rate": 4.745762711864407e-05,
"loss": 0.1154,
"step": 161
},
{
"epoch": 1.265625,
"grad_norm": 8176.4775390625,
"learning_rate": 4.7415254237288136e-05,
"loss": 0.1197,
"step": 162
},
{
"epoch": 1.2734375,
"grad_norm": 8021.41015625,
"learning_rate": 4.7372881355932206e-05,
"loss": 0.1297,
"step": 163
},
{
"epoch": 1.28125,
"grad_norm": 6915.80029296875,
"learning_rate": 4.7330508474576276e-05,
"loss": 0.1064,
"step": 164
},
{
"epoch": 1.2890625,
"grad_norm": 7858.10107421875,
"learning_rate": 4.728813559322034e-05,
"loss": 0.1077,
"step": 165
},
{
"epoch": 1.296875,
"grad_norm": 7547.07958984375,
"learning_rate": 4.724576271186441e-05,
"loss": 0.1052,
"step": 166
},
{
"epoch": 1.3046875,
"grad_norm": 8203.2607421875,
"learning_rate": 4.720338983050848e-05,
"loss": 0.136,
"step": 167
},
{
"epoch": 1.3125,
"grad_norm": 7025.49853515625,
"learning_rate": 4.716101694915254e-05,
"loss": 0.097,
"step": 168
},
{
"epoch": 1.3203125,
"grad_norm": 7980.921875,
"learning_rate": 4.711864406779661e-05,
"loss": 0.1199,
"step": 169
},
{
"epoch": 1.328125,
"grad_norm": 7913.33935546875,
"learning_rate": 4.707627118644068e-05,
"loss": 0.1177,
"step": 170
},
{
"epoch": 1.3359375,
"grad_norm": 7595.5322265625,
"learning_rate": 4.703389830508475e-05,
"loss": 0.122,
"step": 171
},
{
"epoch": 1.34375,
"grad_norm": 8216.0263671875,
"learning_rate": 4.6991525423728815e-05,
"loss": 0.1145,
"step": 172
},
{
"epoch": 1.3515625,
"grad_norm": 7947.375,
"learning_rate": 4.694915254237288e-05,
"loss": 0.1017,
"step": 173
},
{
"epoch": 1.359375,
"grad_norm": 6599.4501953125,
"learning_rate": 4.6906779661016955e-05,
"loss": 0.0997,
"step": 174
},
{
"epoch": 1.3671875,
"grad_norm": 7404.41552734375,
"learning_rate": 4.686440677966102e-05,
"loss": 0.1178,
"step": 175
},
{
"epoch": 1.375,
"grad_norm": 7860.84814453125,
"learning_rate": 4.682203389830508e-05,
"loss": 0.1125,
"step": 176
},
{
"epoch": 1.3828125,
"grad_norm": 7367.52685546875,
"learning_rate": 4.677966101694916e-05,
"loss": 0.1015,
"step": 177
},
{
"epoch": 1.390625,
"grad_norm": 5907.12939453125,
"learning_rate": 4.673728813559322e-05,
"loss": 0.1062,
"step": 178
},
{
"epoch": 1.3984375,
"grad_norm": 9182.591796875,
"learning_rate": 4.669491525423729e-05,
"loss": 0.1253,
"step": 179
},
{
"epoch": 1.40625,
"grad_norm": 7576.8134765625,
"learning_rate": 4.6652542372881355e-05,
"loss": 0.1082,
"step": 180
},
{
"epoch": 1.4140625,
"grad_norm": 6772.412109375,
"learning_rate": 4.6610169491525425e-05,
"loss": 0.0978,
"step": 181
},
{
"epoch": 1.421875,
"grad_norm": 7411.759765625,
"learning_rate": 4.6567796610169495e-05,
"loss": 0.1135,
"step": 182
},
{
"epoch": 1.4296875,
"grad_norm": 6891.1611328125,
"learning_rate": 4.652542372881356e-05,
"loss": 0.1067,
"step": 183
},
{
"epoch": 1.4375,
"grad_norm": 7630.11376953125,
"learning_rate": 4.6483050847457635e-05,
"loss": 0.1307,
"step": 184
},
{
"epoch": 1.4453125,
"grad_norm": 7443.3427734375,
"learning_rate": 4.64406779661017e-05,
"loss": 0.1099,
"step": 185
},
{
"epoch": 1.453125,
"grad_norm": 7893.91748046875,
"learning_rate": 4.639830508474576e-05,
"loss": 0.0995,
"step": 186
},
{
"epoch": 1.4609375,
"grad_norm": 7320.59765625,
"learning_rate": 4.635593220338984e-05,
"loss": 0.1107,
"step": 187
},
{
"epoch": 1.46875,
"grad_norm": 9040.21484375,
"learning_rate": 4.63135593220339e-05,
"loss": 0.0982,
"step": 188
},
{
"epoch": 1.4765625,
"grad_norm": 7455.58251953125,
"learning_rate": 4.6271186440677964e-05,
"loss": 0.1078,
"step": 189
},
{
"epoch": 1.484375,
"grad_norm": 6298.66455078125,
"learning_rate": 4.6228813559322034e-05,
"loss": 0.0938,
"step": 190
},
{
"epoch": 1.4921875,
"grad_norm": 5535.54833984375,
"learning_rate": 4.6186440677966104e-05,
"loss": 0.0904,
"step": 191
},
{
"epoch": 1.5,
"grad_norm": 8060.6328125,
"learning_rate": 4.6144067796610174e-05,
"loss": 0.1021,
"step": 192
},
{
"epoch": 1.5078125,
"grad_norm": 8085.22998046875,
"learning_rate": 4.610169491525424e-05,
"loss": 0.1031,
"step": 193
},
{
"epoch": 1.515625,
"grad_norm": 8397.8251953125,
"learning_rate": 4.605932203389831e-05,
"loss": 0.1165,
"step": 194
},
{
"epoch": 1.5234375,
"grad_norm": 8594.7177734375,
"learning_rate": 4.601694915254238e-05,
"loss": 0.1081,
"step": 195
},
{
"epoch": 1.53125,
"grad_norm": 6699.01025390625,
"learning_rate": 4.597457627118644e-05,
"loss": 0.1174,
"step": 196
},
{
"epoch": 1.5390625,
"grad_norm": 8866.4560546875,
"learning_rate": 4.593220338983051e-05,
"loss": 0.1159,
"step": 197
},
{
"epoch": 1.546875,
"grad_norm": 7634.744140625,
"learning_rate": 4.588983050847458e-05,
"loss": 0.1014,
"step": 198
},
{
"epoch": 1.5546875,
"grad_norm": 7319.58203125,
"learning_rate": 4.5847457627118644e-05,
"loss": 0.0935,
"step": 199
},
{
"epoch": 1.5625,
"grad_norm": 6111.15771484375,
"learning_rate": 4.5805084745762714e-05,
"loss": 0.1101,
"step": 200
},
{
"epoch": 1.5703125,
"grad_norm": 8693.712890625,
"learning_rate": 4.5762711864406784e-05,
"loss": 0.1131,
"step": 201
},
{
"epoch": 1.578125,
"grad_norm": 7222.01904296875,
"learning_rate": 4.572033898305085e-05,
"loss": 0.1084,
"step": 202
},
{
"epoch": 1.5859375,
"grad_norm": 8898.3916015625,
"learning_rate": 4.567796610169492e-05,
"loss": 0.1007,
"step": 203
},
{
"epoch": 1.59375,
"grad_norm": 9154.87890625,
"learning_rate": 4.563559322033899e-05,
"loss": 0.1221,
"step": 204
},
{
"epoch": 1.6015625,
"grad_norm": 6531.8525390625,
"learning_rate": 4.559322033898305e-05,
"loss": 0.101,
"step": 205
},
{
"epoch": 1.609375,
"grad_norm": 8065.54248046875,
"learning_rate": 4.555084745762712e-05,
"loss": 0.1041,
"step": 206
},
{
"epoch": 1.6171875,
"grad_norm": 8549.2294921875,
"learning_rate": 4.550847457627119e-05,
"loss": 0.1153,
"step": 207
},
{
"epoch": 1.625,
"grad_norm": 7914.0400390625,
"learning_rate": 4.546610169491526e-05,
"loss": 0.1063,
"step": 208
},
{
"epoch": 1.6328125,
"grad_norm": 7213.44580078125,
"learning_rate": 4.542372881355932e-05,
"loss": 0.1122,
"step": 209
},
{
"epoch": 1.640625,
"grad_norm": 7495.11767578125,
"learning_rate": 4.5381355932203387e-05,
"loss": 0.0927,
"step": 210
},
{
"epoch": 1.6484375,
"grad_norm": 8375.0556640625,
"learning_rate": 4.533898305084746e-05,
"loss": 0.112,
"step": 211
},
{
"epoch": 1.65625,
"grad_norm": 7878.17236328125,
"learning_rate": 4.5296610169491527e-05,
"loss": 0.1052,
"step": 212
},
{
"epoch": 1.6640625,
"grad_norm": 8551.5546875,
"learning_rate": 4.5254237288135596e-05,
"loss": 0.1029,
"step": 213
},
{
"epoch": 1.671875,
"grad_norm": 9792.3212890625,
"learning_rate": 4.5211864406779666e-05,
"loss": 0.1064,
"step": 214
},
{
"epoch": 1.6796875,
"grad_norm": 9555.201171875,
"learning_rate": 4.516949152542373e-05,
"loss": 0.1186,
"step": 215
},
{
"epoch": 1.6875,
"grad_norm": 7213.63037109375,
"learning_rate": 4.51271186440678e-05,
"loss": 0.1096,
"step": 216
},
{
"epoch": 1.6953125,
"grad_norm": 7901.6787109375,
"learning_rate": 4.508474576271187e-05,
"loss": 0.1092,
"step": 217
},
{
"epoch": 1.703125,
"grad_norm": 9925.9755859375,
"learning_rate": 4.504237288135593e-05,
"loss": 0.1258,
"step": 218
},
{
"epoch": 1.7109375,
"grad_norm": 7219.6376953125,
"learning_rate": 4.5e-05,
"loss": 0.1069,
"step": 219
},
{
"epoch": 1.71875,
"grad_norm": 7480.115234375,
"learning_rate": 4.4957627118644066e-05,
"loss": 0.0978,
"step": 220
},
{
"epoch": 1.7265625,
"grad_norm": 7749.333984375,
"learning_rate": 4.491525423728814e-05,
"loss": 0.1184,
"step": 221
},
{
"epoch": 1.734375,
"grad_norm": 6285.53466796875,
"learning_rate": 4.4872881355932206e-05,
"loss": 0.1041,
"step": 222
},
{
"epoch": 1.7421875,
"grad_norm": 6434.140625,
"learning_rate": 4.483050847457627e-05,
"loss": 0.1016,
"step": 223
},
{
"epoch": 1.75,
"grad_norm": 8411.21484375,
"learning_rate": 4.4788135593220346e-05,
"loss": 0.0922,
"step": 224
},
{
"epoch": 1.7578125,
"grad_norm": 7476.6630859375,
"learning_rate": 4.474576271186441e-05,
"loss": 0.1035,
"step": 225
},
{
"epoch": 1.765625,
"grad_norm": 9043.3330078125,
"learning_rate": 4.470338983050847e-05,
"loss": 0.0916,
"step": 226
},
{
"epoch": 1.7734375,
"grad_norm": 7642.7080078125,
"learning_rate": 4.466101694915254e-05,
"loss": 0.1135,
"step": 227
},
{
"epoch": 1.78125,
"grad_norm": 8682.966796875,
"learning_rate": 4.461864406779661e-05,
"loss": 0.1023,
"step": 228
},
{
"epoch": 1.7890625,
"grad_norm": 21971.939453125,
"learning_rate": 4.457627118644068e-05,
"loss": 0.1405,
"step": 229
},
{
"epoch": 1.796875,
"grad_norm": 8538.4248046875,
"learning_rate": 4.4533898305084746e-05,
"loss": 0.1047,
"step": 230
},
{
"epoch": 1.8046875,
"grad_norm": 9930.2021484375,
"learning_rate": 4.4491525423728816e-05,
"loss": 0.0984,
"step": 231
},
{
"epoch": 1.8125,
"grad_norm": 14569.96484375,
"learning_rate": 4.4449152542372886e-05,
"loss": 0.1089,
"step": 232
},
{
"epoch": 1.8203125,
"grad_norm": 6663.77197265625,
"learning_rate": 4.440677966101695e-05,
"loss": 0.1028,
"step": 233
},
{
"epoch": 1.828125,
"grad_norm": 7405.6904296875,
"learning_rate": 4.436440677966102e-05,
"loss": 0.1165,
"step": 234
},
{
"epoch": 1.8359375,
"grad_norm": 7965.923828125,
"learning_rate": 4.432203389830509e-05,
"loss": 0.0924,
"step": 235
},
{
"epoch": 1.84375,
"grad_norm": 7765.15869140625,
"learning_rate": 4.427966101694915e-05,
"loss": 0.0969,
"step": 236
},
{
"epoch": 1.8515625,
"grad_norm": 9510.52734375,
"learning_rate": 4.423728813559322e-05,
"loss": 0.1038,
"step": 237
},
{
"epoch": 1.859375,
"grad_norm": 6981.47314453125,
"learning_rate": 4.419491525423729e-05,
"loss": 0.0981,
"step": 238
},
{
"epoch": 1.8671875,
"grad_norm": 8804.7470703125,
"learning_rate": 4.4152542372881355e-05,
"loss": 0.112,
"step": 239
},
{
"epoch": 1.875,
"grad_norm": 11450.9814453125,
"learning_rate": 4.4110169491525425e-05,
"loss": 0.0996,
"step": 240
},
{
"epoch": 1.8828125,
"grad_norm": 12555.01953125,
"learning_rate": 4.4067796610169495e-05,
"loss": 0.0974,
"step": 241
},
{
"epoch": 1.890625,
"grad_norm": 6727.42578125,
"learning_rate": 4.4025423728813565e-05,
"loss": 0.1007,
"step": 242
},
{
"epoch": 1.8984375,
"grad_norm": 16772.796875,
"learning_rate": 4.398305084745763e-05,
"loss": 0.0985,
"step": 243
},
{
"epoch": 1.90625,
"grad_norm": 9014.6767578125,
"learning_rate": 4.39406779661017e-05,
"loss": 0.1067,
"step": 244
},
{
"epoch": 1.9140625,
"grad_norm": 7058.94140625,
"learning_rate": 4.389830508474577e-05,
"loss": 0.1026,
"step": 245
},
{
"epoch": 1.921875,
"grad_norm": 8792.0244140625,
"learning_rate": 4.385593220338983e-05,
"loss": 0.1026,
"step": 246
},
{
"epoch": 1.9296875,
"grad_norm": 9302.0390625,
"learning_rate": 4.38135593220339e-05,
"loss": 0.1073,
"step": 247
},
{
"epoch": 1.9375,
"grad_norm": 7998.19091796875,
"learning_rate": 4.377118644067797e-05,
"loss": 0.0969,
"step": 248
},
{
"epoch": 1.9453125,
"grad_norm": 8917.740234375,
"learning_rate": 4.3728813559322035e-05,
"loss": 0.1219,
"step": 249
},
{
"epoch": 1.953125,
"grad_norm": 7154.1865234375,
"learning_rate": 4.3686440677966105e-05,
"loss": 0.1114,
"step": 250
},
{
"epoch": 1.9609375,
"grad_norm": 7094.59326171875,
"learning_rate": 4.3644067796610175e-05,
"loss": 0.1029,
"step": 251
},
{
"epoch": 1.96875,
"grad_norm": 8026.59619140625,
"learning_rate": 4.360169491525424e-05,
"loss": 0.0851,
"step": 252
},
{
"epoch": 1.9765625,
"grad_norm": 8406.6083984375,
"learning_rate": 4.355932203389831e-05,
"loss": 0.0929,
"step": 253
},
{
"epoch": 1.984375,
"grad_norm": 8600.908203125,
"learning_rate": 4.351694915254238e-05,
"loss": 0.0981,
"step": 254
},
{
"epoch": 1.9921875,
"grad_norm": 8042.751953125,
"learning_rate": 4.347457627118644e-05,
"loss": 0.095,
"step": 255
},
{
"epoch": 2.0,
"grad_norm": 12173.9345703125,
"learning_rate": 4.343220338983051e-05,
"loss": 0.1175,
"step": 256
},
{
"epoch": 2.0,
"eval_f1_macro": 0.025867606737171957,
"eval_f1_micro": 0.29292929292929293,
"eval_loss": 0.0997692123055458,
"eval_precision": 0.4943181818181818,
"eval_recall": 0.20813397129186603,
"eval_runtime": 0.9478,
"eval_samples_per_second": 360.832,
"eval_steps_per_second": 15.826,
"step": 256
},
{
"epoch": 2.0078125,
"grad_norm": 9149.880859375,
"learning_rate": 4.3389830508474574e-05,
"loss": 0.1074,
"step": 257
},
{
"epoch": 2.015625,
"grad_norm": 8263.9775390625,
"learning_rate": 4.334745762711865e-05,
"loss": 0.097,
"step": 258
},
{
"epoch": 2.0234375,
"grad_norm": 6848.962890625,
"learning_rate": 4.3305084745762714e-05,
"loss": 0.0959,
"step": 259
},
{
"epoch": 2.03125,
"grad_norm": 8741.2001953125,
"learning_rate": 4.326271186440678e-05,
"loss": 0.1001,
"step": 260
},
{
"epoch": 2.0390625,
"grad_norm": 6768.111328125,
"learning_rate": 4.3220338983050854e-05,
"loss": 0.0993,
"step": 261
},
{
"epoch": 2.046875,
"grad_norm": 9527.1162109375,
"learning_rate": 4.317796610169492e-05,
"loss": 0.0952,
"step": 262
},
{
"epoch": 2.0546875,
"grad_norm": 7461.68408203125,
"learning_rate": 4.313559322033899e-05,
"loss": 0.0951,
"step": 263
},
{
"epoch": 2.0625,
"grad_norm": 8125.28076171875,
"learning_rate": 4.309322033898305e-05,
"loss": 0.1097,
"step": 264
},
{
"epoch": 2.0703125,
"grad_norm": 8084.8818359375,
"learning_rate": 4.305084745762712e-05,
"loss": 0.0922,
"step": 265
},
{
"epoch": 2.078125,
"grad_norm": 7175.9970703125,
"learning_rate": 4.300847457627119e-05,
"loss": 0.1039,
"step": 266
},
{
"epoch": 2.0859375,
"grad_norm": 7640.8798828125,
"learning_rate": 4.2966101694915254e-05,
"loss": 0.091,
"step": 267
},
{
"epoch": 2.09375,
"grad_norm": 7850.1044921875,
"learning_rate": 4.2923728813559324e-05,
"loss": 0.1115,
"step": 268
},
{
"epoch": 2.1015625,
"grad_norm": 8264.763671875,
"learning_rate": 4.2881355932203394e-05,
"loss": 0.09,
"step": 269
},
{
"epoch": 2.109375,
"grad_norm": 7209.39013671875,
"learning_rate": 4.283898305084746e-05,
"loss": 0.1052,
"step": 270
},
{
"epoch": 2.1171875,
"grad_norm": 7244.05078125,
"learning_rate": 4.279661016949153e-05,
"loss": 0.1086,
"step": 271
},
{
"epoch": 2.125,
"grad_norm": 6976.22412109375,
"learning_rate": 4.27542372881356e-05,
"loss": 0.1013,
"step": 272
},
{
"epoch": 2.1328125,
"grad_norm": 7543.41796875,
"learning_rate": 4.271186440677966e-05,
"loss": 0.1071,
"step": 273
},
{
"epoch": 2.140625,
"grad_norm": 7732.81494140625,
"learning_rate": 4.266949152542373e-05,
"loss": 0.0836,
"step": 274
},
{
"epoch": 2.1484375,
"grad_norm": 8138.7109375,
"learning_rate": 4.26271186440678e-05,
"loss": 0.093,
"step": 275
},
{
"epoch": 2.15625,
"grad_norm": 9491.056640625,
"learning_rate": 4.258474576271186e-05,
"loss": 0.1014,
"step": 276
},
{
"epoch": 2.1640625,
"grad_norm": 8288.7080078125,
"learning_rate": 4.254237288135593e-05,
"loss": 0.0911,
"step": 277
},
{
"epoch": 2.171875,
"grad_norm": 7999.8212890625,
"learning_rate": 4.25e-05,
"loss": 0.1056,
"step": 278
},
{
"epoch": 2.1796875,
"grad_norm": 10685.384765625,
"learning_rate": 4.245762711864407e-05,
"loss": 0.0969,
"step": 279
},
{
"epoch": 2.1875,
"grad_norm": 9217.802734375,
"learning_rate": 4.2415254237288136e-05,
"loss": 0.0961,
"step": 280
},
{
"epoch": 2.1953125,
"grad_norm": 7299.93359375,
"learning_rate": 4.2372881355932206e-05,
"loss": 0.0895,
"step": 281
},
{
"epoch": 2.203125,
"grad_norm": 8702.8896484375,
"learning_rate": 4.2330508474576276e-05,
"loss": 0.0908,
"step": 282
},
{
"epoch": 2.2109375,
"grad_norm": 7028.40576171875,
"learning_rate": 4.228813559322034e-05,
"loss": 0.1005,
"step": 283
},
{
"epoch": 2.21875,
"grad_norm": 6924.568359375,
"learning_rate": 4.224576271186441e-05,
"loss": 0.0902,
"step": 284
},
{
"epoch": 2.2265625,
"grad_norm": 8265.728515625,
"learning_rate": 4.220338983050848e-05,
"loss": 0.1062,
"step": 285
},
{
"epoch": 2.234375,
"grad_norm": 7332.0751953125,
"learning_rate": 4.216101694915254e-05,
"loss": 0.0862,
"step": 286
},
{
"epoch": 2.2421875,
"grad_norm": 9956.595703125,
"learning_rate": 4.211864406779661e-05,
"loss": 0.0869,
"step": 287
},
{
"epoch": 2.25,
"grad_norm": 8592.4658203125,
"learning_rate": 4.207627118644068e-05,
"loss": 0.105,
"step": 288
},
{
"epoch": 2.2578125,
"grad_norm": 5796.36572265625,
"learning_rate": 4.2033898305084746e-05,
"loss": 0.0886,
"step": 289
},
{
"epoch": 2.265625,
"grad_norm": 7544.00048828125,
"learning_rate": 4.1991525423728816e-05,
"loss": 0.0928,
"step": 290
},
{
"epoch": 2.2734375,
"grad_norm": 9504.630859375,
"learning_rate": 4.1949152542372886e-05,
"loss": 0.0963,
"step": 291
},
{
"epoch": 2.28125,
"grad_norm": 7236.09521484375,
"learning_rate": 4.1906779661016956e-05,
"loss": 0.0979,
"step": 292
},
{
"epoch": 2.2890625,
"grad_norm": 11308.158203125,
"learning_rate": 4.186440677966102e-05,
"loss": 0.1016,
"step": 293
},
{
"epoch": 2.296875,
"grad_norm": 8347.5537109375,
"learning_rate": 4.182203389830508e-05,
"loss": 0.0993,
"step": 294
},
{
"epoch": 2.3046875,
"grad_norm": 7208.1669921875,
"learning_rate": 4.177966101694916e-05,
"loss": 0.102,
"step": 295
},
{
"epoch": 2.3125,
"grad_norm": 8090.14013671875,
"learning_rate": 4.173728813559322e-05,
"loss": 0.0956,
"step": 296
},
{
"epoch": 2.3203125,
"grad_norm": 7875.2177734375,
"learning_rate": 4.1694915254237285e-05,
"loss": 0.1004,
"step": 297
},
{
"epoch": 2.328125,
"grad_norm": 7086.0478515625,
"learning_rate": 4.165254237288136e-05,
"loss": 0.0774,
"step": 298
},
{
"epoch": 2.3359375,
"grad_norm": 6416.9697265625,
"learning_rate": 4.1610169491525425e-05,
"loss": 0.0884,
"step": 299
},
{
"epoch": 2.34375,
"grad_norm": 6324.03759765625,
"learning_rate": 4.1567796610169495e-05,
"loss": 0.0762,
"step": 300
},
{
"epoch": 2.3515625,
"grad_norm": 10342.5263671875,
"learning_rate": 4.152542372881356e-05,
"loss": 0.1073,
"step": 301
},
{
"epoch": 2.359375,
"grad_norm": 7758.123046875,
