Erland's picture
Add ru-RU (haryos_model_large)
df4642e verified
Raw
History Blame Contribute Delete
249 kB
{
"best_global_step": 900,
"best_metric": 0.8760452533202164,
"best_model_checkpoint": "checkpoint_results/xlm-roberta-large_massive_ru-RU_lr1e-05_ep20_compile/checkpoint-900",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 1440,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005555555555555556,
"grad_norm": 4.344616413116455,
"learning_rate": 0.0,
"loss": 4.1041,
"step": 1
},
{
"epoch": 0.011111111111111112,
"grad_norm": 5.901679515838623,
"learning_rate": 2.777777777777778e-08,
"loss": 4.1051,
"step": 2
},
{
"epoch": 0.016666666666666666,
"grad_norm": 4.7064032554626465,
"learning_rate": 5.555555555555556e-08,
"loss": 4.1206,
"step": 3
},
{
"epoch": 0.022222222222222223,
"grad_norm": 6.4901509284973145,
"learning_rate": 8.333333333333334e-08,
"loss": 4.1424,
"step": 4
},
{
"epoch": 0.027777777777777776,
"grad_norm": 7.610614776611328,
"learning_rate": 1.1111111111111112e-07,
"loss": 4.1465,
"step": 5
},
{
"epoch": 0.03333333333333333,
"grad_norm": 7.4301910400390625,
"learning_rate": 1.3888888888888888e-07,
"loss": 4.1189,
"step": 6
},
{
"epoch": 0.03888888888888889,
"grad_norm": 5.245073318481445,
"learning_rate": 1.6666666666666668e-07,
"loss": 4.1665,
"step": 7
},
{
"epoch": 0.044444444444444446,
"grad_norm": 5.914327144622803,
"learning_rate": 1.9444444444444447e-07,
"loss": 4.1299,
"step": 8
},
{
"epoch": 0.05,
"grad_norm": 4.333767414093018,
"learning_rate": 2.2222222222222224e-07,
"loss": 4.1385,
"step": 9
},
{
"epoch": 0.05555555555555555,
"grad_norm": 4.702990531921387,
"learning_rate": 2.5000000000000004e-07,
"loss": 4.1265,
"step": 10
},
{
"epoch": 0.06111111111111111,
"grad_norm": 5.075908184051514,
"learning_rate": 2.7777777777777776e-07,
"loss": 4.1358,
"step": 11
},
{
"epoch": 0.06666666666666667,
"grad_norm": 4.498830318450928,
"learning_rate": 3.055555555555556e-07,
"loss": 4.1611,
"step": 12
},
{
"epoch": 0.07222222222222222,
"grad_norm": 4.563338756561279,
"learning_rate": 3.3333333333333335e-07,
"loss": 4.2064,
"step": 13
},
{
"epoch": 0.07777777777777778,
"grad_norm": 5.413877487182617,
"learning_rate": 3.611111111111111e-07,
"loss": 4.142,
"step": 14
},
{
"epoch": 0.08333333333333333,
"grad_norm": 5.196332931518555,
"learning_rate": 3.8888888888888895e-07,
"loss": 4.1147,
"step": 15
},
{
"epoch": 0.08888888888888889,
"grad_norm": 5.265275478363037,
"learning_rate": 4.1666666666666667e-07,
"loss": 4.1179,
"step": 16
},
{
"epoch": 0.09444444444444444,
"grad_norm": 4.644185543060303,
"learning_rate": 4.444444444444445e-07,
"loss": 4.0827,
"step": 17
},
{
"epoch": 0.1,
"grad_norm": 10.299473762512207,
"learning_rate": 4.7222222222222226e-07,
"loss": 4.1002,
"step": 18
},
{
"epoch": 0.10555555555555556,
"grad_norm": 4.808837890625,
"learning_rate": 5.000000000000001e-07,
"loss": 4.1319,
"step": 19
},
{
"epoch": 0.1111111111111111,
"grad_norm": 5.34263277053833,
"learning_rate": 5.277777777777779e-07,
"loss": 4.196,
"step": 20