"learning_rate": 4.148305084745763e-05,
"loss": 0.0843,
"step": 302
},
{
"epoch": 2.3671875,
"grad_norm": 8296.701171875,
"learning_rate": 4.14406779661017e-05,
"loss": 0.0928,
"step": 303
},
{
"epoch": 2.375,
"grad_norm": 9369.1064453125,
"learning_rate": 4.139830508474576e-05,
"loss": 0.121,
"step": 304
},
{
"epoch": 2.3828125,
"grad_norm": 10246.279296875,
"learning_rate": 4.135593220338983e-05,
"loss": 0.1057,
"step": 305
},
{
"epoch": 2.390625,
"grad_norm": 7801.75537109375,
"learning_rate": 4.13135593220339e-05,
"loss": 0.1031,
"step": 306
},
{
"epoch": 2.3984375,
"grad_norm": 8480.12890625,
"learning_rate": 4.1271186440677965e-05,
"loss": 0.0881,
"step": 307
},
{
"epoch": 2.40625,
"grad_norm": 9395.498046875,
"learning_rate": 4.1228813559322035e-05,
"loss": 0.087,
"step": 308
},
{
"epoch": 2.4140625,
"grad_norm": 7008.09228515625,
"learning_rate": 4.1186440677966105e-05,
"loss": 0.0857,
"step": 309
},
{
"epoch": 2.421875,
"grad_norm": 10005.681640625,
"learning_rate": 4.114406779661017e-05,
"loss": 0.1177,
"step": 310
},
{
"epoch": 2.4296875,
"grad_norm": 11756.0947265625,
"learning_rate": 4.110169491525424e-05,
"loss": 0.1067,
"step": 311
},
{
"epoch": 2.4375,
"grad_norm": 12281.6328125,
"learning_rate": 4.105932203389831e-05,
"loss": 0.1373,
"step": 312
},
{
"epoch": 2.4453125,
"grad_norm": 8212.9228515625,
"learning_rate": 4.101694915254237e-05,
"loss": 0.1032,
"step": 313
},
{
"epoch": 2.453125,
"grad_norm": 9234.9775390625,
"learning_rate": 4.097457627118644e-05,
"loss": 0.0853,
"step": 314
},
{
"epoch": 2.4609375,
"grad_norm": 8216.4384765625,
"learning_rate": 4.093220338983051e-05,
"loss": 0.095,
"step": 315
},
{
"epoch": 2.46875,
"grad_norm": 7225.9951171875,
"learning_rate": 4.088983050847458e-05,
"loss": 0.1043,
"step": 316
},
{
"epoch": 2.4765625,
"grad_norm": 7565.353515625,
"learning_rate": 4.0847457627118644e-05,
"loss": 0.0869,
"step": 317
},
{
"epoch": 2.484375,
"grad_norm": 8909.1162109375,
"learning_rate": 4.0805084745762714e-05,
"loss": 0.1161,
"step": 318
},
{
"epoch": 2.4921875,
"grad_norm": 6624.9052734375,
"learning_rate": 4.0762711864406784e-05,
"loss": 0.0961,
"step": 319
},
{
"epoch": 2.5,
"grad_norm": 6640.46240234375,
"learning_rate": 4.072033898305085e-05,
"loss": 0.087,
"step": 320
},
{
"epoch": 2.5078125,
"grad_norm": 37102.19140625,
"learning_rate": 4.067796610169492e-05,
"loss": 0.0988,
"step": 321
},
{
"epoch": 2.515625,
"grad_norm": 13478.6650390625,
"learning_rate": 4.063559322033899e-05,
"loss": 0.0956,
"step": 322
},
{
"epoch": 2.5234375,
"grad_norm": 8924.9150390625,
"learning_rate": 4.059322033898305e-05,
"loss": 0.077,
"step": 323
},
{
"epoch": 2.53125,
"grad_norm": 8215.94921875,
"learning_rate": 4.055084745762712e-05,
"loss": 0.0875,
"step": 324
},
{
"epoch": 2.5390625,
"grad_norm": 7980.5810546875,
"learning_rate": 4.050847457627119e-05,
"loss": 0.102,
"step": 325
},
{
"epoch": 2.546875,
"grad_norm": 6554.34228515625,
"learning_rate": 4.0466101694915254e-05,
"loss": 0.0767,
"step": 326
},
{
"epoch": 2.5546875,
"grad_norm": 9588.091796875,
"learning_rate": 4.0423728813559324e-05,
"loss": 0.0946,
"step": 327
},
{
"epoch": 2.5625,
"grad_norm": 8234.3291015625,
"learning_rate": 4.0381355932203394e-05,
"loss": 0.0858,
"step": 328
},
{
"epoch": 2.5703125,
"grad_norm": 7283.93115234375,
"learning_rate": 4.0338983050847464e-05,
"loss": 0.1001,
"step": 329
},
{
"epoch": 2.578125,
"grad_norm": 8910.1572265625,
"learning_rate": 4.029661016949153e-05,
"loss": 0.1002,
"step": 330
},
{
"epoch": 2.5859375,
"grad_norm": 10155.5458984375,
"learning_rate": 4.025423728813559e-05,
"loss": 0.0911,
"step": 331
},
{
"epoch": 2.59375,
"grad_norm": 9585.150390625,
"learning_rate": 4.021186440677967e-05,
"loss": 0.086,
"step": 332
},
{
"epoch": 2.6015625,
"grad_norm": 9947.6220703125,
"learning_rate": 4.016949152542373e-05,
"loss": 0.0776,
"step": 333
},
{
"epoch": 2.609375,
"grad_norm": 7666.09521484375,
"learning_rate": 4.012711864406779e-05,
"loss": 0.0859,
"step": 334
},
{
"epoch": 2.6171875,
"grad_norm": 9651.0458984375,
"learning_rate": 4.008474576271187e-05,
"loss": 0.0805,
"step": 335
},
{
"epoch": 2.625,
"grad_norm": 7785.93505859375,
"learning_rate": 4.004237288135593e-05,
"loss": 0.1061,
"step": 336
},
{
"epoch": 2.6328125,
"grad_norm": 7502.2744140625,
"learning_rate": 4e-05,
"loss": 0.0698,
"step": 337
},
{
"epoch": 2.640625,
"grad_norm": 8920.7509765625,
"learning_rate": 3.9957627118644066e-05,
"loss": 0.0975,
"step": 338
},
{
"epoch": 2.6484375,
"grad_norm": 8391.4990234375,
"learning_rate": 3.9915254237288136e-05,
"loss": 0.0894,
"step": 339
},
{
"epoch": 2.65625,
"grad_norm": 9316.2822265625,
"learning_rate": 3.9872881355932206e-05,
"loss": 0.0785,
"step": 340
},
{
"epoch": 2.6640625,
"grad_norm": 7403.91259765625,
"learning_rate": 3.983050847457627e-05,
"loss": 0.0849,
"step": 341
},
{
"epoch": 2.671875,
"grad_norm": 8460.8525390625,
"learning_rate": 3.978813559322034e-05,
"loss": 0.0803,
"step": 342
},
{
"epoch": 2.6796875,
"grad_norm": 8487.8564453125,
"learning_rate": 3.974576271186441e-05,
"loss": 0.0896,
"step": 343
},
{
"epoch": 2.6875,
"grad_norm": 10957.083984375,
"learning_rate": 3.970338983050847e-05,
"loss": 0.1003,
"step": 344
},
{
"epoch": 2.6953125,
"grad_norm": 7198.779296875,
"learning_rate": 3.966101694915255e-05,
"loss": 0.0873,
"step": 345
},
{
"epoch": 2.703125,
"grad_norm": 7133.6748046875,
"learning_rate": 3.961864406779661e-05,
"loss": 0.0836,
"step": 346
},
{
"epoch": 2.7109375,
"grad_norm": 14363.6474609375,
"learning_rate": 3.9576271186440676e-05,
"loss": 0.1123,
"step": 347
},
{
"epoch": 2.71875,
"grad_norm": 8815.900390625,
"learning_rate": 3.9533898305084746e-05,
"loss": 0.107,
"step": 348
},
{
"epoch": 2.7265625,
"grad_norm": 7641.95556640625,
"learning_rate": 3.9491525423728816e-05,
"loss": 0.0843,
"step": 349
},
{
"epoch": 2.734375,
"grad_norm": 8751.14453125,
"learning_rate": 3.9449152542372886e-05,
"loss": 0.0943,
"step": 350
},
{
"epoch": 2.7421875,
"grad_norm": 7734.27490234375,
"learning_rate": 3.940677966101695e-05,
"loss": 0.0923,
"step": 351
},
{
"epoch": 2.75,
"grad_norm": 9654.419921875,
"learning_rate": 3.936440677966102e-05,
"loss": 0.087,
"step": 352
},
{
"epoch": 2.7578125,
"grad_norm": 8524.4765625,
"learning_rate": 3.932203389830509e-05,
"loss": 0.0832,
"step": 353
},
{
"epoch": 2.765625,
"grad_norm": 9234.8359375,
"learning_rate": 3.927966101694915e-05,
"loss": 0.0851,
"step": 354
},
{
"epoch": 2.7734375,
"grad_norm": 9767.935546875,
"learning_rate": 3.923728813559322e-05,
"loss": 0.0834,
"step": 355
},
{
"epoch": 2.78125,
"grad_norm": 8757.10546875,
"learning_rate": 3.919491525423729e-05,
"loss": 0.0781,
"step": 356
},
{
"epoch": 2.7890625,
"grad_norm": 8494.0634765625,
"learning_rate": 3.9152542372881355e-05,
"loss": 0.0891,
"step": 357
},
{
"epoch": 2.796875,
"grad_norm": 8233.05859375,
"learning_rate": 3.9110169491525425e-05,
"loss": 0.1029,
"step": 358
},
{
"epoch": 2.8046875,
"grad_norm": 8199.48828125,
"learning_rate": 3.9067796610169495e-05,
"loss": 0.0854,
"step": 359
},
{
"epoch": 2.8125,
"grad_norm": 10819.1748046875,
"learning_rate": 3.902542372881356e-05,
"loss": 0.0822,
"step": 360
},
{
"epoch": 2.8203125,
"grad_norm": 6709.2529296875,
"learning_rate": 3.898305084745763e-05,
"loss": 0.0753,
"step": 361
},
{
"epoch": 2.828125,
"grad_norm": 9326.4189453125,
"learning_rate": 3.89406779661017e-05,
"loss": 0.089,
"step": 362
},
{
"epoch": 2.8359375,
"grad_norm": 8590.9599609375,
"learning_rate": 3.889830508474576e-05,
"loss": 0.0841,
"step": 363
},
{
"epoch": 2.84375,
"grad_norm": 6745.58203125,
"learning_rate": 3.885593220338983e-05,
"loss": 0.0806,
"step": 364
},
{
"epoch": 2.8515625,
"grad_norm": 7817.287109375,
"learning_rate": 3.88135593220339e-05,
"loss": 0.0866,
"step": 365
},
{
"epoch": 2.859375,
"grad_norm": 7852.57177734375,
"learning_rate": 3.877118644067797e-05,
"loss": 0.0896,
"step": 366
},
{
"epoch": 2.8671875,
"grad_norm": 10497.076171875,
"learning_rate": 3.8728813559322035e-05,
"loss": 0.0796,
"step": 367
},
{
"epoch": 2.875,
"grad_norm": 6971.8583984375,
"learning_rate": 3.86864406779661e-05,
"loss": 0.0818,
"step": 368
},
{
"epoch": 2.8828125,
"grad_norm": 8942.3916015625,
"learning_rate": 3.8644067796610175e-05,
"loss": 0.0982,
"step": 369
},
{
"epoch": 2.890625,
"grad_norm": 10976.0576171875,
"learning_rate": 3.860169491525424e-05,
"loss": 0.0816,
"step": 370
},
{
"epoch": 2.8984375,
"grad_norm": 16122.8623046875,
"learning_rate": 3.855932203389831e-05,
"loss": 0.0973,
"step": 371
},
{
"epoch": 2.90625,
"grad_norm": 7621.5654296875,
"learning_rate": 3.851694915254238e-05,
"loss": 0.0709,
"step": 372
},
{
"epoch": 2.9140625,
"grad_norm": 9706.9794921875,
"learning_rate": 3.847457627118644e-05,
"loss": 0.0746,
"step": 373
},
{
"epoch": 2.921875,
"grad_norm": 9208.0,
"learning_rate": 3.843220338983051e-05,
"loss": 0.0876,
"step": 374
},
{
"epoch": 2.9296875,
"grad_norm": 7535.5673828125,
"learning_rate": 3.838983050847458e-05,
"loss": 0.0877,
"step": 375
},
{
"epoch": 2.9375,
"grad_norm": 7541.5791015625,
"learning_rate": 3.8347457627118644e-05,
"loss": 0.0844,
"step": 376
},
{
"epoch": 2.9453125,
"grad_norm": 10384.912109375,
"learning_rate": 3.8305084745762714e-05,
"loss": 0.0883,
"step": 377
},
{
"epoch": 2.953125,
"grad_norm": 9038.6640625,
"learning_rate": 3.826271186440678e-05,
"loss": 0.0845,
"step": 378
},
{
"epoch": 2.9609375,
"grad_norm": 8128.64794921875,
"learning_rate": 3.8220338983050854e-05,
"loss": 0.0769,
"step": 379
},
{
"epoch": 2.96875,
"grad_norm": 9013.828125,
"learning_rate": 3.817796610169492e-05,
"loss": 0.086,
"step": 380
},
{
"epoch": 2.9765625,
"grad_norm": 8422.8271484375,
"learning_rate": 3.813559322033898e-05,
"loss": 0.0746,
"step": 381
},
{
"epoch": 2.984375,
"grad_norm": 11208.2646484375,
"learning_rate": 3.809322033898306e-05,
"loss": 0.0831,
"step": 382
},
{
"epoch": 2.9921875,
"grad_norm": 9259.0361328125,
"learning_rate": 3.805084745762712e-05,
"loss": 0.0904,
"step": 383
},
{
"epoch": 3.0,
"grad_norm": 11485.599609375,
"learning_rate": 3.8008474576271184e-05,
"loss": 0.0833,
"step": 384
},
{
"epoch": 3.0,
"eval_f1_macro": 0.08875038904450669,
"eval_f1_micro": 0.4547069271758437,
"eval_loss": 0.07855294644832611,
"eval_precision": 0.8827586206896552,
"eval_recall": 0.3062200956937799,
"eval_runtime": 0.9654,
"eval_samples_per_second": 354.266,
"eval_steps_per_second": 15.538,
"step": 384
},
{
"epoch": 3.0078125,
"grad_norm": 8094.0009765625,
"learning_rate": 3.7966101694915254e-05,
"loss": 0.0935,
"step": 385
},
{
"epoch": 3.015625,
"grad_norm": 7478.25537109375,
"learning_rate": 3.7923728813559324e-05,
"loss": 0.08,
"step": 386
},
{
"epoch": 3.0234375,
"grad_norm": 7963.64111328125,
"learning_rate": 3.7881355932203394e-05,
"loss": 0.0696,
"step": 387
},
{
"epoch": 3.03125,
"grad_norm": 11784.6767578125,
"learning_rate": 3.783898305084746e-05,
"loss": 0.0949,
"step": 388
},
{
"epoch": 3.0390625,
"grad_norm": 6836.80322265625,
"learning_rate": 3.779661016949153e-05,
"loss": 0.0707,
"step": 389
},
{
"epoch": 3.046875,
"grad_norm": 6612.1650390625,
"learning_rate": 3.77542372881356e-05,
"loss": 0.0733,
"step": 390
},
{
"epoch": 3.0546875,
"grad_norm": 9404.9140625,
"learning_rate": 3.771186440677966e-05,
"loss": 0.0779,
"step": 391
},
{
"epoch": 3.0625,
"grad_norm": 6216.525390625,
"learning_rate": 3.766949152542373e-05,
"loss": 0.0689,
"step": 392
},
{
"epoch": 3.0703125,
"grad_norm": 9686.9755859375,
"learning_rate": 3.76271186440678e-05,
"loss": 0.0782,
"step": 393
},
{
"epoch": 3.078125,
"grad_norm": 10290.8818359375,
"learning_rate": 3.7584745762711864e-05,
"loss": 0.0866,
"step": 394
},
{
"epoch": 3.0859375,
"grad_norm": 6736.78662109375,
"learning_rate": 3.7542372881355934e-05,
"loss": 0.0772,
"step": 395
},
{
"epoch": 3.09375,
"grad_norm": 10578.359375,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0829,
"step": 396
},
{
"epoch": 3.1015625,
"grad_norm": 7567.2236328125,
"learning_rate": 3.745762711864407e-05,
"loss": 0.0846,
"step": 397
},
{
"epoch": 3.109375,
"grad_norm": 7298.95458984375,
"learning_rate": 3.741525423728814e-05,
"loss": 0.0798,
"step": 398
},
{
"epoch": 3.1171875,
"grad_norm": 7413.47021484375,
"learning_rate": 3.737288135593221e-05,
"loss": 0.0744,
"step": 399
},
{
"epoch": 3.125,
"grad_norm": 7135.65673828125,
"learning_rate": 3.733050847457628e-05,
"loss": 0.0724,
"step": 400
},
{
"epoch": 3.1328125,
"grad_norm": 6277.826171875,
"learning_rate": 3.728813559322034e-05,
"loss": 0.0744,
"step": 401
},
{
"epoch": 3.140625,
"grad_norm": 7761.1396484375,
"learning_rate": 3.724576271186441e-05,
"loss": 0.0688,
"step": 402
},
{
"epoch": 3.1484375,
"grad_norm": 8545.7197265625,
"learning_rate": 3.720338983050848e-05,
"loss": 0.0694,
"step": 403
},
{
"epoch": 3.15625,
"grad_norm": 8417.447265625,
"learning_rate": 3.716101694915254e-05,
"loss": 0.0921,
"step": 404
},
{
"epoch": 3.1640625,
"grad_norm": 8225.7421875,
"learning_rate": 3.711864406779661e-05,
"loss": 0.079,
"step": 405
},
{
"epoch": 3.171875,
"grad_norm": 8091.76318359375,
"learning_rate": 3.707627118644068e-05,
"loss": 0.0773,
"step": 406
},
{
"epoch": 3.1796875,
"grad_norm": 6200.6904296875,
"learning_rate": 3.7033898305084746e-05,
"loss": 0.0726,
"step": 407
},
{
"epoch": 3.1875,
"grad_norm": 9000.396484375,
"learning_rate": 3.6991525423728816e-05,
"loss": 0.083,
"step": 408
},
{
"epoch": 3.1953125,
"grad_norm": 9996.87109375,
"learning_rate": 3.6949152542372886e-05,
"loss": 0.0934,
"step": 409
},
{
"epoch": 3.203125,
"grad_norm": 8543.9453125,
"learning_rate": 3.690677966101695e-05,
"loss": 0.0796,
"step": 410
},
{
"epoch": 3.2109375,
"grad_norm": 8270.6513671875,
"learning_rate": 3.686440677966102e-05,
"loss": 0.074,
"step": 411
},
{
"epoch": 3.21875,
"grad_norm": 9006.31640625,
"learning_rate": 3.682203389830509e-05,
"loss": 0.0721,
"step": 412
},
{
"epoch": 3.2265625,
"grad_norm": 10627.8466796875,
"learning_rate": 3.677966101694915e-05,
"loss": 0.0728,
"step": 413
},
{
"epoch": 3.234375,
"grad_norm": 7212.29931640625,
"learning_rate": 3.673728813559322e-05,
"loss": 0.0562,
"step": 414
},
{
"epoch": 3.2421875,
"grad_norm": 8798.2431640625,
"learning_rate": 3.6694915254237286e-05,
"loss": 0.08,
"step": 415
},
{
"epoch": 3.25,
"grad_norm": 8120.35400390625,
"learning_rate": 3.665254237288136e-05,
"loss": 0.0688,
"step": 416
},
{
"epoch": 3.2578125,
"grad_norm": 9503.84765625,
"learning_rate": 3.6610169491525426e-05,
"loss": 0.0739,
"step": 417
},
{
"epoch": 3.265625,
"grad_norm": 8463.0078125,
"learning_rate": 3.656779661016949e-05,
"loss": 0.083,
"step": 418
},
{
"epoch": 3.2734375,
"grad_norm": 8095.166015625,
"learning_rate": 3.6525423728813566e-05,
"loss": 0.0689,
"step": 419
},
{
"epoch": 3.28125,
"grad_norm": 8498.3037109375,
"learning_rate": 3.648305084745763e-05,
"loss": 0.0959,
"step": 420
},
{
"epoch": 3.2890625,
"grad_norm": 8614.3544921875,
"learning_rate": 3.644067796610169e-05,
"loss": 0.0624,
"step": 421
},
{
"epoch": 3.296875,
"grad_norm": 9187.6728515625,
"learning_rate": 3.639830508474576e-05,
"loss": 0.0701,
"step": 422
},
{
"epoch": 3.3046875,
"grad_norm": 10048.8173828125,
"learning_rate": 3.635593220338983e-05,
"loss": 0.0797,
"step": 423
},
{
"epoch": 3.3125,
"grad_norm": 8041.92578125,
"learning_rate": 3.63135593220339e-05,
"loss": 0.0653,
"step": 424
},
{
"epoch": 3.3203125,
"grad_norm": 6864.189453125,
"learning_rate": 3.6271186440677965e-05,
"loss": 0.0612,
"step": 425
},
{
"epoch": 3.328125,
"grad_norm": 7392.79833984375,
"learning_rate": 3.6228813559322035e-05,
"loss": 0.0756,
"step": 426
},
{
"epoch": 3.3359375,
"grad_norm": 13530.8203125,
"learning_rate": 3.6186440677966105e-05,
"loss": 0.0838,
"step": 427
},
{
"epoch": 3.34375,
"grad_norm": 7618.60791015625,
"learning_rate": 3.614406779661017e-05,
"loss": 0.0601,
"step": 428
},
{
"epoch": 3.3515625,
"grad_norm": 5971.470703125,
"learning_rate": 3.610169491525424e-05,
"loss": 0.057,
"step": 429
},
{
"epoch": 3.359375,
"grad_norm": 9799.69921875,
"learning_rate": 3.605932203389831e-05,
"loss": 0.0808,
"step": 430
},
{
"epoch": 3.3671875,
"grad_norm": 8180.22216796875,
"learning_rate": 3.601694915254237e-05,
"loss": 0.0788,
"step": 431
},
{
"epoch": 3.375,
"grad_norm": 9090.4853515625,
"learning_rate": 3.597457627118644e-05,
"loss": 0.0562,
"step": 432
},
{
"epoch": 3.3828125,
"grad_norm": 6761.97412109375,
"learning_rate": 3.593220338983051e-05,
"loss": 0.0703,
"step": 433
},
{
"epoch": 3.390625,
"grad_norm": 9256.5263671875,
"learning_rate": 3.5889830508474575e-05,
"loss": 0.0864,
"step": 434
},
{
"epoch": 3.3984375,
"grad_norm": 11279.953125,
"learning_rate": 3.5847457627118645e-05,
"loss": 0.0974,
"step": 435
},
{
"epoch": 3.40625,
"grad_norm": 12105.296875,
"learning_rate": 3.5805084745762715e-05,
"loss": 0.0662,
"step": 436
},
{
"epoch": 3.4140625,
"grad_norm": 9423.44921875,
"learning_rate": 3.5762711864406785e-05,
"loss": 0.0719,
"step": 437
},
{
"epoch": 3.421875,
"grad_norm": 10583.11328125,
"learning_rate": 3.572033898305085e-05,
"loss": 0.0624,
"step": 438
},
{
"epoch": 3.4296875,
"grad_norm": 6143.14501953125,
"learning_rate": 3.567796610169492e-05,
"loss": 0.0676,
"step": 439
},
{
"epoch": 3.4375,
"grad_norm": 7021.9609375,
"learning_rate": 3.563559322033899e-05,
"loss": 0.0695,
"step": 440
},
{
"epoch": 3.4453125,
"grad_norm": 8982.669921875,
"learning_rate": 3.559322033898305e-05,
"loss": 0.0677,
"step": 441
},
{
"epoch": 3.453125,
"grad_norm": 8486.2431640625,
"learning_rate": 3.555084745762712e-05,
"loss": 0.0879,
"step": 442
},
{
"epoch": 3.4609375,
"grad_norm": 8326.0029296875,
"learning_rate": 3.550847457627119e-05,
"loss": 0.0804,
"step": 443
},
{
"epoch": 3.46875,
"grad_norm": 11409.9072265625,
"learning_rate": 3.5466101694915254e-05,
"loss": 0.0662,
"step": 444
},
{
"epoch": 3.4765625,
"grad_norm": 8052.24462890625,
"learning_rate": 3.5423728813559324e-05,
"loss": 0.055,
"step": 445
},
{
"epoch": 3.484375,
"grad_norm": 8522.208984375,
"learning_rate": 3.5381355932203394e-05,
"loss": 0.0635,
"step": 446
},
{
"epoch": 3.4921875,
"grad_norm": 11872.1767578125,
"learning_rate": 3.533898305084746e-05,
"loss": 0.0799,
"step": 447
},
{
"epoch": 3.5,
"grad_norm": 9222.8779296875,
"learning_rate": 3.529661016949153e-05,
"loss": 0.0775,
"step": 448
},
{
"epoch": 3.5078125,
"grad_norm": 7528.74365234375,
"learning_rate": 3.52542372881356e-05,
"loss": 0.0841,
"step": 449
},
{
"epoch": 3.515625,
"grad_norm": 12997.033203125,
"learning_rate": 3.521186440677967e-05,
"loss": 0.0729,
"step": 450
},
{
"epoch": 3.5234375,
"grad_norm": 8383.8115234375,
"learning_rate": 3.516949152542373e-05,
"loss": 0.0764,
"step": 451
},
{
"epoch": 3.53125,
"grad_norm": 10004.0771484375,
"learning_rate": 3.5127118644067794e-05,
"loss": 0.0702,
"step": 452
},
{
"epoch": 3.5390625,
"grad_norm": 11020.66015625,
"learning_rate": 3.508474576271187e-05,
"loss": 0.0667,
"step": 453
},
{
"epoch": 3.546875,
"grad_norm": 8764.0625,
"learning_rate": 3.5042372881355934e-05,
"loss": 0.0769,
"step": 454
},
{
"epoch": 3.5546875,
"grad_norm": 9359.4228515625,
"learning_rate": 3.5e-05,
"loss": 0.0766,
"step": 455
},
{
"epoch": 3.5625,
"grad_norm": 9242.2314453125,
"learning_rate": 3.4957627118644074e-05,
"loss": 0.0654,
"step": 456
},
{
"epoch": 3.5703125,
"grad_norm": 9558.1455078125,
"learning_rate": 3.491525423728814e-05,
"loss": 0.0774,
"step": 457
},
{
"epoch": 3.578125,
"grad_norm": 10789.7060546875,
"learning_rate": 3.487288135593221e-05,
"loss": 0.0724,
"step": 458
},
{
"epoch": 3.5859375,
"grad_norm": 7481.1708984375,
"learning_rate": 3.483050847457627e-05,
"loss": 0.0585,
"step": 459
},
{
"epoch": 3.59375,
"grad_norm": 9794.4970703125,
"learning_rate": 3.478813559322034e-05,
"loss": 0.0712,
"step": 460
},
{
"epoch": 3.6015625,
"grad_norm": 9024.8857421875,
"learning_rate": 3.474576271186441e-05,
"loss": 0.0663,
"step": 461
},
{
"epoch": 3.609375,
"grad_norm": 9181.2705078125,
"learning_rate": 3.470338983050847e-05,
"loss": 0.064,
"step": 462
},
{
"epoch": 3.6171875,
"grad_norm": 7411.22509765625,
"learning_rate": 3.466101694915254e-05,
"loss": 0.0672,
"step": 463
},
{
"epoch": 3.625,
"grad_norm": 8328.5322265625,
"learning_rate": 3.461864406779661e-05,
"loss": 0.0665,
"step": 464
},
{
"epoch": 3.6328125,
"grad_norm": 7927.46875,
"learning_rate": 3.4576271186440676e-05,
"loss": 0.0614,
"step": 465
},
{
"epoch": 3.640625,
"grad_norm": 6948.078125,
"learning_rate": 3.4533898305084746e-05,
"loss": 0.052,
"step": 466
},
{
"epoch": 3.6484375,
"grad_norm": 9418.59375,
"learning_rate": 3.4491525423728816e-05,
"loss": 0.0671,
"step": 467
},
{
"epoch": 3.65625,
"grad_norm": 24462.330078125,
"learning_rate": 3.444915254237288e-05,
"loss": 0.1247,
"step": 468
},
{
"epoch": 3.6640625,
"grad_norm": 8671.6357421875,
"learning_rate": 3.440677966101695e-05,
"loss": 0.0729,
"step": 469
},
{
"epoch": 3.671875,
"grad_norm": 8236.5654296875,
"learning_rate": 3.436440677966102e-05,
"loss": 0.0661,
"step": 470
},
{
"epoch": 3.6796875,
"grad_norm": 9265.0244140625,
"learning_rate": 3.432203389830508e-05,
"loss": 0.06,
"step": 471
},
{
"epoch": 3.6875,
"grad_norm": 10549.0009765625,
"learning_rate": 3.427966101694915e-05,
"loss": 0.0783,
"step": 472
},
{
"epoch": 3.6953125,
"grad_norm": 18151.03515625,
"learning_rate": 3.423728813559322e-05,
"loss": 0.0645,
"step": 473
},
{
"epoch": 3.703125,
"grad_norm": 7044.111328125,
"learning_rate": 3.419491525423729e-05,
"loss": 0.0575,
"step": 474
},
{
"epoch": 3.7109375,
"grad_norm": 8044.390625,
"learning_rate": 3.4152542372881356e-05,
"loss": 0.0605,
"step": 475
},
{
"epoch": 3.71875,
"grad_norm": 9083.5244140625,
"learning_rate": 3.4110169491525426e-05,
"loss": 0.0806,
"step": 476
},
{
"epoch": 3.7265625,
"grad_norm": 8964.7109375,
"learning_rate": 3.4067796610169496e-05,
"loss": 0.0843,
"step": 477
},
{
"epoch": 3.734375,
"grad_norm": 8507.720703125,
"learning_rate": 3.402542372881356e-05,
"loss": 0.0756,
"step": 478
},
{
"epoch": 3.7421875,
"grad_norm": 9470.3564453125,
"learning_rate": 3.398305084745763e-05,
"loss": 0.0646,
"step": 479
},
{
"epoch": 3.75,
"grad_norm": 8800.326171875,
"learning_rate": 3.39406779661017e-05,
"loss": 0.0708,
"step": 480
},
{
"epoch": 3.7578125,
"grad_norm": 8752.83203125,
"learning_rate": 3.389830508474576e-05,
"loss": 0.071,
"step": 481
},
{
"epoch": 3.765625,
"grad_norm": 9763.537109375,
"learning_rate": 3.385593220338983e-05,
"loss": 0.0793,
"step": 482
},
{
"epoch": 3.7734375,
"grad_norm": 11746.50390625,
"learning_rate": 3.38135593220339e-05,
"loss": 0.0731,
"step": 483
},
{
"epoch": 3.78125,
"grad_norm": 7145.78662109375,
"learning_rate": 3.3771186440677965e-05,
"loss": 0.0641,
"step": 484
},
{
"epoch": 3.7890625,
"grad_norm": 9165.763671875,
"learning_rate": 3.3728813559322035e-05,
"loss": 0.0661,
"step": 485
},
{
"epoch": 3.796875,
"grad_norm": 10185.8759765625,
"learning_rate": 3.3686440677966105e-05,
"loss": 0.0723,
"step": 486
},
{
"epoch": 3.8046875,
"grad_norm": 9282.6337890625,
"learning_rate": 3.3644067796610175e-05,
"loss": 0.0791,
"step": 487
},
{
"epoch": 3.8125,
"grad_norm": 7239.23193359375,
"learning_rate": 3.360169491525424e-05,
"loss": 0.0564,
"step": 488
},
{
"epoch": 3.8203125,
"grad_norm": 11052.4541015625,
"learning_rate": 3.35593220338983e-05,
"loss": 0.0797,
"step": 489
},
{
"epoch": 3.828125,
"grad_norm": 7131.8564453125,
"learning_rate": 3.351694915254238e-05,
"loss": 0.0612,
"step": 490
},
{
"epoch": 3.8359375,
"grad_norm": 7524.51318359375,
"learning_rate": 3.347457627118644e-05,
"loss": 0.0482,
"step": 491
},
{
"epoch": 3.84375,
"grad_norm": 10200.5078125,
"learning_rate": 3.3432203389830505e-05,
"loss": 0.081,
"step": 492
},
{
"epoch": 3.8515625,
"grad_norm": 7360.52783203125,
"learning_rate": 3.338983050847458e-05,
"loss": 0.0625,
"step": 493
},
{
"epoch": 3.859375,
"grad_norm": 6450.5263671875,
"learning_rate": 3.3347457627118645e-05,
"loss": 0.0568,
"step": 494
},
{
"epoch": 3.8671875,
"grad_norm": 7416.14794921875,
"learning_rate": 3.3305084745762715e-05,
"loss": 0.0577,
"step": 495
},
{
"epoch": 3.875,
"grad_norm": 12262.193359375,
"learning_rate": 3.326271186440678e-05,
"loss": 0.0694,
"step": 496
},
{
"epoch": 3.8828125,
"grad_norm": 7449.9794921875,
"learning_rate": 3.322033898305085e-05,
"loss": 0.0609,
"step": 497
},
{
"epoch": 3.890625,
"grad_norm": 9025.8583984375,
"learning_rate": 3.317796610169492e-05,
"loss": 0.0671,
"step": 498
},
{
"epoch": 3.8984375,
"grad_norm": 8396.77734375,
"learning_rate": 3.313559322033898e-05,
"loss": 0.0782,
"step": 499
},
{
"epoch": 3.90625,
"grad_norm": 11866.7099609375,
"learning_rate": 3.309322033898305e-05,
"loss": 0.0673,
"step": 500
},
{
"epoch": 3.9140625,
"grad_norm": 9887.666015625,
"learning_rate": 3.305084745762712e-05,
"loss": 0.0571,
"step": 501
},
{
"epoch": 3.921875,
"grad_norm": 11035.9462890625,
"learning_rate": 3.3008474576271184e-05,
"loss": 0.0599,
"step": 502
},
{
"epoch": 3.9296875,
"grad_norm": 7554.6259765625,
"learning_rate": 3.296610169491526e-05,
"loss": 0.0561,
"step": 503
},
{
"epoch": 3.9375,
"grad_norm": 9872.501953125,
"learning_rate": 3.2923728813559324e-05,
"loss": 0.0665,
"step": 504
},
{
"epoch": 3.9453125,
"grad_norm": 10301.208984375,
"learning_rate": 3.288135593220339e-05,
"loss": 0.0556,
"step": 505
},
{
"epoch": 3.953125,
"grad_norm": 9006.5595703125,
"learning_rate": 3.283898305084746e-05,
"loss": 0.0581,
"step": 506
},
{
"epoch": 3.9609375,
"grad_norm": 7544.42431640625,
"learning_rate": 3.279661016949153e-05,
"loss": 0.0466,
"step": 507
},
{
"epoch": 3.96875,
"grad_norm": 8901.37109375,
"learning_rate": 3.27542372881356e-05,
"loss": 0.062,
"step": 508
},
{
"epoch": 3.9765625,
"grad_norm": 11854.673828125,
"learning_rate": 3.271186440677966e-05,
"loss": 0.0548,
"step": 509
},
{
"epoch": 3.984375,
"grad_norm": 10673.900390625,
"learning_rate": 3.266949152542373e-05,
"loss": 0.0697,
"step": 510
},
{
"epoch": 3.9921875,
"grad_norm": 8974.0244140625,
"learning_rate": 3.26271186440678e-05,
"loss": 0.0648,
"step": 511
},
{
"epoch": 4.0,
"grad_norm": 12977.0859375,
"learning_rate": 3.2584745762711864e-05,
"loss": 0.0794,
"step": 512
},
{
"epoch": 4.0,
"eval_f1_macro": 0.24606818117447113,
"eval_f1_micro": 0.6244343891402715,
"eval_loss": 0.061012864112854004,
"eval_precision": 0.8448979591836735,
"eval_recall": 0.49521531100478466,
"eval_runtime": 0.9438,
"eval_samples_per_second": 362.364,
"eval_steps_per_second": 15.893,
"step": 512
},
{
"epoch": 4.0078125,
"grad_norm": 6036.712890625,
"learning_rate": 3.2542372881355934e-05,
"loss": 0.0528,
"step": 513
},
{
"epoch": 4.015625,
"grad_norm": 8663.974609375,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0622,
"step": 514
},
{
"epoch": 4.0234375,
"grad_norm": 7359.67333984375,
"learning_rate": 3.245762711864407e-05,
"loss": 0.0572,
"step": 515
},
{
"epoch": 4.03125,
"grad_norm": 10655.392578125,
"learning_rate": 3.241525423728814e-05,
"loss": 0.0695,
"step": 516
},
{
"epoch": 4.0390625,
"grad_norm": 7536.86767578125,
"learning_rate": 3.237288135593221e-05,
"loss": 0.0667,
"step": 517
},
{
"epoch": 4.046875,
"grad_norm": 6937.216796875,
"learning_rate": 3.233050847457627e-05,
"loss": 0.0588,
"step": 518
},
{
"epoch": 4.0546875,
"grad_norm": 7161.82470703125,
"learning_rate": 3.228813559322034e-05,
"loss": 0.0615,
"step": 519
},
{
"epoch": 4.0625,
"grad_norm": 7335.72265625,
"learning_rate": 3.224576271186441e-05,
"loss": 0.0571,
"step": 520
},
{
"epoch": 4.0703125,
"grad_norm": 6665.498046875,
"learning_rate": 3.2203389830508473e-05,
"loss": 0.0688,
"step": 521
},
{
"epoch": 4.078125,
"grad_norm": 9618.521484375,
"learning_rate": 3.2161016949152543e-05,
"loss": 0.0659,
"step": 522
},
{
"epoch": 4.0859375,
"grad_norm": 9007.03515625,
"learning_rate": 3.2118644067796613e-05,
"loss": 0.0507,
"step": 523
},
{
"epoch": 4.09375,
"grad_norm": 9282.5048828125,
"learning_rate": 3.2076271186440683e-05,
"loss": 0.0645,
"step": 524
},
{
"epoch": 4.1015625,
"grad_norm": 5419.43408203125,
"learning_rate": 3.203389830508475e-05,
"loss": 0.0454,
"step": 525
},
{
"epoch": 4.109375,
"grad_norm": 6807.5498046875,
"learning_rate": 3.199152542372881e-05,
"loss": 0.0544,
"step": 526
},
{
"epoch": 4.1171875,
"grad_norm": 9190.9052734375,
"learning_rate": 3.1949152542372887e-05,
"loss": 0.0671,
"step": 527
},
{
"epoch": 4.125,
"grad_norm": 11522.5576171875,
"learning_rate": 3.190677966101695e-05,
"loss": 0.0676,
"step": 528
},
{
"epoch": 4.1328125,
"grad_norm": 8915.4482421875,
"learning_rate": 3.186440677966101e-05,
"loss": 0.064,
"step": 529
},
{
"epoch": 4.140625,
"grad_norm": 7746.9384765625,
"learning_rate": 3.182203389830509e-05,
"loss": 0.0498,
"step": 530
},
{
"epoch": 4.1484375,
"grad_norm": 9993.7685546875,
"learning_rate": 3.177966101694915e-05,
"loss": 0.047,
"step": 531
},
{
"epoch": 4.15625,
"grad_norm": 10351.76953125,
"learning_rate": 3.173728813559322e-05,
"loss": 0.0606,
"step": 532
},
{
"epoch": 4.1640625,
"grad_norm": 7007.13427734375,
"learning_rate": 3.169491525423729e-05,
"loss": 0.0594,
"step": 533
},
{
"epoch": 4.171875,
"grad_norm": 8622.2939453125,
"learning_rate": 3.1652542372881356e-05,
"loss": 0.0623,
"step": 534
},
{
"epoch": 4.1796875,
"grad_norm": 6703.029296875,
"learning_rate": 3.1610169491525426e-05,
"loss": 0.0517,
"step": 535
},
{
"epoch": 4.1875,
"grad_norm": 10848.2060546875,
"learning_rate": 3.156779661016949e-05,
"loss": 0.0612,
"step": 536
},
{
"epoch": 4.1953125,
"grad_norm": 8520.833984375,
"learning_rate": 3.1525423728813566e-05,
"loss": 0.0445,
"step": 537
},
{
"epoch": 4.203125,
"grad_norm": 9684.46875,
"learning_rate": 3.148305084745763e-05,
"loss": 0.055,
"step": 538
},
{
"epoch": 4.2109375,
"grad_norm": 10403.833984375,
"learning_rate": 3.144067796610169e-05,
"loss": 0.0609,
"step": 539
},
{
"epoch": 4.21875,
"grad_norm": 24900.744140625,
"learning_rate": 3.139830508474577e-05,
"loss": 0.0548,
"step": 540
},
{
"epoch": 4.2265625,
"grad_norm": 6312.015625,
"learning_rate": 3.135593220338983e-05,
"loss": 0.0495,
"step": 541
},
{
"epoch": 4.234375,
"grad_norm": 7820.98291015625,
"learning_rate": 3.1313559322033896e-05,
"loss": 0.0742,
"step": 542
},
{
"epoch": 4.2421875,
"grad_norm": 9990.423828125,
"learning_rate": 3.1271186440677966e-05,
"loss": 0.0587,
"step": 543
},
{
"epoch": 4.25,
"grad_norm": 9218.4833984375,
"learning_rate": 3.1228813559322036e-05,
"loss": 0.0506,
"step": 544
},
{
"epoch": 4.2578125,
"grad_norm": 5639.20751953125,
"learning_rate": 3.1186440677966106e-05,
"loss": 0.0503,
"step": 545
},
{
"epoch": 4.265625,
"grad_norm": 7551.76220703125,
"learning_rate": 3.114406779661017e-05,
"loss": 0.0549,
"step": 546
},
{
"epoch": 4.2734375,
"grad_norm": 5882.1787109375,
"learning_rate": 3.110169491525424e-05,
"loss": 0.0419,
"step": 547
},
{
"epoch": 4.28125,
"grad_norm": 8972.025390625,
"learning_rate": 3.105932203389831e-05,
"loss": 0.0621,
"step": 548
},
{
"epoch": 4.2890625,
"grad_norm": 12484.6513671875,
"learning_rate": 3.101694915254237e-05,
"loss": 0.0629,
"step": 549
},
{
"epoch": 4.296875,
"grad_norm": 12735.1396484375,
"learning_rate": 3.097457627118644e-05,
"loss": 0.0732,
"step": 550
},
{
"epoch": 4.3046875,
"grad_norm": 8783.6162109375,
"learning_rate": 3.093220338983051e-05,
"loss": 0.0727,
"step": 551
},
{
"epoch": 4.3125,
"grad_norm": 17900.498046875,
"learning_rate": 3.0889830508474575e-05,
"loss": 0.071,
"step": 552
},
{
"epoch": 4.3203125,
"grad_norm": 10090.0947265625,
"learning_rate": 3.0847457627118645e-05,
"loss": 0.0538,
"step": 553
},
{
"epoch": 4.328125,
"grad_norm": 10295.0537109375,
"learning_rate": 3.0805084745762715e-05,
"loss": 0.0574,
"step": 554
},
{
"epoch": 4.3359375,
"grad_norm": 8760.890625,
"learning_rate": 3.076271186440678e-05,
"loss": 0.0712,
"step": 555
},
{
"epoch": 4.34375,
"grad_norm": 6124.10546875,
"learning_rate": 3.072033898305085e-05,
"loss": 0.0496,
"step": 556
},
{
"epoch": 4.3515625,
"grad_norm": 9534.9501953125,
"learning_rate": 3.067796610169492e-05,
"loss": 0.0649,
"step": 557
},
{
"epoch": 4.359375,
"grad_norm": 5680.8681640625,
"learning_rate": 3.063559322033899e-05,
"loss": 0.0472,
"step": 558
},
{
"epoch": 4.3671875,
"grad_norm": 8620.578125,
"learning_rate": 3.059322033898305e-05,
"loss": 0.0519,
"step": 559
},
{
"epoch": 4.375,
"grad_norm": 7834.013671875,
"learning_rate": 3.055084745762712e-05,
"loss": 0.052,
"step": 560
},
{
"epoch": 4.3828125,
"grad_norm": 7054.97119140625,
"learning_rate": 3.050847457627119e-05,
"loss": 0.0428,
"step": 561
},
{
"epoch": 4.390625,
"grad_norm": 9393.1943359375,
"learning_rate": 3.0466101694915255e-05,
"loss": 0.0506,
"step": 562
},
{
"epoch": 4.3984375,
"grad_norm": 9048.654296875,
"learning_rate": 3.042372881355932e-05,
"loss": 0.0473,
"step": 563
},
{
"epoch": 4.40625,
"grad_norm": 10525.068359375,
"learning_rate": 3.038135593220339e-05,
"loss": 0.0623,
"step": 564
},
{
"epoch": 4.4140625,
"grad_norm": 6536.67431640625,
"learning_rate": 3.0338983050847458e-05,
"loss": 0.0475,
"step": 565
},
{
"epoch": 4.421875,
"grad_norm": 7490.001953125,
"learning_rate": 3.0296610169491528e-05,
"loss": 0.0529,
"step": 566
},
{
"epoch": 4.4296875,
"grad_norm": 9972.4248046875,
"learning_rate": 3.0254237288135594e-05,
"loss": 0.065,
"step": 567
},
{
"epoch": 4.4375,
"grad_norm": 11988.767578125,
"learning_rate": 3.021186440677966e-05,
"loss": 0.051,
"step": 568
},
{
"epoch": 4.4453125,
"grad_norm": 6232.740234375,
"learning_rate": 3.016949152542373e-05,
"loss": 0.0498,
"step": 569
},
{
"epoch": 4.453125,
"grad_norm": 8058.6513671875,
"learning_rate": 3.0127118644067798e-05,
"loss": 0.0505,
"step": 570
},
{
"epoch": 4.4609375,
"grad_norm": 11326.5009765625,
"learning_rate": 3.0084745762711864e-05,
"loss": 0.0601,
"step": 571
},
{
"epoch": 4.46875,
"grad_norm": 9505.43359375,
"learning_rate": 3.0042372881355934e-05,
"loss": 0.0575,
"step": 572
},
{
"epoch": 4.4765625,
"grad_norm": 7810.712890625,
"learning_rate": 3e-05,
"loss": 0.0511,
"step": 573
},
{
"epoch": 4.484375,
"grad_norm": 7105.65625,
"learning_rate": 2.995762711864407e-05,
"loss": 0.0478,
"step": 574
},
{
"epoch": 4.4921875,
"grad_norm": 6506.89111328125,
"learning_rate": 2.9915254237288137e-05,
"loss": 0.0353,
"step": 575
},
{
"epoch": 4.5,
"grad_norm": 9191.3701171875,
"learning_rate": 2.9872881355932204e-05,
"loss": 0.0679,
"step": 576
},
{
"epoch": 4.5078125,
"grad_norm": 7936.5224609375,
"learning_rate": 2.9830508474576274e-05,
"loss": 0.0571,
"step": 577
},
{
"epoch": 4.515625,
"grad_norm": 9452.22265625,
"learning_rate": 2.978813559322034e-05,
"loss": 0.0651,
"step": 578
},
{
"epoch": 4.5234375,
"grad_norm": 9685.53515625,
"learning_rate": 2.9745762711864407e-05,
"loss": 0.0557,
"step": 579
},
{
"epoch": 4.53125,
"grad_norm": 7954.357421875,
"learning_rate": 2.9703389830508477e-05,
"loss": 0.0499,
"step": 580
},
{
"epoch": 4.5390625,
"grad_norm": 8031.22119140625,
"learning_rate": 2.9661016949152544e-05,
"loss": 0.0603,
"step": 581
},
{
"epoch": 4.546875,
"grad_norm": 10197.0224609375,
"learning_rate": 2.9618644067796614e-05,
"loss": 0.05,
"step": 582
},
{
"epoch": 4.5546875,
"grad_norm": 12842.6337890625,
"learning_rate": 2.957627118644068e-05,
"loss": 0.0459,
"step": 583
},
{
"epoch": 4.5625,
"grad_norm": 9085.4296875,