},
{
"epoch": 0.11666666666666667,
"grad_norm": 5.124789237976074,
"learning_rate": 5.555555555555555e-07,
"loss": 4.1231,
"step": 21
},
{
"epoch": 0.12222222222222222,
"grad_norm": 5.223505973815918,
"learning_rate": 5.833333333333334e-07,
"loss": 4.1451,
"step": 22
},
{
"epoch": 0.12777777777777777,
"grad_norm": 43.71332550048828,
"learning_rate": 6.111111111111112e-07,
"loss": 4.1674,
"step": 23
},
{
"epoch": 0.13333333333333333,
"grad_norm": 5.156864166259766,
"learning_rate": 6.388888888888889e-07,
"loss": 4.1914,
"step": 24
},
{
"epoch": 0.1388888888888889,
"grad_norm": 4.526927471160889,
"learning_rate": 6.666666666666667e-07,
"loss": 4.1368,
"step": 25
},
{
"epoch": 0.14444444444444443,
"grad_norm": 5.298299312591553,
"learning_rate": 6.944444444444446e-07,
"loss": 4.1497,
"step": 26
},
{
"epoch": 0.15,
"grad_norm": 5.633517742156982,
"learning_rate": 7.222222222222222e-07,
"loss": 4.138,
"step": 27
},
{
"epoch": 0.15555555555555556,
"grad_norm": 5.702389717102051,
"learning_rate": 7.5e-07,
"loss": 4.1254,
"step": 28
},
{
"epoch": 0.16111111111111112,
"grad_norm": 7.551218032836914,
"learning_rate": 7.777777777777779e-07,
"loss": 4.1763,
"step": 29
},
{
"epoch": 0.16666666666666666,
"grad_norm": 4.118143558502197,
"learning_rate": 8.055555555555557e-07,
"loss": 4.1363,
"step": 30
},
{
"epoch": 0.17222222222222222,
"grad_norm": 4.370201110839844,
"learning_rate": 8.333333333333333e-07,
"loss": 4.1216,
"step": 31
},
{
"epoch": 0.17777777777777778,
"grad_norm": 4.1547088623046875,
"learning_rate": 8.611111111111112e-07,
"loss": 4.1188,
"step": 32
},
{
"epoch": 0.18333333333333332,
"grad_norm": 4.876753807067871,
"learning_rate": 8.88888888888889e-07,
"loss": 4.1796,
"step": 33
},
{
"epoch": 0.18888888888888888,
"grad_norm": 10.118820190429688,
"learning_rate": 9.166666666666666e-07,
"loss": 4.1359,
"step": 34
},
{
"epoch": 0.19444444444444445,
"grad_norm": 4.595041275024414,
"learning_rate": 9.444444444444445e-07,
"loss": 4.1092,
"step": 35
},
{
"epoch": 0.2,
"grad_norm": 8.558505058288574,
"learning_rate": 9.722222222222224e-07,
"loss": 4.1022,
"step": 36
},
{
"epoch": 0.20555555555555555,
"grad_norm": 6.260637283325195,
"learning_rate": 1.0000000000000002e-06,
"loss": 4.0724,
"step": 37
},
{
"epoch": 0.2111111111111111,
"grad_norm": 5.073309421539307,
"learning_rate": 1.0277777777777777e-06,
"loss": 4.1764,
"step": 38
},
{
"epoch": 0.21666666666666667,
"grad_norm": 4.645645618438721,
"learning_rate": 1.0555555555555557e-06,
"loss": 4.1122,
"step": 39
},
{
"epoch": 0.2222222222222222,
"grad_norm": 5.514182090759277,
"learning_rate": 1.0833333333333335e-06,
"loss": 4.1319,
"step": 40
},
{
"epoch": 0.22777777777777777,
"grad_norm": 12.317588806152344,
"learning_rate": 1.111111111111111e-06,
"loss": 4.1291,
"step": 41
},
{
"epoch": 0.23333333333333334,
"grad_norm": 7.0210113525390625,
"learning_rate": 1.138888888888889e-06,
"loss": 4.1068,
"step": 42
},
{
"epoch": 0.2388888888888889,
"grad_norm": 6.768136501312256,
"learning_rate": 1.1666666666666668e-06,