"learning_rate": 2.9533898305084743e-05,
"loss": 0.0609,
"step": 584
},
{
"epoch": 4.5703125,
"grad_norm": 7889.96630859375,
"learning_rate": 2.9491525423728817e-05,
"loss": 0.0484,
"step": 585
},
{
"epoch": 4.578125,
"grad_norm": 6084.1796875,
"learning_rate": 2.9449152542372883e-05,
"loss": 0.0625,
"step": 586
},
{
"epoch": 4.5859375,
"grad_norm": 11349.4296875,
"learning_rate": 2.9406779661016953e-05,
"loss": 0.0535,
"step": 587
},
{
"epoch": 4.59375,
"grad_norm": 9899.328125,
"learning_rate": 2.936440677966102e-05,
"loss": 0.0579,
"step": 588
},
{
"epoch": 4.6015625,
"grad_norm": 13367.9375,
"learning_rate": 2.9322033898305083e-05,
"loss": 0.0614,
"step": 589
},
{
"epoch": 4.609375,
"grad_norm": 7354.994140625,
"learning_rate": 2.9279661016949157e-05,
"loss": 0.0437,
"step": 590
},
{
"epoch": 4.6171875,
"grad_norm": 9090.298828125,
"learning_rate": 2.9237288135593223e-05,
"loss": 0.0634,
"step": 591
},
{
"epoch": 4.625,
"grad_norm": 11121.28125,
"learning_rate": 2.9194915254237286e-05,
"loss": 0.0529,
"step": 592
},
{
"epoch": 4.6328125,
"grad_norm": 9071.9384765625,
"learning_rate": 2.915254237288136e-05,
"loss": 0.059,
"step": 593
},
{
"epoch": 4.640625,
"grad_norm": 6547.1884765625,
"learning_rate": 2.9110169491525423e-05,
"loss": 0.0503,
"step": 594
},
{
"epoch": 4.6484375,
"grad_norm": 7094.24365234375,
"learning_rate": 2.9067796610169496e-05,
"loss": 0.0533,
"step": 595
},
{
"epoch": 4.65625,
"grad_norm": 5315.11669921875,
"learning_rate": 2.902542372881356e-05,
"loss": 0.036,
"step": 596
},
{
"epoch": 4.6640625,
"grad_norm": 9332.365234375,
"learning_rate": 2.8983050847457626e-05,
"loss": 0.0672,
"step": 597
},
{
"epoch": 4.671875,
"grad_norm": 12868.32421875,
"learning_rate": 2.89406779661017e-05,
"loss": 0.0469,
"step": 598
},
{
"epoch": 4.6796875,
"grad_norm": 12030.3310546875,
"learning_rate": 2.8898305084745763e-05,
"loss": 0.0564,
"step": 599
},
{
"epoch": 4.6875,
"grad_norm": 9086.708984375,
"learning_rate": 2.885593220338983e-05,
"loss": 0.0598,
"step": 600
},
{
"epoch": 4.6953125,
"grad_norm": 9511.6328125,
"learning_rate": 2.88135593220339e-05,
"loss": 0.072,
"step": 601
},
{
"epoch": 4.703125,
"grad_norm": 7827.6875,
"learning_rate": 2.8771186440677966e-05,
"loss": 0.0586,
"step": 602
},
{
"epoch": 4.7109375,
"grad_norm": 11183.3955078125,
"learning_rate": 2.8728813559322036e-05,
"loss": 0.051,
"step": 603
},
{
"epoch": 4.71875,
"grad_norm": 18373.349609375,
"learning_rate": 2.8686440677966102e-05,
"loss": 0.0759,
"step": 604
},
{
"epoch": 4.7265625,
"grad_norm": 10613.033203125,
"learning_rate": 2.864406779661017e-05,
"loss": 0.0477,
"step": 605
},
{
"epoch": 4.734375,
"grad_norm": 8308.37890625,
"learning_rate": 2.860169491525424e-05,
"loss": 0.0524,
"step": 606
},
{
"epoch": 4.7421875,
"grad_norm": 8757.744140625,
"learning_rate": 2.8559322033898306e-05,
"loss": 0.0484,
"step": 607
},
{
"epoch": 4.75,
"grad_norm": 7603.671875,
"learning_rate": 2.8516949152542372e-05,
"loss": 0.0622,
"step": 608
},
{
"epoch": 4.7578125,
"grad_norm": 7253.7578125,
"learning_rate": 2.8474576271186442e-05,
"loss": 0.0472,
"step": 609
},
{
"epoch": 4.765625,
"grad_norm": 10971.4189453125,
"learning_rate": 2.843220338983051e-05,
"loss": 0.0518,
"step": 610
},
{
"epoch": 4.7734375,
"grad_norm": 8221.505859375,
"learning_rate": 2.838983050847458e-05,
"loss": 0.0542,
"step": 611
},
{
"epoch": 4.78125,
"grad_norm": 7676.4375,
"learning_rate": 2.8347457627118645e-05,
"loss": 0.0515,
"step": 612
},
{
"epoch": 4.7890625,
"grad_norm": 10376.1416015625,
"learning_rate": 2.8305084745762712e-05,
"loss": 0.0554,
"step": 613
},
{
"epoch": 4.796875,
"grad_norm": 8190.84716796875,
"learning_rate": 2.8262711864406782e-05,
"loss": 0.0513,
"step": 614
},
{
"epoch": 4.8046875,
"grad_norm": 10305.0771484375,
"learning_rate": 2.822033898305085e-05,
"loss": 0.0447,
"step": 615
},
{
"epoch": 4.8125,
"grad_norm": 6549.70703125,
"learning_rate": 2.817796610169492e-05,
"loss": 0.0415,
"step": 616
},
{
"epoch": 4.8203125,
"grad_norm": 6613.16162109375,
"learning_rate": 2.8135593220338985e-05,
"loss": 0.0438,
"step": 617
},
{
"epoch": 4.828125,
"grad_norm": 6645.7216796875,
"learning_rate": 2.8093220338983052e-05,
"loss": 0.0503,
"step": 618
},
{
"epoch": 4.8359375,
"grad_norm": 8451.93359375,
"learning_rate": 2.8050847457627122e-05,
"loss": 0.0563,
"step": 619
},
{
"epoch": 4.84375,
"grad_norm": 8280.98828125,
"learning_rate": 2.8008474576271188e-05,
"loss": 0.06,
"step": 620
},
{
"epoch": 4.8515625,
"grad_norm": 12635.70703125,
"learning_rate": 2.7966101694915255e-05,
"loss": 0.0542,
"step": 621
},
{
"epoch": 4.859375,
"grad_norm": 6301.15087890625,
"learning_rate": 2.7923728813559325e-05,
"loss": 0.0435,
"step": 622
},
{
"epoch": 4.8671875,
"grad_norm": 11142.12890625,
"learning_rate": 2.788135593220339e-05,
"loss": 0.0607,
"step": 623
},
{
"epoch": 4.875,
"grad_norm": 8378.48046875,
"learning_rate": 2.783898305084746e-05,
"loss": 0.0534,
"step": 624
},
{
"epoch": 4.8828125,
"grad_norm": 9150.828125,
"learning_rate": 2.7796610169491528e-05,
"loss": 0.0552,
"step": 625
},
{
"epoch": 4.890625,
"grad_norm": 9330.259765625,
"learning_rate": 2.775423728813559e-05,
"loss": 0.0561,
"step": 626
},
{
"epoch": 4.8984375,
"grad_norm": 9137.9404296875,
"learning_rate": 2.7711864406779665e-05,
"loss": 0.056,
"step": 627
},
{
"epoch": 4.90625,
"grad_norm": 8682.009765625,
"learning_rate": 2.766949152542373e-05,
"loss": 0.0532,
"step": 628
},
{
"epoch": 4.9140625,
"grad_norm": 8534.43359375,
"learning_rate": 2.7627118644067794e-05,
"loss": 0.0505,
"step": 629
},
{
"epoch": 4.921875,
"grad_norm": 10386.4072265625,
"learning_rate": 2.7584745762711868e-05,
"loss": 0.0548,
"step": 630
},
{
"epoch": 4.9296875,
"grad_norm": 7624.96728515625,
"learning_rate": 2.754237288135593e-05,
"loss": 0.0447,
"step": 631
},
{
"epoch": 4.9375,
"grad_norm": 7019.66162109375,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0542,
"step": 632
},
{
"epoch": 4.9453125,
"grad_norm": 9105.5400390625,
"learning_rate": 2.7457627118644068e-05,
"loss": 0.0519,
"step": 633
},
{
"epoch": 4.953125,
"grad_norm": 9408.3857421875,
"learning_rate": 2.7415254237288134e-05,
"loss": 0.0603,
"step": 634
},
{
"epoch": 4.9609375,
"grad_norm": 10687.482421875,
"learning_rate": 2.7372881355932208e-05,
"loss": 0.0554,
"step": 635
},
{
"epoch": 4.96875,
"grad_norm": 10231.705078125,
"learning_rate": 2.733050847457627e-05,
"loss": 0.07,
"step": 636
},
{
"epoch": 4.9765625,
"grad_norm": 7169.52490234375,
"learning_rate": 2.7288135593220337e-05,
"loss": 0.0407,
"step": 637
},
{
"epoch": 4.984375,
"grad_norm": 7169.38134765625,
"learning_rate": 2.7245762711864407e-05,
"loss": 0.0455,
"step": 638
},
{
"epoch": 4.9921875,
"grad_norm": 10786.70703125,
"learning_rate": 2.7203389830508474e-05,
"loss": 0.0593,
"step": 639
},
{
"epoch": 5.0,
"grad_norm": 9401.41015625,
"learning_rate": 2.7161016949152547e-05,
"loss": 0.0517,
"step": 640
},
{
"epoch": 5.0,
"eval_f1_macro": 0.4221225113393924,
"eval_f1_micro": 0.7177304964539007,
"eval_loss": 0.051938652992248535,
"eval_precision": 0.8815331010452961,
"eval_recall": 0.6052631578947368,
"eval_runtime": 0.9584,
"eval_samples_per_second": 356.854,
"eval_steps_per_second": 15.651,
"step": 640
},
{
"epoch": 5.0078125,
"grad_norm": 8301.05078125,
"learning_rate": 2.711864406779661e-05,
"loss": 0.051,
"step": 641
},
{
"epoch": 5.015625,
"grad_norm": 9765.9306640625,
"learning_rate": 2.7076271186440677e-05,
"loss": 0.0572,
"step": 642
},
{
"epoch": 5.0234375,
"grad_norm": 8120.72607421875,
"learning_rate": 2.7033898305084747e-05,
"loss": 0.0408,
"step": 643
},
{
"epoch": 5.03125,
"grad_norm": 8007.16015625,
"learning_rate": 2.6991525423728814e-05,
"loss": 0.0496,
"step": 644
},
{
"epoch": 5.0390625,
"grad_norm": 8338.7060546875,
"learning_rate": 2.6949152542372884e-05,
"loss": 0.0509,
"step": 645
},
{
"epoch": 5.046875,
"grad_norm": 8752.2216796875,
"learning_rate": 2.690677966101695e-05,
"loss": 0.0463,
"step": 646
},
{
"epoch": 5.0546875,
"grad_norm": 6075.150390625,
"learning_rate": 2.6864406779661017e-05,
"loss": 0.0464,
"step": 647
},
{
"epoch": 5.0625,
"grad_norm": 10957.205078125,
"learning_rate": 2.6822033898305087e-05,
"loss": 0.0473,
"step": 648
},
{
"epoch": 5.0703125,
"grad_norm": 7418.18896484375,
"learning_rate": 2.6779661016949153e-05,
"loss": 0.0481,
"step": 649
},
{
"epoch": 5.078125,
"grad_norm": 10034.28515625,
"learning_rate": 2.673728813559322e-05,
"loss": 0.0581,
"step": 650
},
{
"epoch": 5.0859375,
"grad_norm": 5875.8017578125,
"learning_rate": 2.669491525423729e-05,
"loss": 0.0345,
"step": 651
},
{
"epoch": 5.09375,
"grad_norm": 8718.865234375,
"learning_rate": 2.6652542372881357e-05,
"loss": 0.0647,
"step": 652
},
{
"epoch": 5.1015625,
"grad_norm": 10030.1826171875,
"learning_rate": 2.6610169491525427e-05,
"loss": 0.0602,
"step": 653
},
{
"epoch": 5.109375,
"grad_norm": 5996.3193359375,
"learning_rate": 2.6567796610169493e-05,
"loss": 0.0436,
"step": 654
},
{
"epoch": 5.1171875,
"grad_norm": 6315.1669921875,
"learning_rate": 2.652542372881356e-05,
"loss": 0.0466,
"step": 655
},
{
"epoch": 5.125,
"grad_norm": 8698.6689453125,
"learning_rate": 2.648305084745763e-05,
"loss": 0.0597,
"step": 656
},
{
"epoch": 5.1328125,
"grad_norm": 10581.140625,
"learning_rate": 2.6440677966101696e-05,
"loss": 0.0481,
"step": 657
},
{
"epoch": 5.140625,
"grad_norm": 6633.81298828125,
"learning_rate": 2.6398305084745763e-05,
"loss": 0.0374,
"step": 658
},
{
"epoch": 5.1484375,
"grad_norm": 7837.68310546875,
"learning_rate": 2.6355932203389833e-05,
"loss": 0.0559,
"step": 659
},
{
"epoch": 5.15625,
"grad_norm": 7419.39599609375,
"learning_rate": 2.63135593220339e-05,
"loss": 0.0449,
"step": 660
},
{
"epoch": 5.1640625,
"grad_norm": 7005.61279296875,
"learning_rate": 2.627118644067797e-05,
"loss": 0.0437,
"step": 661
},
{
"epoch": 5.171875,
"grad_norm": 6599.4482421875,
"learning_rate": 2.6228813559322036e-05,
"loss": 0.0413,
"step": 662
},
{
"epoch": 5.1796875,
"grad_norm": 5710.912109375,
"learning_rate": 2.61864406779661e-05,
"loss": 0.0371,
"step": 663
},
{
"epoch": 5.1875,
"grad_norm": 6884.81298828125,
"learning_rate": 2.6144067796610173e-05,
"loss": 0.0548,
"step": 664
},
{
"epoch": 5.1953125,
"grad_norm": 6289.5986328125,
"learning_rate": 2.610169491525424e-05,
"loss": 0.0417,
"step": 665
},
{
"epoch": 5.203125,
"grad_norm": 6601.28759765625,
"learning_rate": 2.605932203389831e-05,
"loss": 0.0398,
"step": 666
},
{
"epoch": 5.2109375,
"grad_norm": 10250.0205078125,
"learning_rate": 2.6016949152542376e-05,
"loss": 0.0422,
"step": 667
},
{
"epoch": 5.21875,
"grad_norm": 9905.0751953125,
"learning_rate": 2.597457627118644e-05,
"loss": 0.0596,
"step": 668
},
{
"epoch": 5.2265625,
"grad_norm": 5716.935546875,
"learning_rate": 2.5932203389830512e-05,
"loss": 0.0344,
"step": 669
},
{
"epoch": 5.234375,
"grad_norm": 7819.662109375,
"learning_rate": 2.588983050847458e-05,
"loss": 0.0528,
"step": 670
},
{
"epoch": 5.2421875,
"grad_norm": 8608.111328125,
"learning_rate": 2.5847457627118642e-05,
"loss": 0.0548,
"step": 671
},
{
"epoch": 5.25,
"grad_norm": 7235.7646484375,
"learning_rate": 2.5805084745762716e-05,
"loss": 0.0515,
"step": 672
},
{
"epoch": 5.2578125,
"grad_norm": 10493.30078125,
"learning_rate": 2.576271186440678e-05,
"loss": 0.0477,
"step": 673
},
{
"epoch": 5.265625,
"grad_norm": 8957.4140625,
"learning_rate": 2.5720338983050852e-05,
"loss": 0.0393,
"step": 674
},
{
"epoch": 5.2734375,
"grad_norm": 10166.033203125,
"learning_rate": 2.5677966101694915e-05,
"loss": 0.0466,
"step": 675
},
{
"epoch": 5.28125,
"grad_norm": 6986.44677734375,
"learning_rate": 2.5635593220338982e-05,
"loss": 0.0377,
"step": 676
},
{
"epoch": 5.2890625,
"grad_norm": 8484.8662109375,
"learning_rate": 2.5593220338983055e-05,
"loss": 0.0524,
"step": 677
},
{
"epoch": 5.296875,
"grad_norm": 6796.80126953125,
"learning_rate": 2.555084745762712e-05,
"loss": 0.0432,
"step": 678
},
{
"epoch": 5.3046875,
"grad_norm": 8737.033203125,
"learning_rate": 2.5508474576271185e-05,
"loss": 0.0365,
"step": 679
},
{
"epoch": 5.3125,
"grad_norm": 8511.1533203125,
"learning_rate": 2.5466101694915255e-05,
"loss": 0.053,
"step": 680
},
{
"epoch": 5.3203125,
"grad_norm": 7522.27685546875,
"learning_rate": 2.5423728813559322e-05,
"loss": 0.0478,
"step": 681
},
{
"epoch": 5.328125,
"grad_norm": 5846.4140625,
"learning_rate": 2.538135593220339e-05,
"loss": 0.0355,
"step": 682
},
{
"epoch": 5.3359375,
"grad_norm": 5238.078125,
"learning_rate": 2.5338983050847458e-05,
"loss": 0.0338,
"step": 683
},
{
"epoch": 5.34375,
"grad_norm": 7361.98974609375,
"learning_rate": 2.5296610169491525e-05,
"loss": 0.0427,
"step": 684
},
{
"epoch": 5.3515625,
"grad_norm": 10141.0849609375,
"learning_rate": 2.5254237288135595e-05,
"loss": 0.0345,
"step": 685
},
{
"epoch": 5.359375,
"grad_norm": 7265.44384765625,
"learning_rate": 2.521186440677966e-05,
"loss": 0.0457,
"step": 686
},
{
"epoch": 5.3671875,
"grad_norm": 11025.0888671875,
"learning_rate": 2.5169491525423728e-05,
"loss": 0.0506,
"step": 687
},
{
"epoch": 5.375,
"grad_norm": 6839.9521484375,
"learning_rate": 2.5127118644067798e-05,
"loss": 0.0503,
"step": 688
},
{
"epoch": 5.3828125,
"grad_norm": 7332.271484375,
"learning_rate": 2.5084745762711865e-05,
"loss": 0.0556,
"step": 689
},
{
"epoch": 5.390625,
"grad_norm": 6450.46484375,
"learning_rate": 2.5042372881355935e-05,
"loss": 0.0391,
"step": 690
},
{
"epoch": 5.3984375,
"grad_norm": 6263.70703125,
"learning_rate": 2.5e-05,
"loss": 0.044,
"step": 691
},
{
"epoch": 5.40625,
"grad_norm": 8939.21484375,
"learning_rate": 2.495762711864407e-05,
"loss": 0.0549,
"step": 692
},
{
"epoch": 5.4140625,
"grad_norm": 7050.35302734375,
"learning_rate": 2.4915254237288138e-05,
"loss": 0.0368,
"step": 693
},
{
"epoch": 5.421875,
"grad_norm": 6592.341796875,
"learning_rate": 2.4872881355932204e-05,
"loss": 0.0344,
"step": 694
},
{
"epoch": 5.4296875,
"grad_norm": 7646.71142578125,
"learning_rate": 2.483050847457627e-05,
"loss": 0.0534,
"step": 695
},
{
"epoch": 5.4375,
"grad_norm": 6838.74853515625,
"learning_rate": 2.478813559322034e-05,
"loss": 0.0398,
"step": 696
},
{
"epoch": 5.4453125,
"grad_norm": 6312.92138671875,
"learning_rate": 2.4745762711864408e-05,
"loss": 0.0453,
"step": 697
},
{
"epoch": 5.453125,
"grad_norm": 7989.7763671875,
"learning_rate": 2.4703389830508474e-05,
"loss": 0.043,
"step": 698
},
{
"epoch": 5.4609375,
"grad_norm": 8529.10546875,
"learning_rate": 2.4661016949152544e-05,
"loss": 0.0481,
"step": 699
},
{
"epoch": 5.46875,
"grad_norm": 7755.81298828125,
"learning_rate": 2.461864406779661e-05,
"loss": 0.045,
"step": 700
},
{
"epoch": 5.4765625,
"grad_norm": 11920.576171875,
"learning_rate": 2.457627118644068e-05,
"loss": 0.046,
"step": 701
},
{
"epoch": 5.484375,
"grad_norm": 5322.46728515625,
"learning_rate": 2.4533898305084747e-05,
"loss": 0.0385,
"step": 702
},
{
"epoch": 5.4921875,
"grad_norm": 8184.45654296875,
"learning_rate": 2.4491525423728814e-05,
"loss": 0.0546,
"step": 703
},
{
"epoch": 5.5,
"grad_norm": 7862.18994140625,
"learning_rate": 2.4449152542372884e-05,
"loss": 0.045,
"step": 704
},
{
"epoch": 5.5078125,
"grad_norm": 8704.5751953125,
"learning_rate": 2.440677966101695e-05,
"loss": 0.0428,
"step": 705
},
{
"epoch": 5.515625,
"grad_norm": 8961.3251953125,
"learning_rate": 2.4364406779661017e-05,
"loss": 0.0432,
"step": 706
},
{
"epoch": 5.5234375,
"grad_norm": 6205.46728515625,
"learning_rate": 2.4322033898305087e-05,
"loss": 0.0442,
"step": 707
},
{
"epoch": 5.53125,
"grad_norm": 10107.7392578125,
"learning_rate": 2.4279661016949154e-05,
"loss": 0.0381,
"step": 708
},
{
"epoch": 5.5390625,
"grad_norm": 11671.6103515625,
"learning_rate": 2.4237288135593224e-05,
"loss": 0.059,
"step": 709
},
{
"epoch": 5.546875,
"grad_norm": 6803.935546875,
"learning_rate": 2.4194915254237287e-05,
"loss": 0.0438,
"step": 710
},
{
"epoch": 5.5546875,
"grad_norm": 7092.56884765625,
"learning_rate": 2.4152542372881357e-05,
"loss": 0.0385,
"step": 711
},
{
"epoch": 5.5625,
"grad_norm": 6236.2333984375,
"learning_rate": 2.4110169491525423e-05,
"loss": 0.0448,
"step": 712
},
{
"epoch": 5.5703125,
"grad_norm": 6901.10986328125,
"learning_rate": 2.4067796610169493e-05,
"loss": 0.0349,
"step": 713
},
{
"epoch": 5.578125,
"grad_norm": 6055.93359375,
"learning_rate": 2.402542372881356e-05,
"loss": 0.0394,
"step": 714
},
{
"epoch": 5.5859375,
"grad_norm": 10082.9091796875,
"learning_rate": 2.3983050847457627e-05,
"loss": 0.0499,
"step": 715
},
{
"epoch": 5.59375,
"grad_norm": 7922.22607421875,
"learning_rate": 2.3940677966101697e-05,
"loss": 0.0484,
"step": 716
},
{
"epoch": 5.6015625,
"grad_norm": 7357.60791015625,
"learning_rate": 2.3898305084745763e-05,
"loss": 0.0394,
"step": 717
},
{
"epoch": 5.609375,
"grad_norm": 6069.3720703125,
"learning_rate": 2.3855932203389833e-05,
"loss": 0.0336,
"step": 718
},
{
"epoch": 5.6171875,
"grad_norm": 7310.486328125,
"learning_rate": 2.38135593220339e-05,
"loss": 0.0387,
"step": 719
},
{
"epoch": 5.625,
"grad_norm": 9625.2333984375,
"learning_rate": 2.3771186440677966e-05,
"loss": 0.0477,
"step": 720
},
{
"epoch": 5.6328125,
"grad_norm": 7902.58984375,
"learning_rate": 2.3728813559322036e-05,
"loss": 0.0437,
"step": 721
},
{
"epoch": 5.640625,
"grad_norm": 5631.72412109375,
"learning_rate": 2.3686440677966103e-05,
"loss": 0.0392,
"step": 722
},
{
"epoch": 5.6484375,
"grad_norm": 7505.671875,
"learning_rate": 2.364406779661017e-05,
"loss": 0.0391,
"step": 723
},
{
"epoch": 5.65625,
"grad_norm": 7038.07763671875,
"learning_rate": 2.360169491525424e-05,
"loss": 0.0326,
"step": 724
},
{
"epoch": 5.6640625,
"grad_norm": 6705.578125,
"learning_rate": 2.3559322033898306e-05,
"loss": 0.0531,
"step": 725
},
{
"epoch": 5.671875,
"grad_norm": 7321.1640625,
"learning_rate": 2.3516949152542376e-05,
"loss": 0.0547,
"step": 726
},
{
"epoch": 5.6796875,
"grad_norm": 7575.568359375,
"learning_rate": 2.347457627118644e-05,
"loss": 0.038,
"step": 727
},
{
"epoch": 5.6875,
"grad_norm": 7480.619140625,
"learning_rate": 2.343220338983051e-05,
"loss": 0.0401,
"step": 728
},
{
"epoch": 5.6953125,
"grad_norm": 8098.4912109375,
"learning_rate": 2.338983050847458e-05,
"loss": 0.0377,
"step": 729
},
{
"epoch": 5.703125,
"grad_norm": 7198.10693359375,
"learning_rate": 2.3347457627118646e-05,
"loss": 0.0339,
"step": 730
},
{
"epoch": 5.7109375,
"grad_norm": 8510.83203125,
"learning_rate": 2.3305084745762712e-05,
"loss": 0.0403,
"step": 731
},
{
"epoch": 5.71875,
"grad_norm": 7569.01171875,
"learning_rate": 2.326271186440678e-05,
"loss": 0.0434,
"step": 732
},
{
"epoch": 5.7265625,
"grad_norm": 8294.7841796875,
"learning_rate": 2.322033898305085e-05,
"loss": 0.0367,
"step": 733
},
{
"epoch": 5.734375,
"grad_norm": 7746.98583984375,
"learning_rate": 2.317796610169492e-05,
"loss": 0.036,
"step": 734
},
{
"epoch": 5.7421875,
"grad_norm": 5573.05419921875,
"learning_rate": 2.3135593220338982e-05,
"loss": 0.0359,
"step": 735
},
{
"epoch": 5.75,
"grad_norm": 9092.48828125,
"learning_rate": 2.3093220338983052e-05,
"loss": 0.0347,
"step": 736
},
{
"epoch": 5.7578125,
"grad_norm": 8884.451171875,
"learning_rate": 2.305084745762712e-05,
"loss": 0.0443,
"step": 737
},
{
"epoch": 5.765625,
"grad_norm": 10255.2578125,
"learning_rate": 2.300847457627119e-05,
"loss": 0.0501,
"step": 738
},
{
"epoch": 5.7734375,
"grad_norm": 8139.00634765625,
"learning_rate": 2.2966101694915255e-05,
"loss": 0.0414,
"step": 739
},
{
"epoch": 5.78125,
"grad_norm": 7265.35302734375,
"learning_rate": 2.2923728813559322e-05,
"loss": 0.0327,
"step": 740
},
{
"epoch": 5.7890625,
"grad_norm": 10017.8955078125,
"learning_rate": 2.2881355932203392e-05,
"loss": 0.0509,
"step": 741
},
{
"epoch": 5.796875,
"grad_norm": 11049.427734375,
"learning_rate": 2.283898305084746e-05,
"loss": 0.0441,
"step": 742
},
{
"epoch": 5.8046875,
"grad_norm": 7237.79541015625,
"learning_rate": 2.2796610169491525e-05,
"loss": 0.0519,
"step": 743
},
{
"epoch": 5.8125,
"grad_norm": 13909.09765625,
"learning_rate": 2.2754237288135595e-05,
"loss": 0.0599,
"step": 744
},
{
"epoch": 5.8203125,
"grad_norm": 10629.5556640625,
"learning_rate": 2.271186440677966e-05,
"loss": 0.0671,
"step": 745
},
{
"epoch": 5.828125,
"grad_norm": 6558.1728515625,
"learning_rate": 2.266949152542373e-05,
"loss": 0.0472,
"step": 746
},
{
"epoch": 5.8359375,
"grad_norm": 9295.50390625,
"learning_rate": 2.2627118644067798e-05,
"loss": 0.0444,
"step": 747
},
{
"epoch": 5.84375,
"grad_norm": 10433.88671875,
"learning_rate": 2.2584745762711865e-05,
"loss": 0.0526,
"step": 748
},
{
"epoch": 5.8515625,
"grad_norm": 6356.17333984375,
"learning_rate": 2.2542372881355935e-05,
"loss": 0.0312,
"step": 749
},
{
"epoch": 5.859375,
"grad_norm": 12547.232421875,
"learning_rate": 2.25e-05,
"loss": 0.0552,
"step": 750
},
{
"epoch": 5.8671875,
"grad_norm": 5786.74609375,
"learning_rate": 2.245762711864407e-05,
"loss": 0.0372,
"step": 751
},
{
"epoch": 5.875,
"grad_norm": 9362.380859375,
"learning_rate": 2.2415254237288135e-05,
"loss": 0.0585,
"step": 752
},
{
"epoch": 5.8828125,
"grad_norm": 7418.009765625,
"learning_rate": 2.2372881355932205e-05,
"loss": 0.0426,
"step": 753
},
{
"epoch": 5.890625,
"grad_norm": 6602.6162109375,
"learning_rate": 2.233050847457627e-05,
"loss": 0.0417,
"step": 754
},
{
"epoch": 5.8984375,
"grad_norm": 12380.49609375,
"learning_rate": 2.228813559322034e-05,
"loss": 0.0368,
"step": 755
},
{
"epoch": 5.90625,
"grad_norm": 9019.6376953125,
"learning_rate": 2.2245762711864408e-05,
"loss": 0.0334,
"step": 756
},
{
"epoch": 5.9140625,
"grad_norm": 8400.5634765625,
"learning_rate": 2.2203389830508474e-05,
"loss": 0.0413,
"step": 757
},
{
"epoch": 5.921875,
"grad_norm": 9092.2890625,
"learning_rate": 2.2161016949152544e-05,
"loss": 0.0536,
"step": 758
},
{
"epoch": 5.9296875,
"grad_norm": 10978.078125,
"learning_rate": 2.211864406779661e-05,
"loss": 0.0405,
"step": 759
},
{
"epoch": 5.9375,
"grad_norm": 8295.9755859375,
"learning_rate": 2.2076271186440678e-05,
"loss": 0.0378,
"step": 760
},
{
"epoch": 5.9453125,
"grad_norm": 10708.904296875,
"learning_rate": 2.2033898305084748e-05,
"loss": 0.04,
"step": 761
},
{
"epoch": 5.953125,
"grad_norm": 12049.2587890625,
"learning_rate": 2.1991525423728814e-05,
"loss": 0.0424,
"step": 762
},
{
"epoch": 5.9609375,
"grad_norm": 11605.8857421875,
"learning_rate": 2.1949152542372884e-05,
"loss": 0.064,
"step": 763
},
{
"epoch": 5.96875,
"grad_norm": 11222.7744140625,
"learning_rate": 2.190677966101695e-05,
"loss": 0.045,
"step": 764
},
{
"epoch": 5.9765625,
"grad_norm": 7078.74951171875,
"learning_rate": 2.1864406779661017e-05,
"loss": 0.0344,
"step": 765
},
{
"epoch": 5.984375,
"grad_norm": 6693.341796875,
"learning_rate": 2.1822033898305087e-05,
"loss": 0.0397,
"step": 766
},
{
"epoch": 5.9921875,
"grad_norm": 8009.3720703125,
"learning_rate": 2.1779661016949154e-05,
"loss": 0.0451,
"step": 767
},
{
"epoch": 6.0,
"grad_norm": 7511.54296875,
"learning_rate": 2.173728813559322e-05,
"loss": 0.0496,
"step": 768
},
{
"epoch": 6.0,
"eval_f1_macro": 0.5087589834800437,
"eval_f1_micro": 0.7603748326639893,
"eval_loss": 0.04617245867848396,
"eval_precision": 0.8632218844984803,
"eval_recall": 0.6794258373205742,
"eval_runtime": 0.9693,
"eval_samples_per_second": 352.841,
"eval_steps_per_second": 15.475,
"step": 768
},
{
"epoch": 6.0078125,
"grad_norm": 7750.53076171875,
"learning_rate": 2.1694915254237287e-05,
"loss": 0.042,
"step": 769
},
{
"epoch": 6.015625,
"grad_norm": 7804.34326171875,
"learning_rate": 2.1652542372881357e-05,
"loss": 0.0475,
"step": 770
},
{
"epoch": 6.0234375,
"grad_norm": 6684.17578125,
"learning_rate": 2.1610169491525427e-05,
"loss": 0.0363,
"step": 771
},
{
"epoch": 6.03125,
"grad_norm": 6000.5439453125,
"learning_rate": 2.1567796610169494e-05,
"loss": 0.033,
"step": 772
},
{
"epoch": 6.0390625,
"grad_norm": 5613.25146484375,
"learning_rate": 2.152542372881356e-05,
"loss": 0.036,
"step": 773
},
{
"epoch": 6.046875,
"grad_norm": 5963.81689453125,
"learning_rate": 2.1483050847457627e-05,
"loss": 0.0339,
"step": 774
},
{
"epoch": 6.0546875,
"grad_norm": 8401.326171875,
"learning_rate": 2.1440677966101697e-05,
"loss": 0.0474,
"step": 775
},
{
"epoch": 6.0625,
"grad_norm": 9630.81640625,
"learning_rate": 2.1398305084745763e-05,
"loss": 0.0472,
"step": 776
},
{
"epoch": 6.0703125,
"grad_norm": 7641.67431640625,
"learning_rate": 2.135593220338983e-05,
"loss": 0.0457,
"step": 777
},
{
"epoch": 6.078125,
"grad_norm": 5217.06689453125,
"learning_rate": 2.13135593220339e-05,
"loss": 0.0373,
"step": 778
},
{
"epoch": 6.0859375,
"grad_norm": 7327.80224609375,
"learning_rate": 2.1271186440677967e-05,
"loss": 0.0416,
"step": 779
},
{
"epoch": 6.09375,
"grad_norm": 7830.796875,
"learning_rate": 2.1228813559322037e-05,
"loss": 0.0387,
"step": 780
},
{
"epoch": 6.1015625,
"grad_norm": 8775.0126953125,
"learning_rate": 2.1186440677966103e-05,
"loss": 0.0446,
"step": 781
},
{
"epoch": 6.109375,
"grad_norm": 6372.89697265625,
"learning_rate": 2.114406779661017e-05,
"loss": 0.0466,
"step": 782
},
{
"epoch": 6.1171875,
"grad_norm": 8056.0166015625,
"learning_rate": 2.110169491525424e-05,
"loss": 0.037,
"step": 783
},
{
"epoch": 6.125,
"grad_norm": 5710.79150390625,
"learning_rate": 2.1059322033898306e-05,
"loss": 0.0316,
"step": 784
},
{
"epoch": 6.1328125,
"grad_norm": 6978.189453125,
"learning_rate": 2.1016949152542373e-05,
"loss": 0.0432,
"step": 785
},
{
"epoch": 6.140625,
"grad_norm": 6205.8505859375,
"learning_rate": 2.0974576271186443e-05,
"loss": 0.0365,
"step": 786
},
{
"epoch": 6.1484375,
"grad_norm": 7969.16015625,
"learning_rate": 2.093220338983051e-05,
"loss": 0.0362,
"step": 787
},
{
"epoch": 6.15625,
"grad_norm": 6783.23681640625,
"learning_rate": 2.088983050847458e-05,
"loss": 0.0506,
"step": 788
},
{
"epoch": 6.1640625,
"grad_norm": 6174.73486328125,
"learning_rate": 2.0847457627118643e-05,
"loss": 0.0358,
"step": 789
},
{
"epoch": 6.171875,
"grad_norm": 10219.9365234375,
"learning_rate": 2.0805084745762713e-05,
"loss": 0.046,
"step": 790
},
{
"epoch": 6.1796875,
"grad_norm": 9365.5498046875,
"learning_rate": 2.076271186440678e-05,
"loss": 0.0489,
"step": 791
},
{
"epoch": 6.1875,
"grad_norm": 7265.6875,
"learning_rate": 2.072033898305085e-05,
"loss": 0.0334,
"step": 792
},
{
"epoch": 6.1953125,
"grad_norm": 7976.56884765625,
"learning_rate": 2.0677966101694916e-05,
"loss": 0.0394,
"step": 793
},
{
"epoch": 6.203125,
"grad_norm": 7171.7578125,
"learning_rate": 2.0635593220338982e-05,
"loss": 0.0412,
"step": 794
},
{
"epoch": 6.2109375,
"grad_norm": 9302.0888671875,
"learning_rate": 2.0593220338983052e-05,
"loss": 0.0657,
"step": 795
},
{
"epoch": 6.21875,
"grad_norm": 9760.6728515625,
"learning_rate": 2.055084745762712e-05,
"loss": 0.042,
"step": 796
},
{
"epoch": 6.2265625,
"grad_norm": 5452.31787109375,
"learning_rate": 2.0508474576271186e-05,
"loss": 0.043,
"step": 797
},
{
"epoch": 6.234375,
"grad_norm": 8860.9453125,
"learning_rate": 2.0466101694915256e-05,
"loss": 0.0364,
"step": 798
},
{
"epoch": 6.2421875,
"grad_norm": 6308.78955078125,
"learning_rate": 2.0423728813559322e-05,
"loss": 0.0274,
"step": 799
},
{
"epoch": 6.25,
"grad_norm": 13957.2265625,
"learning_rate": 2.0381355932203392e-05,
"loss": 0.0529,
"step": 800
},
{
"epoch": 6.2578125,
"grad_norm": 6530.29052734375,
"learning_rate": 2.033898305084746e-05,
"loss": 0.028,
"step": 801
},
{
"epoch": 6.265625,
"grad_norm": 10696.5009765625,
"learning_rate": 2.0296610169491525e-05,
"loss": 0.0559,
"step": 802
},
{
"epoch": 6.2734375,
"grad_norm": 7625.404296875,
"learning_rate": 2.0254237288135595e-05,
"loss": 0.0493,
"step": 803
},
{
"epoch": 6.28125,
"grad_norm": 8953.2548828125,
"learning_rate": 2.0211864406779662e-05,
"loss": 0.0357,
"step": 804
},
{
"epoch": 6.2890625,
"grad_norm": 8335.3076171875,
"learning_rate": 2.0169491525423732e-05,
"loss": 0.0364,
"step": 805
},
{
"epoch": 6.296875,
"grad_norm": 7971.70654296875,
"learning_rate": 2.0127118644067795e-05,
"loss": 0.0393,
"step": 806
},
{
"epoch": 6.3046875,
"grad_norm": 7900.57177734375,
"learning_rate": 2.0084745762711865e-05,
"loss": 0.0489,
"step": 807
},
{
"epoch": 6.3125,
"grad_norm": 8629.1826171875,
"learning_rate": 2.0042372881355935e-05,
"loss": 0.0388,
"step": 808
},
{
"epoch": 6.3203125,
"grad_norm": 6643.5302734375,
"learning_rate": 2e-05,
"loss": 0.0305,
"step": 809
},
{
"epoch": 6.328125,
"grad_norm": 7594.80810546875,
"learning_rate": 1.9957627118644068e-05,
"loss": 0.0377,
"step": 810
},
{
"epoch": 6.3359375,
"grad_norm": 9676.9111328125,
"learning_rate": 1.9915254237288135e-05,
"loss": 0.0455,
"step": 811
},
{
"epoch": 6.34375,
"grad_norm": 5967.9375,
"learning_rate": 1.9872881355932205e-05,
"loss": 0.0368,
"step": 812
},
{
"epoch": 6.3515625,
"grad_norm": 8536.017578125,
"learning_rate": 1.9830508474576275e-05,
"loss": 0.0396,
"step": 813
},
{
"epoch": 6.359375,
"grad_norm": 8277.9189453125,
"learning_rate": 1.9788135593220338e-05,
"loss": 0.0419,
"step": 814
},
{
"epoch": 6.3671875,
"grad_norm": 10122.4619140625,
"learning_rate": 1.9745762711864408e-05,
"loss": 0.0355,
"step": 815
},
{
"epoch": 6.375,
"grad_norm": 4928.501953125,
"learning_rate": 1.9703389830508475e-05,
"loss": 0.0287,
"step": 816
},
{
"epoch": 6.3828125,
"grad_norm": 7002.77587890625,
"learning_rate": 1.9661016949152545e-05,
"loss": 0.0435,
"step": 817
},
{
"epoch": 6.390625,
"grad_norm": 8403.669921875,
"learning_rate": 1.961864406779661e-05,
"loss": 0.0343,
"step": 818
},
{
"epoch": 6.3984375,
"grad_norm": 4909.2958984375,
"learning_rate": 1.9576271186440678e-05,
"loss": 0.0355,
"step": 819
},
{
"epoch": 6.40625,
"grad_norm": 15611.5185546875,
"learning_rate": 1.9533898305084748e-05,
"loss": 0.0357,
"step": 820
},
{
"epoch": 6.4140625,
"grad_norm": 6846.7880859375,
"learning_rate": 1.9491525423728814e-05,
"loss": 0.0377,
"step": 821
},
{
"epoch": 6.421875,
"grad_norm": 6283.9580078125,
"learning_rate": 1.944915254237288e-05,
"loss": 0.0319,
"step": 822
},
{
"epoch": 6.4296875,
"grad_norm": 8701.087890625,
"learning_rate": 1.940677966101695e-05,
"loss": 0.0303,
"step": 823
},
{
"epoch": 6.4375,
"grad_norm": 9575.08203125,
"learning_rate": 1.9364406779661017e-05,
"loss": 0.0604,
"step": 824
},
{
"epoch": 6.4453125,
"grad_norm": 7263.29150390625,
"learning_rate": 1.9322033898305087e-05,
"loss": 0.0372,
"step": 825
},
{
"epoch": 6.453125,
"grad_norm": 10601.0947265625,
"learning_rate": 1.9279661016949154e-05,
"loss": 0.0441,
"step": 826
},
{
"epoch": 6.4609375,
"grad_norm": 4414.587890625,
"learning_rate": 1.923728813559322e-05,
"loss": 0.0288,
"step": 827
},
{
"epoch": 6.46875,
"grad_norm": 9007.638671875,
"learning_rate": 1.919491525423729e-05,
"loss": 0.0434,
"step": 828
},
{
"epoch": 6.4765625,
"grad_norm": 6824.4638671875,
"learning_rate": 1.9152542372881357e-05,
"loss": 0.036,
"step": 829
},
{
"epoch": 6.484375,
"grad_norm": 5217.1982421875,
"learning_rate": 1.9110169491525427e-05,
"loss": 0.0363,
"step": 830
},
{
"epoch": 6.4921875,
"grad_norm": 5962.2587890625,
"learning_rate": 1.906779661016949e-05,
"loss": 0.0347,
"step": 831
},
{
"epoch": 6.5,
"grad_norm": 7231.85107421875,
"learning_rate": 1.902542372881356e-05,
"loss": 0.0403,
"step": 832
},
{
"epoch": 6.5078125,
"grad_norm": 8758.6708984375,
"learning_rate": 1.8983050847457627e-05,
"loss": 0.0327,
"step": 833
},
{
"epoch": 6.515625,
"grad_norm": 7367.3974609375,
"learning_rate": 1.8940677966101697e-05,
"loss": 0.0401,
"step": 834
},
{
"epoch": 6.5234375,
"grad_norm": 7367.6279296875,
"learning_rate": 1.8898305084745764e-05,
"loss": 0.0366,
"step": 835
},
{
"epoch": 6.53125,
"grad_norm": 5156.99853515625,
"learning_rate": 1.885593220338983e-05,
"loss": 0.0317,
"step": 836
},
{
"epoch": 6.5390625,
"grad_norm": 8522.4619140625,
"learning_rate": 1.88135593220339e-05,
"loss": 0.035,
"step": 837
},
{
"epoch": 6.546875,
"grad_norm": 7059.3662109375,
"learning_rate": 1.8771186440677967e-05,
"loss": 0.0335,
"step": 838
},
{
"epoch": 6.5546875,
"grad_norm": 6692.23193359375,
"learning_rate": 1.8728813559322033e-05,
"loss": 0.0302,
"step": 839
},
{
"epoch": 6.5625,
"grad_norm": 5876.23193359375,
"learning_rate": 1.8686440677966103e-05,
"loss": 0.0313,
"step": 840
},
{
"epoch": 6.5703125,
"grad_norm": 10631.568359375,
"learning_rate": 1.864406779661017e-05,
"loss": 0.0352,
"step": 841
},
{
"epoch": 6.578125,
"grad_norm": 6270.96875,
"learning_rate": 1.860169491525424e-05,
"loss": 0.0271,
"step": 842
},
{
"epoch": 6.5859375,
"grad_norm": 6402.1103515625,
"learning_rate": 1.8559322033898307e-05,
"loss": 0.0435,
"step": 843
},
{
"epoch": 6.59375,
"grad_norm": 8916.91015625,
"learning_rate": 1.8516949152542373e-05,
"loss": 0.0426,
"step": 844
},
{
"epoch": 6.6015625,
"grad_norm": 7738.92919921875,
"learning_rate": 1.8474576271186443e-05,
"loss": 0.0387,
"step": 845
},
{
"epoch": 6.609375,
"grad_norm": 6624.61083984375,
"learning_rate": 1.843220338983051e-05,
"loss": 0.0357,
"step": 846
},
{
"epoch": 6.6171875,
"grad_norm": 6960.50146484375,
"learning_rate": 1.8389830508474576e-05,
"loss": 0.041,
"step": 847
},
{
"epoch": 6.625,
"grad_norm": 10229.4833984375,
"learning_rate": 1.8347457627118643e-05,
"loss": 0.0404,
"step": 848
},
{
"epoch": 6.6328125,
"grad_norm": 7144.75830078125,
"learning_rate": 1.8305084745762713e-05,
"loss": 0.0495,
"step": 849
},
{
"epoch": 6.640625,
"grad_norm": 7363.787109375,
"learning_rate": 1.8262711864406783e-05,
"loss": 0.0428,
"step": 850
},
{
"epoch": 6.6484375,
"grad_norm": 5557.26708984375,
"learning_rate": 1.8220338983050846e-05,
"loss": 0.0327,
"step": 851
},
{
"epoch": 6.65625,
"grad_norm": 9139.32421875,
"learning_rate": 1.8177966101694916e-05,
"loss": 0.0309,
"step": 852
},
{
"epoch": 6.6640625,
"grad_norm": 7102.10693359375,
"learning_rate": 1.8135593220338983e-05,
"loss": 0.031,
"step": 853
},
{
"epoch": 6.671875,
"grad_norm": 7712.4248046875,
"learning_rate": 1.8093220338983053e-05,
"loss": 0.0215,
"step": 854
},
{
"epoch": 6.6796875,
"grad_norm": 6690.7197265625,
"learning_rate": 1.805084745762712e-05,
"loss": 0.0298,
"step": 855
},
{
"epoch": 6.6875,
"grad_norm": 7487.84326171875,
"learning_rate": 1.8008474576271186e-05,
"loss": 0.0452,
"step": 856
},
{
"epoch": 6.6953125,
"grad_norm": 12249.931640625,
"learning_rate": 1.7966101694915256e-05,
"loss": 0.0454,
"step": 857
},
{
"epoch": 6.703125,
"grad_norm": 17868.73046875,
"learning_rate": 1.7923728813559322e-05,
"loss": 0.0476,
"step": 858
},
{
"epoch": 6.7109375,
"grad_norm": 5075.1953125,
"learning_rate": 1.7881355932203392e-05,
"loss": 0.0292,
"step": 859
},
{
"epoch": 6.71875,
"grad_norm": 13670.7783203125,
"learning_rate": 1.783898305084746e-05,
"loss": 0.0353,
"step": 860
},
{
"epoch": 6.7265625,
"grad_norm": 5678.1025390625,
"learning_rate": 1.7796610169491526e-05,
"loss": 0.0395,
"step": 861
},
{
"epoch": 6.734375,
"grad_norm": 10402.283203125,
"learning_rate": 1.7754237288135596e-05,
"loss": 0.044,
"step": 862
},
{
"epoch": 6.7421875,
"grad_norm": 8098.005859375,
"learning_rate": 1.7711864406779662e-05,
"loss": 0.0304,
"step": 863
},
{
"epoch": 6.75,
"grad_norm": 6548.56396484375,
"learning_rate": 1.766949152542373e-05,
"loss": 0.029,
"step": 864
},
{
"epoch": 6.7578125,
"grad_norm": 5388.458984375,