"loss": 4.1177,
"step": 43
},
{
"epoch": 0.24444444444444444,
"grad_norm": 5.266323566436768,
"learning_rate": 1.1944444444444446e-06,
"loss": 4.1007,
"step": 44
},
{
"epoch": 0.25,
"grad_norm": 4.739731788635254,
"learning_rate": 1.2222222222222223e-06,
"loss": 4.1192,
"step": 45
},
{
"epoch": 0.25555555555555554,
"grad_norm": 6.239261150360107,
"learning_rate": 1.25e-06,
"loss": 4.1065,
"step": 46
},
{
"epoch": 0.2611111111111111,
"grad_norm": 7.669517993927002,
"learning_rate": 1.2777777777777779e-06,
"loss": 4.1183,
"step": 47
},
{
"epoch": 0.26666666666666666,
"grad_norm": 6.261764049530029,
"learning_rate": 1.3055555555555556e-06,
"loss": 4.2023,
"step": 48
},
{
"epoch": 0.2722222222222222,
"grad_norm": 4.664489269256592,
"learning_rate": 1.3333333333333334e-06,
"loss": 4.1294,
"step": 49
},
{
"epoch": 0.2777777777777778,
"grad_norm": 4.4140520095825195,
"learning_rate": 1.3611111111111112e-06,
"loss": 4.1435,
"step": 50
},
{
"epoch": 0.2833333333333333,
"grad_norm": 6.362937927246094,
"learning_rate": 1.3888888888888892e-06,
"loss": 4.1341,
"step": 51
},
{
"epoch": 0.28888888888888886,
"grad_norm": 28.318382263183594,
"learning_rate": 1.4166666666666667e-06,
"loss": 4.0801,
"step": 52
},
{
"epoch": 0.29444444444444445,
"grad_norm": 38.65362548828125,
"learning_rate": 1.4444444444444445e-06,
"loss": 4.1569,
"step": 53
},
{
"epoch": 0.3,
"grad_norm": 7.488961696624756,
"learning_rate": 1.4722222222222225e-06,
"loss": 4.0841,
"step": 54
},
{
"epoch": 0.3055555555555556,
"grad_norm": 5.2586140632629395,
"learning_rate": 1.5e-06,
"loss": 4.0908,
"step": 55
},
{
"epoch": 0.3111111111111111,
"grad_norm": 5.334456920623779,
"learning_rate": 1.527777777777778e-06,
"loss": 4.1004,
"step": 56
},
{
"epoch": 0.31666666666666665,
"grad_norm": 5.478425025939941,
"learning_rate": 1.5555555555555558e-06,
"loss": 4.0952,
"step": 57
},
{
"epoch": 0.32222222222222224,
"grad_norm": 6.723354339599609,
"learning_rate": 1.5833333333333333e-06,
"loss": 4.0696,
"step": 58
},
{
"epoch": 0.3277777777777778,
"grad_norm": 4.649587631225586,
"learning_rate": 1.6111111111111113e-06,
"loss": 4.1241,
"step": 59
},
{
"epoch": 0.3333333333333333,
"grad_norm": 5.428715229034424,
"learning_rate": 1.638888888888889e-06,
"loss": 4.1658,
"step": 60
},
{
"epoch": 0.3388888888888889,
"grad_norm": 5.658595561981201,
"learning_rate": 1.6666666666666667e-06,
"loss": 4.1135,
"step": 61
},
{
"epoch": 0.34444444444444444,
"grad_norm": 107.06902313232422,
"learning_rate": 1.6944444444444446e-06,
"loss": 4.1307,
"step": 62
},
{
"epoch": 0.35,
"grad_norm": 5.702193737030029,
"learning_rate": 1.7222222222222224e-06,
"loss": 4.0456,
"step": 63
},
{
"epoch": 0.35555555555555557,
"grad_norm": 10.893062591552734,
"learning_rate": 1.75e-06,
"loss": 4.1072,
"step": 64
},
{
"epoch": 0.3611111111111111,
"grad_norm": 6.114178657531738,
"learning_rate": 1.777777777777778e-06,
"loss": 4.0841,
"step": 65
},
{
"epoch": 0.36666666666666664,
"grad_norm": 12.26750659942627,
"learning_rate": 1.8055555555555557e-06,
"loss": 4.1075,