"learning_rate": 1.76271186440678e-05,
"loss": 0.0272,
"step": 865
},
{
"epoch": 6.765625,
"grad_norm": 10328.3486328125,
"learning_rate": 1.7584745762711865e-05,
"loss": 0.0387,
"step": 866
},
{
"epoch": 6.7734375,
"grad_norm": 6069.62744140625,
"learning_rate": 1.7542372881355935e-05,
"loss": 0.0328,
"step": 867
},
{
"epoch": 6.78125,
"grad_norm": 5153.02587890625,
"learning_rate": 1.75e-05,
"loss": 0.0292,
"step": 868
},
{
"epoch": 6.7890625,
"grad_norm": 8218.369140625,
"learning_rate": 1.745762711864407e-05,
"loss": 0.0338,
"step": 869
},
{
"epoch": 6.796875,
"grad_norm": 5088.0625,
"learning_rate": 1.7415254237288135e-05,
"loss": 0.0316,
"step": 870
},
{
"epoch": 6.8046875,
"grad_norm": 10896.08984375,
"learning_rate": 1.7372881355932205e-05,
"loss": 0.0482,
"step": 871
},
{
"epoch": 6.8125,
"grad_norm": 6145.6279296875,
"learning_rate": 1.733050847457627e-05,
"loss": 0.0363,
"step": 872
},
{
"epoch": 6.8203125,
"grad_norm": 6597.6533203125,
"learning_rate": 1.7288135593220338e-05,
"loss": 0.0402,
"step": 873
},
{
"epoch": 6.828125,
"grad_norm": 6152.89453125,
"learning_rate": 1.7245762711864408e-05,
"loss": 0.0388,
"step": 874
},
{
"epoch": 6.8359375,
"grad_norm": 5782.5703125,
"learning_rate": 1.7203389830508475e-05,
"loss": 0.0256,
"step": 875
},
{
"epoch": 6.84375,
"grad_norm": 11534.2890625,
"learning_rate": 1.716101694915254e-05,
"loss": 0.0425,
"step": 876
},
{
"epoch": 6.8515625,
"grad_norm": 7156.7080078125,
"learning_rate": 1.711864406779661e-05,
"loss": 0.028,
"step": 877
},
{
"epoch": 6.859375,
"grad_norm": 6310.9521484375,
"learning_rate": 1.7076271186440678e-05,
"loss": 0.0298,
"step": 878
},
{
"epoch": 6.8671875,
"grad_norm": 7145.35302734375,
"learning_rate": 1.7033898305084748e-05,
"loss": 0.0299,
"step": 879
},
{
"epoch": 6.875,
"grad_norm": 9907.32421875,
"learning_rate": 1.6991525423728815e-05,
"loss": 0.0364,
"step": 880
},
{
"epoch": 6.8828125,
"grad_norm": 7759.9658203125,
"learning_rate": 1.694915254237288e-05,
"loss": 0.0329,
"step": 881
},
{
"epoch": 6.890625,
"grad_norm": 11696.173828125,
"learning_rate": 1.690677966101695e-05,
"loss": 0.0341,
"step": 882
},
{
"epoch": 6.8984375,
"grad_norm": 10410.7724609375,
"learning_rate": 1.6864406779661018e-05,
"loss": 0.0354,
"step": 883
},
{
"epoch": 6.90625,
"grad_norm": 5017.21923828125,
"learning_rate": 1.6822033898305088e-05,
"loss": 0.0281,
"step": 884
},
{
"epoch": 6.9140625,
"grad_norm": 7809.46142578125,
"learning_rate": 1.677966101694915e-05,
"loss": 0.0281,
"step": 885
},
{
"epoch": 6.921875,
"grad_norm": 7975.55078125,
"learning_rate": 1.673728813559322e-05,
"loss": 0.0444,
"step": 886
},
{
"epoch": 6.9296875,
"grad_norm": 7357.98486328125,
"learning_rate": 1.669491525423729e-05,
"loss": 0.0329,
"step": 887
},
{
"epoch": 6.9375,
"grad_norm": 8290.84765625,
"learning_rate": 1.6652542372881357e-05,
"loss": 0.0304,
"step": 888
},
{
"epoch": 6.9453125,
"grad_norm": 5248.8701171875,
"learning_rate": 1.6610169491525424e-05,
"loss": 0.0341,
"step": 889
},
{
"epoch": 6.953125,
"grad_norm": 10679.189453125,
"learning_rate": 1.656779661016949e-05,
"loss": 0.0409,
"step": 890
},
{
"epoch": 6.9609375,
"grad_norm": 10320.708984375,
"learning_rate": 1.652542372881356e-05,
"loss": 0.035,
"step": 891
},
{
"epoch": 6.96875,
"grad_norm": 7708.0244140625,
"learning_rate": 1.648305084745763e-05,
"loss": 0.0284,
"step": 892
},
{
"epoch": 6.9765625,
"grad_norm": 5716.4599609375,
"learning_rate": 1.6440677966101694e-05,
"loss": 0.0299,
"step": 893
},
{
"epoch": 6.984375,
"grad_norm": 5226.2724609375,
"learning_rate": 1.6398305084745764e-05,
"loss": 0.0291,
"step": 894
},
{
"epoch": 6.9921875,
"grad_norm": 7574.9775390625,
"learning_rate": 1.635593220338983e-05,
"loss": 0.0381,
"step": 895
},
{
"epoch": 7.0,
"grad_norm": 5377.39990234375,
"learning_rate": 1.63135593220339e-05,
"loss": 0.0262,
"step": 896
},
{
"epoch": 7.0,
"eval_f1_macro": 0.5576800741730833,
"eval_f1_micro": 0.7813712807244502,
"eval_loss": 0.04291614890098572,
"eval_precision": 0.8507042253521127,
"eval_recall": 0.722488038277512,
"eval_runtime": 0.9574,
"eval_samples_per_second": 357.212,
"eval_steps_per_second": 15.667,
"step": 896
},
{
"epoch": 7.0078125,
"grad_norm": 5881.08447265625,
"learning_rate": 1.6271186440677967e-05,
"loss": 0.0283,
"step": 897
},
{
"epoch": 7.015625,
"grad_norm": 9107.8466796875,
"learning_rate": 1.6228813559322034e-05,
"loss": 0.045,
"step": 898
},
{
"epoch": 7.0234375,
"grad_norm": 5134.2958984375,
"learning_rate": 1.6186440677966104e-05,
"loss": 0.0316,
"step": 899
},
{
"epoch": 7.03125,
"grad_norm": 4676.7333984375,
"learning_rate": 1.614406779661017e-05,
"loss": 0.0274,
"step": 900
},
{
"epoch": 7.0390625,
"grad_norm": 11200.8291015625,
"learning_rate": 1.6101694915254237e-05,
"loss": 0.0305,
"step": 901
},
{
"epoch": 7.046875,
"grad_norm": 6205.8427734375,
"learning_rate": 1.6059322033898307e-05,
"loss": 0.0401,
"step": 902
},
{
"epoch": 7.0546875,
"grad_norm": 7047.4296875,
"learning_rate": 1.6016949152542373e-05,
"loss": 0.0303,
"step": 903
},
{
"epoch": 7.0625,
"grad_norm": 8133.98046875,
"learning_rate": 1.5974576271186443e-05,
"loss": 0.028,
"step": 904
},
{
"epoch": 7.0703125,
"grad_norm": 5041.7900390625,
"learning_rate": 1.5932203389830507e-05,
"loss": 0.0322,
"step": 905
},
{
"epoch": 7.078125,
"grad_norm": 5740.25,
"learning_rate": 1.5889830508474576e-05,
"loss": 0.0322,
"step": 906
},
{
"epoch": 7.0859375,
"grad_norm": 9796.6396484375,
"learning_rate": 1.5847457627118646e-05,
"loss": 0.0466,
"step": 907
},
{
"epoch": 7.09375,
"grad_norm": 5448.6396484375,
"learning_rate": 1.5805084745762713e-05,
"loss": 0.0314,
"step": 908
},
{
"epoch": 7.1015625,
"grad_norm": 6105.302734375,
"learning_rate": 1.5762711864406783e-05,
"loss": 0.0274,
"step": 909
},
{
"epoch": 7.109375,
"grad_norm": 12725.3544921875,
"learning_rate": 1.5720338983050846e-05,
"loss": 0.0424,
"step": 910
},
{
"epoch": 7.1171875,
"grad_norm": 6767.6123046875,
"learning_rate": 1.5677966101694916e-05,
"loss": 0.0333,
"step": 911
},
{
"epoch": 7.125,
"grad_norm": 4802.52587890625,
"learning_rate": 1.5635593220338983e-05,
"loss": 0.0235,
"step": 912
},
{
"epoch": 7.1328125,
"grad_norm": 7812.11474609375,
"learning_rate": 1.5593220338983053e-05,
"loss": 0.0327,
"step": 913
},
{
"epoch": 7.140625,
"grad_norm": 6049.68115234375,
"learning_rate": 1.555084745762712e-05,
"loss": 0.0328,
"step": 914
},
{
"epoch": 7.1484375,
"grad_norm": 5883.60546875,
"learning_rate": 1.5508474576271186e-05,
"loss": 0.0274,
"step": 915
},
{
"epoch": 7.15625,
"grad_norm": 7280.63671875,
"learning_rate": 1.5466101694915256e-05,
"loss": 0.0415,
"step": 916
},
{
"epoch": 7.1640625,
"grad_norm": 6676.4306640625,
"learning_rate": 1.5423728813559323e-05,
"loss": 0.0332,
"step": 917
},
{
"epoch": 7.171875,
"grad_norm": 4655.0341796875,
"learning_rate": 1.538135593220339e-05,
"loss": 0.0301,
"step": 918
},
{
"epoch": 7.1796875,
"grad_norm": 5075.13427734375,
"learning_rate": 1.533898305084746e-05,
"loss": 0.0336,
"step": 919
},
{
"epoch": 7.1875,
"grad_norm": 7564.26806640625,
"learning_rate": 1.5296610169491526e-05,
"loss": 0.0391,
"step": 920
},
{
"epoch": 7.1953125,
"grad_norm": 3422.302734375,
"learning_rate": 1.5254237288135596e-05,
"loss": 0.0192,
"step": 921
},
{
"epoch": 7.203125,
"grad_norm": 6189.4892578125,
"learning_rate": 1.521186440677966e-05,
"loss": 0.0298,
"step": 922
},
{
"epoch": 7.2109375,
"grad_norm": 7490.0703125,
"learning_rate": 1.5169491525423729e-05,
"loss": 0.032,
"step": 923
},
{
"epoch": 7.21875,
"grad_norm": 8305.1015625,
"learning_rate": 1.5127118644067797e-05,
"loss": 0.0309,
"step": 924
},
{
"epoch": 7.2265625,
"grad_norm": 4765.5146484375,
"learning_rate": 1.5084745762711865e-05,
"loss": 0.0259,
"step": 925
},
{
"epoch": 7.234375,
"grad_norm": 8681.189453125,
"learning_rate": 1.5042372881355932e-05,
"loss": 0.035,
"step": 926
},
{
"epoch": 7.2421875,
"grad_norm": 5264.79736328125,
"learning_rate": 1.5e-05,
"loss": 0.0378,
"step": 927
},
{
"epoch": 7.25,
"grad_norm": 7965.76025390625,
"learning_rate": 1.4957627118644069e-05,
"loss": 0.0431,
"step": 928
},
{
"epoch": 7.2578125,
"grad_norm": 5769.1474609375,
"learning_rate": 1.4915254237288137e-05,
"loss": 0.039,
"step": 929
},
{
"epoch": 7.265625,
"grad_norm": 7542.259765625,
"learning_rate": 1.4872881355932204e-05,
"loss": 0.0377,
"step": 930
},
{
"epoch": 7.2734375,
"grad_norm": 6779.00244140625,
"learning_rate": 1.4830508474576272e-05,
"loss": 0.0247,
"step": 931
},
{
"epoch": 7.28125,
"grad_norm": 5240.8720703125,
"learning_rate": 1.478813559322034e-05,
"loss": 0.0326,
"step": 932
},
{
"epoch": 7.2890625,
"grad_norm": 6682.4140625,
"learning_rate": 1.4745762711864408e-05,
"loss": 0.0354,
"step": 933
},
{
"epoch": 7.296875,
"grad_norm": 13012.0771484375,
"learning_rate": 1.4703389830508477e-05,
"loss": 0.0372,
"step": 934
},
{
"epoch": 7.3046875,
"grad_norm": 9186.1474609375,
"learning_rate": 1.4661016949152542e-05,
"loss": 0.0489,
"step": 935
},
{
"epoch": 7.3125,
"grad_norm": 6434.982421875,
"learning_rate": 1.4618644067796612e-05,
"loss": 0.0351,
"step": 936
},
{
"epoch": 7.3203125,
"grad_norm": 4910.662109375,
"learning_rate": 1.457627118644068e-05,
"loss": 0.0208,
"step": 937
},
{
"epoch": 7.328125,
"grad_norm": 6652.982421875,
"learning_rate": 1.4533898305084748e-05,
"loss": 0.0371,
"step": 938
},
{
"epoch": 7.3359375,
"grad_norm": 5904.052734375,
"learning_rate": 1.4491525423728813e-05,
"loss": 0.0303,
"step": 939
},
{
"epoch": 7.34375,
"grad_norm": 6480.48486328125,
"learning_rate": 1.4449152542372881e-05,
"loss": 0.0405,
"step": 940
},
{
"epoch": 7.3515625,
"grad_norm": 5383.20068359375,
"learning_rate": 1.440677966101695e-05,
"loss": 0.0291,
"step": 941
},
{
"epoch": 7.359375,
"grad_norm": 6930.58740234375,
"learning_rate": 1.4364406779661018e-05,
"loss": 0.0315,
"step": 942
},
{
"epoch": 7.3671875,
"grad_norm": 6401.66064453125,
"learning_rate": 1.4322033898305085e-05,
"loss": 0.0297,
"step": 943
},
{
"epoch": 7.375,
"grad_norm": 11917.96484375,
"learning_rate": 1.4279661016949153e-05,
"loss": 0.0477,
"step": 944
},
{
"epoch": 7.3828125,
"grad_norm": 5271.685546875,
"learning_rate": 1.4237288135593221e-05,
"loss": 0.038,
"step": 945
},
{
"epoch": 7.390625,
"grad_norm": 9209.56640625,
"learning_rate": 1.419491525423729e-05,
"loss": 0.0298,
"step": 946
},
{
"epoch": 7.3984375,
"grad_norm": 5938.71484375,
"learning_rate": 1.4152542372881356e-05,
"loss": 0.0278,
"step": 947
},
{
"epoch": 7.40625,
"grad_norm": 8900.69921875,
"learning_rate": 1.4110169491525424e-05,
"loss": 0.0374,
"step": 948
},
{
"epoch": 7.4140625,
"grad_norm": 9179.1240234375,
"learning_rate": 1.4067796610169493e-05,
"loss": 0.039,
"step": 949
},
{
"epoch": 7.421875,
"grad_norm": 5845.91943359375,
"learning_rate": 1.4025423728813561e-05,
"loss": 0.0256,
"step": 950
},
{
"epoch": 7.4296875,
"grad_norm": 5118.044921875,
"learning_rate": 1.3983050847457627e-05,
"loss": 0.0327,
"step": 951
},
{
"epoch": 7.4375,
"grad_norm": 5894.31640625,
"learning_rate": 1.3940677966101696e-05,
"loss": 0.0416,
"step": 952
},
{
"epoch": 7.4453125,
"grad_norm": 6184.0810546875,
"learning_rate": 1.3898305084745764e-05,
"loss": 0.0298,
"step": 953
},
{
"epoch": 7.453125,
"grad_norm": 4090.339599609375,
"learning_rate": 1.3855932203389832e-05,
"loss": 0.0244,
"step": 954
},
{
"epoch": 7.4609375,
"grad_norm": 5520.26513671875,
"learning_rate": 1.3813559322033897e-05,
"loss": 0.0346,
"step": 955
},
{
"epoch": 7.46875,
"grad_norm": 6052.70703125,
"learning_rate": 1.3771186440677965e-05,
"loss": 0.039,
"step": 956
},
{
"epoch": 7.4765625,
"grad_norm": 5298.1572265625,
"learning_rate": 1.3728813559322034e-05,
"loss": 0.0296,
"step": 957
},
{
"epoch": 7.484375,
"grad_norm": 5919.70458984375,
"learning_rate": 1.3686440677966104e-05,
"loss": 0.0319,
"step": 958
},
{
"epoch": 7.4921875,
"grad_norm": 8309.9970703125,
"learning_rate": 1.3644067796610169e-05,
"loss": 0.041,
"step": 959
},
{
"epoch": 7.5,
"grad_norm": 7968.78125,
"learning_rate": 1.3601694915254237e-05,
"loss": 0.0283,
"step": 960
},
{
"epoch": 7.5078125,
"grad_norm": 6181.9541015625,
"learning_rate": 1.3559322033898305e-05,
"loss": 0.0316,
"step": 961
},
{
"epoch": 7.515625,
"grad_norm": 11298.2685546875,
"learning_rate": 1.3516949152542374e-05,
"loss": 0.0371,
"step": 962
},
{
"epoch": 7.5234375,
"grad_norm": 5614.81494140625,
"learning_rate": 1.3474576271186442e-05,
"loss": 0.0249,
"step": 963
},
{
"epoch": 7.53125,
"grad_norm": 5778.6689453125,
"learning_rate": 1.3432203389830508e-05,
"loss": 0.0354,
"step": 964
},
{
"epoch": 7.5390625,
"grad_norm": 5912.9580078125,
"learning_rate": 1.3389830508474577e-05,
"loss": 0.0279,
"step": 965
},
{
"epoch": 7.546875,
"grad_norm": 6358.44970703125,
"learning_rate": 1.3347457627118645e-05,
"loss": 0.0287,
"step": 966
},
{
"epoch": 7.5546875,
"grad_norm": 12069.4609375,
"learning_rate": 1.3305084745762713e-05,
"loss": 0.0411,
"step": 967
},
{
"epoch": 7.5625,
"grad_norm": 6777.72705078125,
"learning_rate": 1.326271186440678e-05,
"loss": 0.038,
"step": 968
},
{
"epoch": 7.5703125,
"grad_norm": 6046.52294921875,
"learning_rate": 1.3220338983050848e-05,
"loss": 0.0288,
"step": 969
},
{
"epoch": 7.578125,
"grad_norm": 8347.2060546875,
"learning_rate": 1.3177966101694916e-05,
"loss": 0.0353,
"step": 970
},
{
"epoch": 7.5859375,
"grad_norm": 9543.3935546875,
"learning_rate": 1.3135593220338985e-05,
"loss": 0.0363,
"step": 971
},
{
"epoch": 7.59375,
"grad_norm": 6966.24853515625,
"learning_rate": 1.309322033898305e-05,
"loss": 0.0297,
"step": 972
},
{
"epoch": 7.6015625,
"grad_norm": 6987.7919921875,
"learning_rate": 1.305084745762712e-05,
"loss": 0.03,
"step": 973
},
{
"epoch": 7.609375,
"grad_norm": 6495.5517578125,
"learning_rate": 1.3008474576271188e-05,
"loss": 0.0371,
"step": 974
},
{
"epoch": 7.6171875,
"grad_norm": 10758.4248046875,
"learning_rate": 1.2966101694915256e-05,
"loss": 0.033,
"step": 975
},
{
"epoch": 7.625,
"grad_norm": 6341.98486328125,
"learning_rate": 1.2923728813559321e-05,
"loss": 0.0294,
"step": 976
},
{
"epoch": 7.6328125,
"grad_norm": 6339.486328125,
"learning_rate": 1.288135593220339e-05,
"loss": 0.0283,
"step": 977
},
{
"epoch": 7.640625,
"grad_norm": 4354.5888671875,
"learning_rate": 1.2838983050847458e-05,
"loss": 0.0306,
"step": 978
},
{
"epoch": 7.6484375,
"grad_norm": 5270.28369140625,
"learning_rate": 1.2796610169491528e-05,
"loss": 0.0304,
"step": 979
},
{
"epoch": 7.65625,
"grad_norm": 5608.5400390625,
"learning_rate": 1.2754237288135593e-05,
"loss": 0.0289,
"step": 980
},
{
"epoch": 7.6640625,
"grad_norm": 3364.42626953125,
"learning_rate": 1.2711864406779661e-05,
"loss": 0.0199,
"step": 981
},
{
"epoch": 7.671875,
"grad_norm": 8510.955078125,
"learning_rate": 1.2669491525423729e-05,
"loss": 0.0337,
"step": 982
},
{
"epoch": 7.6796875,
"grad_norm": 7066.22607421875,
"learning_rate": 1.2627118644067797e-05,
"loss": 0.0334,
"step": 983
},
{
"epoch": 7.6875,
"grad_norm": 4054.10498046875,
"learning_rate": 1.2584745762711864e-05,
"loss": 0.0235,
"step": 984
},
{
"epoch": 7.6953125,
"grad_norm": 6405.0810546875,
"learning_rate": 1.2542372881355932e-05,
"loss": 0.0318,
"step": 985
},
{
"epoch": 7.703125,
"grad_norm": 5400.9658203125,
"learning_rate": 1.25e-05,
"loss": 0.0236,
"step": 986
},
{
"epoch": 7.7109375,
"grad_norm": 42279.66015625,
"learning_rate": 1.2457627118644069e-05,
"loss": 0.0661,
"step": 987
},
{
"epoch": 7.71875,
"grad_norm": 10319.927734375,
"learning_rate": 1.2415254237288135e-05,
"loss": 0.028,
"step": 988
},
{
"epoch": 7.7265625,
"grad_norm": 12801.990234375,
"learning_rate": 1.2372881355932204e-05,
"loss": 0.0347,
"step": 989
},
{
"epoch": 7.734375,
"grad_norm": 7054.58642578125,
"learning_rate": 1.2330508474576272e-05,
"loss": 0.0369,
"step": 990
},
{
"epoch": 7.7421875,
"grad_norm": 9095.548828125,
"learning_rate": 1.228813559322034e-05,
"loss": 0.0323,
"step": 991
},
{
"epoch": 7.75,
"grad_norm": 8175.7392578125,
"learning_rate": 1.2245762711864407e-05,
"loss": 0.0388,
"step": 992
},
{
"epoch": 7.7578125,
"grad_norm": 8310.94921875,
"learning_rate": 1.2203389830508475e-05,
"loss": 0.0311,
"step": 993
},
{
"epoch": 7.765625,
"grad_norm": 6858.0908203125,
"learning_rate": 1.2161016949152544e-05,
"loss": 0.027,
"step": 994
},
{
"epoch": 7.7734375,
"grad_norm": 6796.79345703125,
"learning_rate": 1.2118644067796612e-05,
"loss": 0.0422,
"step": 995
},
{
"epoch": 7.78125,
"grad_norm": 4559.4580078125,
"learning_rate": 1.2076271186440678e-05,
"loss": 0.0231,
"step": 996
},
{
"epoch": 7.7890625,
"grad_norm": 7917.20849609375,
"learning_rate": 1.2033898305084747e-05,
"loss": 0.036,
"step": 997
},
{
"epoch": 7.796875,
"grad_norm": 10291.0908203125,
"learning_rate": 1.1991525423728813e-05,
"loss": 0.0304,
"step": 998
},
{
"epoch": 7.8046875,
"grad_norm": 5865.853515625,
"learning_rate": 1.1949152542372882e-05,
"loss": 0.0262,
"step": 999
},
{
"epoch": 7.8125,
"grad_norm": 8966.7158203125,
"learning_rate": 1.190677966101695e-05,
"loss": 0.0323,
"step": 1000
},
{
"epoch": 7.8203125,
"grad_norm": 5051.666015625,
"learning_rate": 1.1864406779661018e-05,
"loss": 0.0286,
"step": 1001
},
{
"epoch": 7.828125,
"grad_norm": 8937.671875,
"learning_rate": 1.1822033898305085e-05,
"loss": 0.0282,
"step": 1002
},
{
"epoch": 7.8359375,
"grad_norm": 5069.89111328125,
"learning_rate": 1.1779661016949153e-05,
"loss": 0.02,
"step": 1003
},
{
"epoch": 7.84375,
"grad_norm": 4136.7529296875,
"learning_rate": 1.173728813559322e-05,
"loss": 0.0171,
"step": 1004
},
{
"epoch": 7.8515625,
"grad_norm": 9865.9443359375,
"learning_rate": 1.169491525423729e-05,
"loss": 0.0295,
"step": 1005
},
{