"step": 66
},
{
"epoch": 0.37222222222222223,
"grad_norm": 8.89498519897461,
"learning_rate": 1.8333333333333333e-06,
"loss": 4.1117,
"step": 67
},
{
"epoch": 0.37777777777777777,
"grad_norm": 8.339689254760742,
"learning_rate": 1.8611111111111113e-06,
"loss": 4.1178,
"step": 68
},
{
"epoch": 0.38333333333333336,
"grad_norm": 11.912612915039062,
"learning_rate": 1.888888888888889e-06,
"loss": 4.02,
"step": 69
},
{
"epoch": 0.3888888888888889,
"grad_norm": 7.293727397918701,
"learning_rate": 1.916666666666667e-06,
"loss": 4.0333,
"step": 70
},
{
"epoch": 0.39444444444444443,
"grad_norm": 10.65302848815918,
"learning_rate": 1.944444444444445e-06,
"loss": 4.0323,
"step": 71
},
{
"epoch": 0.4,
"grad_norm": 8.193239212036133,
"learning_rate": 1.9722222222222224e-06,
"loss": 3.9554,
"step": 72
},
{
"epoch": 0.40555555555555556,
"grad_norm": 13.741752624511719,
"learning_rate": 2.0000000000000003e-06,
"loss": 4.0494,
"step": 73
},
{
"epoch": 0.4111111111111111,
"grad_norm": 11.981536865234375,
"learning_rate": 2.027777777777778e-06,
"loss": 4.0235,
"step": 74
},
{
"epoch": 0.4166666666666667,
"grad_norm": 23.27454376220703,
"learning_rate": 2.0555555555555555e-06,
"loss": 4.0849,
"step": 75
},
{
"epoch": 0.4222222222222222,
"grad_norm": 11.925698280334473,
"learning_rate": 2.0833333333333334e-06,
"loss": 4.0182,
"step": 76
},
{
"epoch": 0.42777777777777776,
"grad_norm": 9.173333168029785,
"learning_rate": 2.1111111111111114e-06,
"loss": 4.0119,
"step": 77
},
{
"epoch": 0.43333333333333335,
"grad_norm": 8.953814506530762,
"learning_rate": 2.138888888888889e-06,
"loss": 4.0022,
"step": 78
},
{
"epoch": 0.4388888888888889,
"grad_norm": 8.501323699951172,
"learning_rate": 2.166666666666667e-06,
"loss": 3.9922,
"step": 79
},
{
"epoch": 0.4444444444444444,
"grad_norm": 30.978384017944336,
"learning_rate": 2.1944444444444445e-06,
"loss": 3.9945,
"step": 80
},
{
"epoch": 0.45,
"grad_norm": 9.939839363098145,
"learning_rate": 2.222222222222222e-06,
"loss": 3.9972,
"step": 81
},
{
"epoch": 0.45555555555555555,
"grad_norm": 13.168832778930664,
"learning_rate": 2.25e-06,
"loss": 3.9616,
"step": 82
},
{
"epoch": 0.46111111111111114,
"grad_norm": 30.183183670043945,
"learning_rate": 2.277777777777778e-06,
"loss": 3.9093,
"step": 83
},
{
"epoch": 0.4666666666666667,
"grad_norm": 18.325775146484375,
"learning_rate": 2.305555555555556e-06,
"loss": 4.069,
"step": 84
},
{
"epoch": 0.4722222222222222,
"grad_norm": 20.31040382385254,
"learning_rate": 2.3333333333333336e-06,
"loss": 3.9485,
"step": 85
},
{
"epoch": 0.4777777777777778,
"grad_norm": 12.166489601135254,
"learning_rate": 2.361111111111111e-06,
"loss": 3.9644,
"step": 86
},
{
"epoch": 0.48333333333333334,
"grad_norm": 11.54350757598877,
"learning_rate": 2.388888888888889e-06,
"loss": 4.0155,
"step": 87
},
{
"epoch": 0.4888888888888889,
"grad_norm": 12.203667640686035,
"learning_rate": 2.4166666666666667e-06,
"loss": 3.9369,
"step": 88
},
{
"epoch": 0.49444444444444446,
"grad_norm": 163.48681640625,
"learning_rate": 2.4444444444444447e-06,