"epoch": 7.859375,
"grad_norm": 6053.2763671875,
"learning_rate": 1.1652542372881356e-05,
"loss": 0.0184,
"step": 1006
},
{
"epoch": 7.8671875,
"grad_norm": 8258.0390625,
"learning_rate": 1.1610169491525424e-05,
"loss": 0.0364,
"step": 1007
},
{
"epoch": 7.875,
"grad_norm": 7677.3486328125,
"learning_rate": 1.1567796610169491e-05,
"loss": 0.024,
"step": 1008
},
{
"epoch": 7.8828125,
"grad_norm": 5362.6708984375,
"learning_rate": 1.152542372881356e-05,
"loss": 0.0246,
"step": 1009
},
{
"epoch": 7.890625,
"grad_norm": 6939.908203125,
"learning_rate": 1.1483050847457628e-05,
"loss": 0.0293,
"step": 1010
},
{
"epoch": 7.8984375,
"grad_norm": 5305.58740234375,
"learning_rate": 1.1440677966101696e-05,
"loss": 0.0252,
"step": 1011
},
{
"epoch": 7.90625,
"grad_norm": 7678.05078125,
"learning_rate": 1.1398305084745763e-05,
"loss": 0.0268,
"step": 1012
},
{
"epoch": 7.9140625,
"grad_norm": 6511.91357421875,
"learning_rate": 1.135593220338983e-05,
"loss": 0.0333,
"step": 1013
},
{
"epoch": 7.921875,
"grad_norm": 7980.66064453125,
"learning_rate": 1.1313559322033899e-05,
"loss": 0.0367,
"step": 1014
},
{
"epoch": 7.9296875,
"grad_norm": 6000.0751953125,
"learning_rate": 1.1271186440677967e-05,
"loss": 0.0345,
"step": 1015
},
{
"epoch": 7.9375,
"grad_norm": 6976.12255859375,
"learning_rate": 1.1228813559322036e-05,
"loss": 0.0349,
"step": 1016
},
{
"epoch": 7.9453125,
"grad_norm": 6820.16650390625,
"learning_rate": 1.1186440677966102e-05,
"loss": 0.0349,
"step": 1017
},
{
"epoch": 7.953125,
"grad_norm": 7169.0087890625,
"learning_rate": 1.114406779661017e-05,
"loss": 0.0229,
"step": 1018
},
{
"epoch": 7.9609375,
"grad_norm": 8476.9296875,
"learning_rate": 1.1101694915254237e-05,
"loss": 0.041,
"step": 1019
},
{
"epoch": 7.96875,
"grad_norm": 7307.53515625,
"learning_rate": 1.1059322033898305e-05,
"loss": 0.0375,
"step": 1020
},
{
"epoch": 7.9765625,
"grad_norm": 5141.7099609375,
"learning_rate": 1.1016949152542374e-05,
"loss": 0.0294,
"step": 1021
},
{
"epoch": 7.984375,
"grad_norm": 7192.37255859375,
"learning_rate": 1.0974576271186442e-05,
"loss": 0.0315,
"step": 1022
},
{
"epoch": 7.9921875,
"grad_norm": 6211.17236328125,
"learning_rate": 1.0932203389830509e-05,
"loss": 0.0301,
"step": 1023
},
{
"epoch": 8.0,
"grad_norm": 9713.328125,
"learning_rate": 1.0889830508474577e-05,
"loss": 0.0399,
"step": 1024
},
{
"epoch": 8.0,
"eval_f1_macro": 0.6438144746683533,
"eval_f1_micro": 0.8060075093867334,
"eval_loss": 0.040581997483968735,
"eval_precision": 0.8451443569553806,
"eval_recall": 0.7703349282296651,
"eval_runtime": 0.9626,
"eval_samples_per_second": 355.271,
"eval_steps_per_second": 15.582,
"step": 1024
},
{
"epoch": 8.0078125,
"grad_norm": 6071.39013671875,
"learning_rate": 1.0847457627118644e-05,
"loss": 0.0347,
"step": 1025
},
{
"epoch": 8.015625,
"grad_norm": 7513.33447265625,
"learning_rate": 1.0805084745762714e-05,
"loss": 0.0289,
"step": 1026
},
{
"epoch": 8.0234375,
"grad_norm": 4257.7978515625,
"learning_rate": 1.076271186440678e-05,
"loss": 0.0239,
"step": 1027
},
{
"epoch": 8.03125,
"grad_norm": 7449.67578125,
"learning_rate": 1.0720338983050848e-05,
"loss": 0.0239,
"step": 1028
},
{
"epoch": 8.0390625,
"grad_norm": 5810.79736328125,
"learning_rate": 1.0677966101694915e-05,
"loss": 0.0292,
"step": 1029
},
{
"epoch": 8.046875,
"grad_norm": 6529.50244140625,
"learning_rate": 1.0635593220338983e-05,
"loss": 0.0273,
"step": 1030
},
{
"epoch": 8.0546875,
"grad_norm": 5185.3330078125,
"learning_rate": 1.0593220338983052e-05,
"loss": 0.0252,
"step": 1031
},
{
"epoch": 8.0625,
"grad_norm": 6429.828125,
"learning_rate": 1.055084745762712e-05,
"loss": 0.0397,
"step": 1032
},
{
"epoch": 8.0703125,
"grad_norm": 7532.2294921875,
"learning_rate": 1.0508474576271186e-05,
"loss": 0.0238,
"step": 1033
},
{
"epoch": 8.078125,
"grad_norm": 8061.30712890625,
"learning_rate": 1.0466101694915255e-05,
"loss": 0.0347,
"step": 1034
},
{
"epoch": 8.0859375,
"grad_norm": 4410.4990234375,
"learning_rate": 1.0423728813559321e-05,
"loss": 0.0284,
"step": 1035
},
{
"epoch": 8.09375,
"grad_norm": 5692.14306640625,
"learning_rate": 1.038135593220339e-05,
"loss": 0.0344,
"step": 1036
},
{
"epoch": 8.1015625,
"grad_norm": 5113.8564453125,
"learning_rate": 1.0338983050847458e-05,
"loss": 0.0284,
"step": 1037
},
{
"epoch": 8.109375,
"grad_norm": 4947.67041015625,
"learning_rate": 1.0296610169491526e-05,
"loss": 0.0292,
"step": 1038
},
{
"epoch": 8.1171875,
"grad_norm": 6980.16357421875,
"learning_rate": 1.0254237288135593e-05,
"loss": 0.0314,
"step": 1039
},
{
"epoch": 8.125,
"grad_norm": 11856.7861328125,
"learning_rate": 1.0211864406779661e-05,
"loss": 0.0364,
"step": 1040
},
{
"epoch": 8.1328125,
"grad_norm": 5969.02880859375,
"learning_rate": 1.016949152542373e-05,
"loss": 0.0299,
"step": 1041
},
{
"epoch": 8.140625,
"grad_norm": 6479.8671875,
"learning_rate": 1.0127118644067798e-05,
"loss": 0.0269,
"step": 1042
},
{
"epoch": 8.1484375,
"grad_norm": 9616.21875,
"learning_rate": 1.0084745762711866e-05,
"loss": 0.0269,
"step": 1043
},
{
"epoch": 8.15625,
"grad_norm": 4053.617919921875,
"learning_rate": 1.0042372881355933e-05,
"loss": 0.0182,
"step": 1044
},
{
"epoch": 8.1640625,
"grad_norm": 10093.27734375,
"learning_rate": 1e-05,
"loss": 0.0495,
"step": 1045
},
{
"epoch": 8.171875,
"grad_norm": 5139.89453125,
"learning_rate": 9.957627118644067e-06,
"loss": 0.0266,
"step": 1046
},
{
"epoch": 8.1796875,
"grad_norm": 5918.72802734375,
"learning_rate": 9.915254237288137e-06,
"loss": 0.0225,
"step": 1047
},
{
"epoch": 8.1875,
"grad_norm": 6141.876953125,
"learning_rate": 9.872881355932204e-06,
"loss": 0.0303,
"step": 1048
},
{
"epoch": 8.1953125,
"grad_norm": 6408.3388671875,
"learning_rate": 9.830508474576272e-06,
"loss": 0.0304,
"step": 1049
},
{
"epoch": 8.203125,
"grad_norm": 8830.541015625,
"learning_rate": 9.788135593220339e-06,
"loss": 0.0465,
"step": 1050
},
{
"epoch": 8.2109375,
"grad_norm": 5525.220703125,
"learning_rate": 9.745762711864407e-06,
"loss": 0.0253,
"step": 1051
},
{
"epoch": 8.21875,
"grad_norm": 3203.750732421875,
"learning_rate": 9.703389830508475e-06,
"loss": 0.0185,
"step": 1052
},
{
"epoch": 8.2265625,
"grad_norm": 4742.48583984375,
"learning_rate": 9.661016949152544e-06,
"loss": 0.0231,
"step": 1053
},
{
"epoch": 8.234375,
"grad_norm": 3764.86767578125,
"learning_rate": 9.61864406779661e-06,
"loss": 0.0231,
"step": 1054
},
{
"epoch": 8.2421875,
"grad_norm": 7735.37158203125,
"learning_rate": 9.576271186440679e-06,
"loss": 0.0377,
"step": 1055
},
{
"epoch": 8.25,
"grad_norm": 6223.10107421875,
"learning_rate": 9.533898305084745e-06,
"loss": 0.0309,
"step": 1056
},
{
"epoch": 8.2578125,
"grad_norm": 6637.75341796875,
"learning_rate": 9.491525423728814e-06,
"loss": 0.0284,
"step": 1057
},
{
"epoch": 8.265625,
"grad_norm": 6764.4658203125,
"learning_rate": 9.449152542372882e-06,
"loss": 0.0323,
"step": 1058
},
{
"epoch": 8.2734375,
"grad_norm": 4817.35693359375,
"learning_rate": 9.40677966101695e-06,
"loss": 0.0293,
"step": 1059
},
{
"epoch": 8.28125,
"grad_norm": 4765.6083984375,
"learning_rate": 9.364406779661017e-06,
"loss": 0.0274,
"step": 1060
},
{
"epoch": 8.2890625,
"grad_norm": 7413.97265625,
"learning_rate": 9.322033898305085e-06,
"loss": 0.027,
"step": 1061
},
{
"epoch": 8.296875,
"grad_norm": 6805.26806640625,
"learning_rate": 9.279661016949153e-06,
"loss": 0.0238,
"step": 1062
},
{
"epoch": 8.3046875,
"grad_norm": 7125.6201171875,
"learning_rate": 9.237288135593222e-06,
"loss": 0.0395,
"step": 1063
},
{
"epoch": 8.3125,
"grad_norm": 6981.13232421875,
"learning_rate": 9.194915254237288e-06,
"loss": 0.0295,
"step": 1064
},
{
"epoch": 8.3203125,
"grad_norm": 5315.1123046875,
"learning_rate": 9.152542372881356e-06,
"loss": 0.0328,
"step": 1065
},
{
"epoch": 8.328125,
"grad_norm": 6804.814453125,
"learning_rate": 9.110169491525423e-06,
"loss": 0.0313,
"step": 1066
},
{
"epoch": 8.3359375,
"grad_norm": 3865.76708984375,
"learning_rate": 9.067796610169491e-06,
"loss": 0.0177,
"step": 1067
},
{
"epoch": 8.34375,
"grad_norm": 8431.0625,
"learning_rate": 9.02542372881356e-06,
"loss": 0.026,
"step": 1068
},
{
"epoch": 8.3515625,
"grad_norm": 4410.67822265625,
"learning_rate": 8.983050847457628e-06,
"loss": 0.027,
"step": 1069
},
{
"epoch": 8.359375,
"grad_norm": 4392.67431640625,
"learning_rate": 8.940677966101696e-06,
"loss": 0.029,
"step": 1070
},
{
"epoch": 8.3671875,
"grad_norm": 11461.17578125,
"learning_rate": 8.898305084745763e-06,
"loss": 0.0261,
"step": 1071
},
{
"epoch": 8.375,
"grad_norm": 3123.602294921875,
"learning_rate": 8.855932203389831e-06,
"loss": 0.0198,
"step": 1072
},
{
"epoch": 8.3828125,
"grad_norm": 6793.90380859375,
"learning_rate": 8.8135593220339e-06,
"loss": 0.0269,
"step": 1073
},
{
"epoch": 8.390625,
"grad_norm": 9541.9384765625,
"learning_rate": 8.771186440677968e-06,
"loss": 0.0414,
"step": 1074
},
{
"epoch": 8.3984375,
"grad_norm": 4862.1083984375,
"learning_rate": 8.728813559322034e-06,
"loss": 0.0298,
"step": 1075
},
{
"epoch": 8.40625,
"grad_norm": 5907.154296875,
"learning_rate": 8.686440677966103e-06,
"loss": 0.0281,
"step": 1076
},
{
"epoch": 8.4140625,
"grad_norm": 6116.0185546875,
"learning_rate": 8.644067796610169e-06,
"loss": 0.0262,
"step": 1077
},
{
"epoch": 8.421875,
"grad_norm": 7222.55322265625,
"learning_rate": 8.601694915254237e-06,
"loss": 0.0261,
"step": 1078
},
{
"epoch": 8.4296875,
"grad_norm": 6592.15185546875,
"learning_rate": 8.559322033898306e-06,
"loss": 0.0437,
"step": 1079
},
{
"epoch": 8.4375,
"grad_norm": 6138.49169921875,
"learning_rate": 8.516949152542374e-06,
"loss": 0.0355,
"step": 1080
},
{
"epoch": 8.4453125,
"grad_norm": 4654.087890625,
"learning_rate": 8.47457627118644e-06,
"loss": 0.0229,
"step": 1081
},
{
"epoch": 8.453125,
"grad_norm": 7042.80322265625,
"learning_rate": 8.432203389830509e-06,
"loss": 0.0239,
"step": 1082
},
{
"epoch": 8.4609375,
"grad_norm": 3418.085693359375,
"learning_rate": 8.389830508474575e-06,
"loss": 0.017,
"step": 1083
},
{
"epoch": 8.46875,
"grad_norm": 4873.7216796875,
"learning_rate": 8.347457627118645e-06,
"loss": 0.029,
"step": 1084
},
{
"epoch": 8.4765625,
"grad_norm": 4372.8046875,
"learning_rate": 8.305084745762712e-06,
"loss": 0.0229,
"step": 1085
},
{
"epoch": 8.484375,
"grad_norm": 4896.13134765625,
"learning_rate": 8.26271186440678e-06,
"loss": 0.0219,
"step": 1086
},
{
"epoch": 8.4921875,
"grad_norm": 4784.4970703125,
"learning_rate": 8.220338983050847e-06,
"loss": 0.0202,
"step": 1087
},
{
"epoch": 8.5,
"grad_norm": 13893.103515625,
"learning_rate": 8.177966101694915e-06,
"loss": 0.0504,
"step": 1088
},
{
"epoch": 8.5078125,
"grad_norm": 4869.3740234375,
"learning_rate": 8.135593220338983e-06,
"loss": 0.021,
"step": 1089
},
{
"epoch": 8.515625,
"grad_norm": 5039.43505859375,
"learning_rate": 8.093220338983052e-06,
"loss": 0.0211,
"step": 1090
},
{
"epoch": 8.5234375,
"grad_norm": 3833.005859375,
"learning_rate": 8.050847457627118e-06,
"loss": 0.0236,
"step": 1091
},
{
"epoch": 8.53125,
"grad_norm": 9487.751953125,
"learning_rate": 8.008474576271187e-06,
"loss": 0.0316,
"step": 1092
},
{
"epoch": 8.5390625,
"grad_norm": 8038.54833984375,
"learning_rate": 7.966101694915253e-06,
"loss": 0.0231,
"step": 1093
},
{
"epoch": 8.546875,
"grad_norm": 5829.37939453125,
"learning_rate": 7.923728813559323e-06,
"loss": 0.0347,
"step": 1094
},
{
"epoch": 8.5546875,
"grad_norm": 4067.704345703125,
"learning_rate": 7.881355932203392e-06,
"loss": 0.0279,
"step": 1095
},
{
"epoch": 8.5625,
"grad_norm": 5950.03076171875,
"learning_rate": 7.838983050847458e-06,
"loss": 0.0265,
"step": 1096
},
{
"epoch": 8.5703125,
"grad_norm": 5590.00341796875,
"learning_rate": 7.796610169491526e-06,
"loss": 0.0294,
"step": 1097
},
{
"epoch": 8.578125,
"grad_norm": 5132.7919921875,
"learning_rate": 7.754237288135593e-06,
"loss": 0.0308,
"step": 1098
},
{
"epoch": 8.5859375,
"grad_norm": 6174.7685546875,
"learning_rate": 7.711864406779661e-06,
"loss": 0.0312,
"step": 1099
},
{
"epoch": 8.59375,
"grad_norm": 7201.44873046875,
"learning_rate": 7.66949152542373e-06,
"loss": 0.0274,
"step": 1100
},
{
"epoch": 8.6015625,
"grad_norm": 3964.30908203125,
"learning_rate": 7.627118644067798e-06,
"loss": 0.0192,
"step": 1101
},
{
"epoch": 8.609375,
"grad_norm": 4569.48095703125,
"learning_rate": 7.5847457627118645e-06,
"loss": 0.0231,
"step": 1102
},
{
"epoch": 8.6171875,
"grad_norm": 8443.8662109375,
"learning_rate": 7.542372881355933e-06,
"loss": 0.0276,
"step": 1103
},
{
"epoch": 8.625,
"grad_norm": 6956.72265625,
"learning_rate": 7.5e-06,
"loss": 0.0336,
"step": 1104
},
{
"epoch": 8.6328125,
"grad_norm": 4084.778564453125,
"learning_rate": 7.4576271186440685e-06,
"loss": 0.0206,
"step": 1105
},
{
"epoch": 8.640625,
"grad_norm": 5957.373046875,
"learning_rate": 7.415254237288136e-06,
"loss": 0.0258,
"step": 1106
},
{
"epoch": 8.6484375,
"grad_norm": 6853.255859375,
"learning_rate": 7.372881355932204e-06,
"loss": 0.0325,
"step": 1107
},
{
"epoch": 8.65625,
"grad_norm": 6685.517578125,
"learning_rate": 7.330508474576271e-06,
"loss": 0.0269,
"step": 1108
},
{
"epoch": 8.6640625,
"grad_norm": 5845.654296875,
"learning_rate": 7.28813559322034e-06,
"loss": 0.029,
"step": 1109
},
{
"epoch": 8.671875,
"grad_norm": 9941.9833984375,
"learning_rate": 7.2457627118644065e-06,
"loss": 0.035,
"step": 1110
},
{
"epoch": 8.6796875,
"grad_norm": 5552.146484375,
"learning_rate": 7.203389830508475e-06,
"loss": 0.0268,
"step": 1111
},
{
"epoch": 8.6875,
"grad_norm": 9213.5498046875,
"learning_rate": 7.161016949152542e-06,
"loss": 0.0331,
"step": 1112
},
{
"epoch": 8.6953125,
"grad_norm": 8328.6044921875,
"learning_rate": 7.1186440677966106e-06,
"loss": 0.0298,
"step": 1113
},
{
"epoch": 8.703125,
"grad_norm": 9299.001953125,
"learning_rate": 7.076271186440678e-06,
"loss": 0.0407,
"step": 1114
},
{
"epoch": 8.7109375,
"grad_norm": 7187.4912109375,
"learning_rate": 7.033898305084746e-06,
"loss": 0.0349,
"step": 1115
},
{
"epoch": 8.71875,
"grad_norm": 6971.86669921875,
"learning_rate": 6.991525423728814e-06,
"loss": 0.0341,
"step": 1116
},
{
"epoch": 8.7265625,
"grad_norm": 7665.25634765625,
"learning_rate": 6.949152542372882e-06,
"loss": 0.0299,
"step": 1117
},
{
"epoch": 8.734375,
"grad_norm": 4887.4912109375,
"learning_rate": 6.906779661016949e-06,
"loss": 0.0235,
"step": 1118
},
{
"epoch": 8.7421875,
"grad_norm": 6069.05859375,
"learning_rate": 6.864406779661017e-06,
"loss": 0.0351,
"step": 1119
},
{
"epoch": 8.75,
"grad_norm": 5257.1796875,
"learning_rate": 6.822033898305084e-06,
"loss": 0.0278,
"step": 1120
},
{
"epoch": 8.7578125,
"grad_norm": 4754.6630859375,
"learning_rate": 6.779661016949153e-06,
"loss": 0.0228,
"step": 1121
},
{
"epoch": 8.765625,
"grad_norm": 3649.241455078125,
"learning_rate": 6.737288135593221e-06,
"loss": 0.0172,
"step": 1122
},
{
"epoch": 8.7734375,
"grad_norm": 5769.125,
"learning_rate": 6.694915254237288e-06,
"loss": 0.0388,
"step": 1123
},
{
"epoch": 8.78125,
"grad_norm": 5844.658203125,
"learning_rate": 6.652542372881357e-06,
"loss": 0.0256,
"step": 1124
},
{
"epoch": 8.7890625,
"grad_norm": 4553.904296875,
"learning_rate": 6.610169491525424e-06,
"loss": 0.0255,
"step": 1125
},
{
"epoch": 8.796875,
"grad_norm": 9810.65625,
"learning_rate": 6.567796610169492e-06,
"loss": 0.0377,
"step": 1126
},
{
"epoch": 8.8046875,
"grad_norm": 6570.43603515625,
"learning_rate": 6.52542372881356e-06,
"loss": 0.0274,
"step": 1127
},
{
"epoch": 8.8125,
"grad_norm": 7566.02099609375,
"learning_rate": 6.483050847457628e-06,
"loss": 0.0283,
"step": 1128
},
{
"epoch": 8.8203125,
"grad_norm": 4592.482421875,
"learning_rate": 6.440677966101695e-06,
"loss": 0.0283,
"step": 1129
},
{
"epoch": 8.828125,
"grad_norm": 6080.28369140625,
"learning_rate": 6.398305084745764e-06,
"loss": 0.0217,
"step": 1130
},
{
"epoch": 8.8359375,
"grad_norm": 6117.42578125,
"learning_rate": 6.3559322033898304e-06,
"loss": 0.0228,
"step": 1131
},
{
"epoch": 8.84375,
"grad_norm": 4134.37841796875,
"learning_rate": 6.313559322033899e-06,
"loss": 0.0277,
"step": 1132
},
{
"epoch": 8.8515625,
"grad_norm": 5395.4423828125,
"learning_rate": 6.271186440677966e-06,
"loss": 0.0335,
"step": 1133
},
{
"epoch": 8.859375,
"grad_norm": 4442.18408203125,
"learning_rate": 6.2288135593220344e-06,
"loss": 0.0213,
"step": 1134
},
{
"epoch": 8.8671875,
"grad_norm": 10708.1533203125,
"learning_rate": 6.186440677966102e-06,
"loss": 0.0255,
"step": 1135
},
{
"epoch": 8.875,
"grad_norm": 11302.8466796875,
"learning_rate": 6.14406779661017e-06,
"loss": 0.0362,
"step": 1136
},
{
"epoch": 8.8828125,
"grad_norm": 5220.56640625,
"learning_rate": 6.101694915254238e-06,
"loss": 0.0246,
"step": 1137
},
{
"epoch": 8.890625,
"grad_norm": 6472.3994140625,
"learning_rate": 6.059322033898306e-06,
"loss": 0.0346,
"step": 1138
},
{
"epoch": 8.8984375,
"grad_norm": 6041.857421875,
"learning_rate": 6.016949152542373e-06,
"loss": 0.0384,
"step": 1139
},
{
"epoch": 8.90625,
"grad_norm": 6012.9814453125,
"learning_rate": 5.974576271186441e-06,
"loss": 0.0285,
"step": 1140
},
{
"epoch": 8.9140625,
"grad_norm": 4448.99072265625,
"learning_rate": 5.932203389830509e-06,
"loss": 0.0183,
"step": 1141
},
{
"epoch": 8.921875,
"grad_norm": 4368.072265625,
"learning_rate": 5.8898305084745765e-06,
"loss": 0.0321,
"step": 1142
},
{
"epoch": 8.9296875,
"grad_norm": 7539.6708984375,
"learning_rate": 5.847457627118645e-06,
"loss": 0.0335,
"step": 1143
},
{
"epoch": 8.9375,
"grad_norm": 9250.6513671875,
"learning_rate": 5.805084745762712e-06,
"loss": 0.0236,
"step": 1144
},
{
"epoch": 8.9453125,
"grad_norm": 5289.416015625,
"learning_rate": 5.76271186440678e-06,
"loss": 0.0247,
"step": 1145
},
{
"epoch": 8.953125,
"grad_norm": 6851.64306640625,
"learning_rate": 5.720338983050848e-06,
"loss": 0.0236,
"step": 1146
},
{
"epoch": 8.9609375,
"grad_norm": 3551.806884765625,
"learning_rate": 5.677966101694915e-06,
"loss": 0.0185,
"step": 1147
},
{
"epoch": 8.96875,
"grad_norm": 7779.05859375,
"learning_rate": 5.635593220338984e-06,
"loss": 0.0391,
"step": 1148
},
{
"epoch": 8.9765625,
"grad_norm": 4065.190185546875,
"learning_rate": 5.593220338983051e-06,
"loss": 0.0256,
"step": 1149
},
{
"epoch": 8.984375,
"grad_norm": 5641.29736328125,
"learning_rate": 5.550847457627119e-06,
"loss": 0.0315,
"step": 1150
},
{
"epoch": 8.9921875,
"grad_norm": 6987.65380859375,
"learning_rate": 5.508474576271187e-06,
"loss": 0.042,
"step": 1151
},
{
"epoch": 9.0,
"grad_norm": 4003.3515625,
"learning_rate": 5.466101694915254e-06,
"loss": 0.0231,
"step": 1152
},
{
"epoch": 9.0,
"eval_f1_macro": 0.6402217849253086,
"eval_f1_micro": 0.8085106382978723,
"eval_loss": 0.03940509632229805,
"eval_precision": 0.847769028871391,
"eval_recall": 0.7727272727272727,
"eval_runtime": 0.9656,
"eval_samples_per_second": 354.191,
"eval_steps_per_second": 15.535,
"step": 1152
},
{
"epoch": 9.0078125,
"grad_norm": 4437.02880859375,
"learning_rate": 5.423728813559322e-06,
"loss": 0.0246,
"step": 1153
},
{
"epoch": 9.015625,
"grad_norm": 4161.5791015625,
"learning_rate": 5.38135593220339e-06,
"loss": 0.0263,
"step": 1154
},
{
"epoch": 9.0234375,
"grad_norm": 5125.38134765625,
"learning_rate": 5.3389830508474575e-06,
"loss": 0.0273,
"step": 1155
},
{
"epoch": 9.03125,
"grad_norm": 8570.2763671875,
"learning_rate": 5.296610169491526e-06,
"loss": 0.0413,
"step": 1156
},
{
"epoch": 9.0390625,
"grad_norm": 3315.14306640625,
"learning_rate": 5.254237288135593e-06,
"loss": 0.0187,
"step": 1157
},
{
"epoch": 9.046875,
"grad_norm": 9631.3310546875,
"learning_rate": 5.211864406779661e-06,
"loss": 0.0269,
"step": 1158
},
{
"epoch": 9.0546875,
"grad_norm": 8717.6494140625,
"learning_rate": 5.169491525423729e-06,
"loss": 0.027,
"step": 1159
},
{
"epoch": 9.0625,
"grad_norm": 6941.48779296875,
"learning_rate": 5.127118644067796e-06,
"loss": 0.031,
"step": 1160
},
{
"epoch": 9.0703125,
"grad_norm": 6844.98291015625,
"learning_rate": 5.084745762711865e-06,
"loss": 0.0328,
"step": 1161
},
{
"epoch": 9.078125,
"grad_norm": 6341.5322265625,
"learning_rate": 5.042372881355933e-06,
"loss": 0.0382,
"step": 1162
},
{
"epoch": 9.0859375,
"grad_norm": 8118.283203125,
"learning_rate": 5e-06,
"loss": 0.0337,
"step": 1163
},
{
"epoch": 9.09375,
"grad_norm": 6843.1171875,
"learning_rate": 4.957627118644069e-06,
"loss": 0.0285,
"step": 1164
},
{
"epoch": 9.1015625,
"grad_norm": 4028.68896484375,
"learning_rate": 4.915254237288136e-06,
"loss": 0.0211,
"step": 1165
},
{
"epoch": 9.109375,
"grad_norm": 9727.4384765625,
"learning_rate": 4.872881355932204e-06,
"loss": 0.0271,
"step": 1166
},
{
"epoch": 9.1171875,
"grad_norm": 6235.552734375,
"learning_rate": 4.830508474576272e-06,
"loss": 0.0379,
"step": 1167
},
{
"epoch": 9.125,
"grad_norm": 5365.880859375,
"learning_rate": 4.788135593220339e-06,
"loss": 0.0319,
"step": 1168
},
{
"epoch": 9.1328125,
"grad_norm": 5417.88525390625,
"learning_rate": 4.745762711864407e-06,
"loss": 0.0243,
"step": 1169
},
{
"epoch": 9.140625,
"grad_norm": 7676.85400390625,
"learning_rate": 4.703389830508475e-06,
"loss": 0.0315,
"step": 1170
},
{
"epoch": 9.1484375,
"grad_norm": 6260.35205078125,
"learning_rate": 4.6610169491525425e-06,
"loss": 0.0298,
"step": 1171
},
{
"epoch": 9.15625,
"grad_norm": 5888.86474609375,
"learning_rate": 4.618644067796611e-06,
"loss": 0.0299,
"step": 1172
},
{
"epoch": 9.1640625,
"grad_norm": 5138.916015625,
"learning_rate": 4.576271186440678e-06,
"loss": 0.0238,
"step": 1173
},
{
"epoch": 9.171875,
"grad_norm": 9133.30859375,
"learning_rate": 4.533898305084746e-06,
"loss": 0.0381,
"step": 1174
},
{
"epoch": 9.1796875,
"grad_norm": 5835.43310546875,
"learning_rate": 4.491525423728814e-06,
"loss": 0.0293,
"step": 1175
},
{
"epoch": 9.1875,
"grad_norm": 4155.7900390625,
"learning_rate": 4.449152542372881e-06,
"loss": 0.0213,
"step": 1176
},
{
"epoch": 9.1953125,
"grad_norm": 5702.70654296875,
"learning_rate": 4.40677966101695e-06,
"loss": 0.0296,
"step": 1177
},
{
"epoch": 9.203125,
"grad_norm": 5850.8359375,
"learning_rate": 4.364406779661017e-06,
"loss": 0.0331,
"step": 1178
},
{
"epoch": 9.2109375,
"grad_norm": 4211.248046875,
"learning_rate": 4.3220338983050846e-06,
"loss": 0.0243,
"step": 1179
},
{
"epoch": 9.21875,
"grad_norm": 8536.279296875,
"learning_rate": 4.279661016949153e-06,
"loss": 0.0285,
"step": 1180
},
{
"epoch": 9.2265625,
"grad_norm": 4515.28759765625,
"learning_rate": 4.23728813559322e-06,
"loss": 0.0218,
"step": 1181
},
{
"epoch": 9.234375,
"grad_norm": 4239.47998046875,
"learning_rate": 4.194915254237288e-06,
"loss": 0.0255,
"step": 1182
},
{
"epoch": 9.2421875,
"grad_norm": 5965.873046875,
"learning_rate": 4.152542372881356e-06,
"loss": 0.0348,
"step": 1183
},
{
"epoch": 9.25,
"grad_norm": 5384.48486328125,
"learning_rate": 4.1101694915254235e-06,
"loss": 0.0281,
"step": 1184
},
{
"epoch": 9.2578125,
"grad_norm": 3375.787353515625,
"learning_rate": 4.067796610169492e-06,
"loss": 0.0214,
"step": 1185
},
{
"epoch": 9.265625,
"grad_norm": 8799.5517578125,
"learning_rate": 4.025423728813559e-06,
"loss": 0.022,
"step": 1186
},
{
"epoch": 9.2734375,
"grad_norm": 5043.50537109375,
"learning_rate": 3.983050847457627e-06,
"loss": 0.0297,
"step": 1187
},
{
"epoch": 9.28125,
"grad_norm": 7059.8994140625,
"learning_rate": 3.940677966101696e-06,
"loss": 0.026,
"step": 1188
},
{
"epoch": 9.2890625,
"grad_norm": 4606.06005859375,
"learning_rate": 3.898305084745763e-06,
"loss": 0.0198,
"step": 1189
},
{
"epoch": 9.296875,
"grad_norm": 5390.6875,
"learning_rate": 3.855932203389831e-06,
"loss": 0.0246,
"step": 1190
},
{
"epoch": 9.3046875,
"grad_norm": 5660.11181640625,
"learning_rate": 3.813559322033899e-06,
"loss": 0.0259,
"step": 1191
},
{
"epoch": 9.3125,
"grad_norm": 5039.08740234375,
"learning_rate": 3.7711864406779664e-06,
"loss": 0.0298,
"step": 1192
},
{
"epoch": 9.3203125,
"grad_norm": 6163.6650390625,
"learning_rate": 3.7288135593220342e-06,
"loss": 0.0248,
"step": 1193
},
{
"epoch": 9.328125,
"grad_norm": 3844.65380859375,
"learning_rate": 3.686440677966102e-06,
"loss": 0.0193,
"step": 1194
},
{
"epoch": 9.3359375,
"grad_norm": 4783.8076171875,
"learning_rate": 3.64406779661017e-06,
"loss": 0.0245,
"step": 1195
},
{
"epoch": 9.34375,
"grad_norm": 6383.99560546875,
"learning_rate": 3.6016949152542374e-06,
"loss": 0.0188,
"step": 1196
},
{
"epoch": 9.3515625,
"grad_norm": 4392.365234375,
"learning_rate": 3.5593220338983053e-06,
"loss": 0.0228,
"step": 1197
},
{
"epoch": 9.359375,
"grad_norm": 3577.877197265625,
"learning_rate": 3.516949152542373e-06,
"loss": 0.0212,
"step": 1198
},
{
"epoch": 9.3671875,
"grad_norm": 4586.41357421875,
"learning_rate": 3.474576271186441e-06,
"loss": 0.0233,
"step": 1199
},
{
"epoch": 9.375,
"grad_norm": 6286.810546875,
"learning_rate": 3.4322033898305084e-06,
"loss": 0.0248,
"step": 1200
},
{
"epoch": 9.3828125,
"grad_norm": 5276.919921875,
"learning_rate": 3.3898305084745763e-06,
"loss": 0.0251,
"step": 1201
},
{
"epoch": 9.390625,
"grad_norm": 4581.96826171875,
"learning_rate": 3.347457627118644e-06,
"loss": 0.0215,
"step": 1202
},
{
"epoch": 9.3984375,
"grad_norm": 6444.8076171875,
"learning_rate": 3.305084745762712e-06,
"loss": 0.0269,
"step": 1203
},
{
"epoch": 9.40625,
"grad_norm": 6820.58935546875,
"learning_rate": 3.26271186440678e-06,
"loss": 0.0341,
"step": 1204
},
{
"epoch": 9.4140625,
"grad_norm": 6650.009765625,
"learning_rate": 3.2203389830508473e-06,
"loss": 0.0323,
"step": 1205
},
{
"epoch": 9.421875,
"grad_norm": 7648.53173828125,
"learning_rate": 3.1779661016949152e-06,
"loss": 0.0263,
"step": 1206
},
{
"epoch": 9.4296875,
"grad_norm": 7402.11669921875,
"learning_rate": 3.135593220338983e-06,
"loss": 0.0233,
"step": 1207
},
{
"epoch": 9.4375,
"grad_norm": 8048.23974609375,
"learning_rate": 3.093220338983051e-06,
"loss": 0.0364,
"step": 1208
},
{
"epoch": 9.4453125,
"grad_norm": 4203.61279296875,
"learning_rate": 3.050847457627119e-06,
"loss": 0.0256,
"step": 1209
},
{
"epoch": 9.453125,
"grad_norm": 6082.70751953125,
"learning_rate": 3.0084745762711867e-06,
"loss": 0.0244,
"step": 1210
},
{
"epoch": 9.4609375,
"grad_norm": 5152.71923828125,
"learning_rate": 2.9661016949152545e-06,
"loss": 0.0221,
"step": 1211
},
{
"epoch": 9.46875,
"grad_norm": 9202.958984375,
"learning_rate": 2.9237288135593224e-06,
"loss": 0.0334,
"step": 1212
},
{
"epoch": 9.4765625,
"grad_norm": 6290.6767578125,
"learning_rate": 2.88135593220339e-06,
"loss": 0.0299,
"step": 1213
},
{
"epoch": 9.484375,
"grad_norm": 7286.15380859375,
"learning_rate": 2.8389830508474577e-06,
"loss": 0.0428,
"step": 1214
},
{
"epoch": 9.4921875,
"grad_norm": 6934.98681640625,
"learning_rate": 2.7966101694915256e-06,
"loss": 0.0253,
"step": 1215
},
{
"epoch": 9.5,
"grad_norm": 7437.26904296875,
"learning_rate": 2.7542372881355934e-06,
"loss": 0.0296,
"step": 1216
},
{
"epoch": 9.5078125,
"grad_norm": 7182.04248046875,
"learning_rate": 2.711864406779661e-06,
"loss": 0.0279,
"step": 1217
},
{
"epoch": 9.515625,
"grad_norm": 5111.908203125,
"learning_rate": 2.6694915254237287e-06,
"loss": 0.0292,
"step": 1218
},
{
"epoch": 9.5234375,
"grad_norm": 6158.67041015625,
"learning_rate": 2.6271186440677966e-06,
"loss": 0.0298,
"step": 1219
},
{
"epoch": 9.53125,
"grad_norm": 7653.3173828125,
"learning_rate": 2.5847457627118645e-06,
"loss": 0.0257,
"step": 1220
},
{
"epoch": 9.5390625,
"grad_norm": 4783.30517578125,
"learning_rate": 2.5423728813559323e-06,
"loss": 0.023,
"step": 1221
},
{
"epoch": 9.546875,
"grad_norm": 5689.5087890625,
"learning_rate": 2.5e-06,
"loss": 0.0324,
"step": 1222
},
{
"epoch": 9.5546875,
"grad_norm": 5559.02392578125,
"learning_rate": 2.457627118644068e-06,
"loss": 0.0226,
"step": 1223
},
{
"epoch": 9.5625,
"grad_norm": 5397.81103515625,
"learning_rate": 2.415254237288136e-06,
"loss": 0.0228,
"step": 1224
},
{
"epoch": 9.5703125,
"grad_norm": 10019.9892578125,
"learning_rate": 2.3728813559322034e-06,
"loss": 0.031,
"step": 1225
},
{
"epoch": 9.578125,
"grad_norm": 5605.50146484375,
"learning_rate": 2.3305084745762712e-06,
"loss": 0.0251,
"step": 1226
},
{
"epoch": 9.5859375,
"grad_norm": 11014.6982421875,
"learning_rate": 2.288135593220339e-06,
"loss": 0.0265,
"step": 1227
},
{
"epoch": 9.59375,
"grad_norm": 8228.841796875,
"learning_rate": 2.245762711864407e-06,
"loss": 0.043,
"step": 1228
},
{
"epoch": 9.6015625,
"grad_norm": 4805.31005859375,
"learning_rate": 2.203389830508475e-06,
"loss": 0.0277,
"step": 1229
},
{
"epoch": 9.609375,
"grad_norm": 5495.8935546875,
"learning_rate": 2.1610169491525423e-06,
"loss": 0.0327,
"step": 1230
},
{
"epoch": 9.6171875,
"grad_norm": 5298.52392578125,
"learning_rate": 2.11864406779661e-06,
"loss": 0.03,
"step": 1231
},
{
"epoch": 9.625,
"grad_norm": 4747.50146484375,
"learning_rate": 2.076271186440678e-06,
"loss": 0.0239,
"step": 1232
},
{
"epoch": 9.6328125,
"grad_norm": 5919.845703125,
"learning_rate": 2.033898305084746e-06,
"loss": 0.0245,
"step": 1233
},
{
"epoch": 9.640625,
"grad_norm": 4644.22509765625,
"learning_rate": 1.9915254237288133e-06,
"loss": 0.0242,
"step": 1234
},
{
"epoch": 9.6484375,
"grad_norm": 3752.98095703125,
"learning_rate": 1.9491525423728816e-06,
"loss": 0.0215,
"step": 1235
},
{
"epoch": 9.65625,
"grad_norm": 7217.20849609375,
"learning_rate": 1.9067796610169495e-06,
"loss": 0.0275,
"step": 1236
},
{
"epoch": 9.6640625,
"grad_norm": 5142.59912109375,
"learning_rate": 1.8644067796610171e-06,
"loss": 0.0227,
"step": 1237
},
{
"epoch": 9.671875,
"grad_norm": 5993.99609375,
"learning_rate": 1.822033898305085e-06,
"loss": 0.0272,
"step": 1238
},
{
"epoch": 9.6796875,
"grad_norm": 2078.112548828125,
"learning_rate": 1.7796610169491526e-06,
"loss": 0.0134,
"step": 1239
},
{
"epoch": 9.6875,
"grad_norm": 5162.859375,
"learning_rate": 1.7372881355932205e-06,
"loss": 0.0271,
"step": 1240
},
{
"epoch": 9.6953125,
"grad_norm": 5032.458984375,
"learning_rate": 1.6949152542372882e-06,
"loss": 0.0307,
"step": 1241
},
{
"epoch": 9.703125,
"grad_norm": 5534.09033203125,
"learning_rate": 1.652542372881356e-06,
"loss": 0.0206,
"step": 1242
},
{
"epoch": 9.7109375,
"grad_norm": 3177.3193359375,
"learning_rate": 1.6101694915254237e-06,
"loss": 0.0192,
"step": 1243
},
{
"epoch": 9.71875,
"grad_norm": 8134.8173828125,
"learning_rate": 1.5677966101694915e-06,
"loss": 0.027,
"step": 1244
},
{
"epoch": 9.7265625,
"grad_norm": 5094.0478515625,
"learning_rate": 1.5254237288135594e-06,
"loss": 0.0244,
"step": 1245
},
{
"epoch": 9.734375,
"grad_norm": 6769.5283203125,
"learning_rate": 1.4830508474576273e-06,
"loss": 0.0316,
"step": 1246
},
{
"epoch": 9.7421875,
"grad_norm": 6298.63330078125,
"learning_rate": 1.440677966101695e-06,
"loss": 0.0248,
"step": 1247
},
{
"epoch": 9.75,
"grad_norm": 6314.537109375,
"learning_rate": 1.3983050847457628e-06,
"loss": 0.0325,
"step": 1248
},
{
"epoch": 9.7578125,
"grad_norm": 5658.31201171875,
"learning_rate": 1.3559322033898304e-06,
"loss": 0.0278,
"step": 1249
},
{
"epoch": 9.765625,
"grad_norm": 4891.05224609375,
"learning_rate": 1.3135593220338983e-06,
"loss": 0.026,
"step": 1250
},
{
"epoch": 9.7734375,
"grad_norm": 4064.448486328125,
"learning_rate": 1.2711864406779662e-06,
"loss": 0.0221,
"step": 1251
},
{
"epoch": 9.78125,
"grad_norm": 7016.22314453125,
"learning_rate": 1.228813559322034e-06,
"loss": 0.0304,
"step": 1252
},
{
"epoch": 9.7890625,
"grad_norm": 14025.6298828125,
"learning_rate": 1.1864406779661017e-06,
"loss": 0.0354,
"step": 1253
},
{
"epoch": 9.796875,
"grad_norm": 5520.884765625,
"learning_rate": 1.1440677966101696e-06,
"loss": 0.0328,
"step": 1254
},
{
"epoch": 9.8046875,
"grad_norm": 6142.18310546875,
"learning_rate": 1.1016949152542374e-06,
"loss": 0.0252,
"step": 1255
},
{
"epoch": 9.8125,
"grad_norm": 5370.37841796875,
"learning_rate": 1.059322033898305e-06,
"loss": 0.0248,
"step": 1256
},
{
"epoch": 9.8203125,
"grad_norm": 5067.8095703125,
"learning_rate": 1.016949152542373e-06,
"loss": 0.0249,
"step": 1257
},
{
"epoch": 9.828125,
"grad_norm": 7998.80712890625,
"learning_rate": 9.745762711864408e-07,
"loss": 0.0306,
"step": 1258
},
{
"epoch": 9.8359375,
"grad_norm": 3767.293212890625,
"learning_rate": 9.322033898305086e-07,
"loss": 0.018,
"step": 1259
},
{
"epoch": 9.84375,
"grad_norm": 6761.5185546875,
"learning_rate": 8.898305084745763e-07,
"loss": 0.0241,
"step": 1260
},
{
"epoch": 9.8515625,
"grad_norm": 5618.4365234375,
"learning_rate": 8.474576271186441e-07,
"loss": 0.0199,
"step": 1261
},
{
"epoch": 9.859375,
"grad_norm": 8051.69677734375,
"learning_rate": 8.050847457627118e-07,
"loss": 0.0368,
"step": 1262
},
{
"epoch": 9.8671875,
"grad_norm": 5177.255859375,
"learning_rate": 7.627118644067797e-07,
"loss": 0.0216,
"step": 1263
},
{
"epoch": 9.875,
"grad_norm": 5250.49365234375,
"learning_rate": 7.203389830508475e-07,
"loss": 0.0216,
"step": 1264
},
{
"epoch": 9.8828125,
"grad_norm": 5667.3046875,
"learning_rate": 6.779661016949152e-07,
"loss": 0.0198,
"step": 1265
},
{
"epoch": 9.890625,
"grad_norm": 5943.46435546875,
"learning_rate": 6.355932203389831e-07,
"loss": 0.0284,
"step": 1266
},
{
"epoch": 9.8984375,
"grad_norm": 5587.56103515625,
"learning_rate": 5.932203389830508e-07,
"loss": 0.0257,
"step": 1267
},
{
"epoch": 9.90625,
"grad_norm": 4717.15478515625,
"learning_rate": 5.508474576271187e-07,
"loss": 0.0256,
"step": 1268
},
{
"epoch": 9.9140625,
"grad_norm": 4780.7919921875,
"learning_rate": 5.084745762711865e-07,
"loss": 0.027,
"step": 1269
},
{
"epoch": 9.921875,
"grad_norm": 6068.326171875,
"learning_rate": 4.661016949152543e-07,
"loss": 0.0244,
"step": 1270
},
{
"epoch": 9.9296875,
"grad_norm": 5599.2080078125,
"learning_rate": 4.2372881355932204e-07,
"loss": 0.026,
"step": 1271
},
{
"epoch": 9.9375,
"grad_norm": 6779.73291015625,
"learning_rate": 3.8135593220338985e-07,
"loss": 0.0324,
"step": 1272
},
{
"epoch": 9.9453125,
"grad_norm": 6175.234375,
"learning_rate": 3.389830508474576e-07,
"loss": 0.0222,
"step": 1273
},
{
"epoch": 9.953125,
"grad_norm": 5667.9052734375,
"learning_rate": 2.966101694915254e-07,
"loss": 0.0277,
"step": 1274
},
{
"epoch": 9.9609375,
"grad_norm": 8041.81982421875,
"learning_rate": 2.5423728813559323e-07,
"loss": 0.0246,
"step": 1275
},
{
"epoch": 9.96875,
"grad_norm": 4582.69482421875,
"learning_rate": 2.1186440677966102e-07,
"loss": 0.0308,
"step": 1276
},
{
"epoch": 9.9765625,
"grad_norm": 3083.62646484375,
"learning_rate": 1.694915254237288e-07,
"loss": 0.0174,
"step": 1277
},
{
"epoch": 9.984375,
"grad_norm": 5182.75341796875,
"learning_rate": 1.2711864406779662e-07,
"loss": 0.029,
"step": 1278
},
{
"epoch": 9.9921875,
"grad_norm": 3887.08642578125,
"learning_rate": 8.47457627118644e-08,
"loss": 0.0233,
"step": 1279
},
{
"epoch": 10.0,
"grad_norm": 4546.1416015625,
"learning_rate": 4.23728813559322e-08,
"loss": 0.0219,
"step": 1280
},
{
"epoch": 10.0,
"eval_f1_macro": 0.6369670032163984,
"eval_f1_micro": 0.8070175438596491,
"eval_loss": 0.038641802966594696,
"eval_precision": 0.8473684210526315,
"eval_recall": 0.7703349282296651,
"eval_runtime": 0.9652,
"eval_samples_per_second": 354.346,
"eval_steps_per_second": 15.541,
"step": 1280
}
],
"logging_steps": 1,
"max_steps": 1280,
"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": 8078358340546560.0,
"train_batch_size": 24,
"trial_name": null,
"trial_params": null
}