"loss": 3.9203,
"step": 89
},
{
"epoch": 0.5,
"grad_norm": 32.91755294799805,
"learning_rate": 2.4722222222222226e-06,
"loss": 3.9015,
"step": 90
},
{
"epoch": 0.5055555555555555,
"grad_norm": 13.690444946289062,
"learning_rate": 2.5e-06,
"loss": 3.9026,
"step": 91
},
{
"epoch": 0.5111111111111111,
"grad_norm": 9.139657974243164,
"learning_rate": 2.5277777777777778e-06,
"loss": 3.9007,
"step": 92
},
{
"epoch": 0.5166666666666667,
"grad_norm": 13.26919937133789,
"learning_rate": 2.5555555555555557e-06,
"loss": 3.8949,
"step": 93
},
{
"epoch": 0.5222222222222223,
"grad_norm": 10.40602970123291,
"learning_rate": 2.5833333333333337e-06,
"loss": 3.9827,
"step": 94
},
{
"epoch": 0.5277777777777778,
"grad_norm": 15.16673755645752,
"learning_rate": 2.6111111111111113e-06,
"loss": 3.9309,
"step": 95
},
{
"epoch": 0.5333333333333333,
"grad_norm": 16.39362907409668,
"learning_rate": 2.6388888888888893e-06,
"loss": 3.9292,
"step": 96
},
{
"epoch": 0.5388888888888889,
"grad_norm": 14.639756202697754,
"learning_rate": 2.666666666666667e-06,
"loss": 3.9167,
"step": 97
},
{
"epoch": 0.5444444444444444,
"grad_norm": 10.048202514648438,
"learning_rate": 2.6944444444444444e-06,
"loss": 3.8935,
"step": 98
},
{
"epoch": 0.55,
"grad_norm": 10.029499053955078,
"learning_rate": 2.7222222222222224e-06,
"loss": 3.8616,
"step": 99
},
{
"epoch": 0.5555555555555556,
"grad_norm": 8.698563575744629,
"learning_rate": 2.7500000000000004e-06,
"loss": 3.8979,
"step": 100
},
{
"epoch": 0.5611111111111111,
"grad_norm": 39.559139251708984,
"learning_rate": 2.7777777777777783e-06,
"loss": 3.8863,
"step": 101
},
{
"epoch": 0.5666666666666667,
"grad_norm": 21.348575592041016,
"learning_rate": 2.805555555555556e-06,
"loss": 3.8871,
"step": 102
},
{
"epoch": 0.5722222222222222,
"grad_norm": 11.112700462341309,
"learning_rate": 2.8333333333333335e-06,
"loss": 3.8732,
"step": 103
},
{
"epoch": 0.5777777777777777,
"grad_norm": 21.130285263061523,
"learning_rate": 2.861111111111111e-06,
"loss": 3.8405,
"step": 104
},
{
"epoch": 0.5833333333333334,
"grad_norm": 16.2684326171875,
"learning_rate": 2.888888888888889e-06,
"loss": 3.8668,
"step": 105
},
{
"epoch": 0.5888888888888889,
"grad_norm": 20.406702041625977,
"learning_rate": 2.916666666666667e-06,
"loss": 3.9076,
"step": 106
},
{
"epoch": 0.5944444444444444,
"grad_norm": 64.09777069091797,
"learning_rate": 2.944444444444445e-06,
"loss": 3.916,
"step": 107
},
{
"epoch": 0.6,
"grad_norm": 10.292810440063477,
"learning_rate": 2.9722222222222225e-06,
"loss": 3.7633,
"step": 108
},
{
"epoch": 0.6055555555555555,
"grad_norm": 13.03030776977539,
"learning_rate": 3e-06,
"loss": 3.8223,
"step": 109
},
{
"epoch": 0.6111111111111112,
"grad_norm": 13.965351104736328,
"learning_rate": 3.0277777777777776e-06,
"loss": 3.8961,
"step": 110
},
{
"epoch": 0.6166666666666667,
"grad_norm": 14.073107719421387,
"learning_rate": 3.055555555555556e-06,
"loss": 3.8379,
"step": 111
},
{
"epoch": 0.6222222222222222,
"grad_norm": 16.710189819335938,
"learning_rate": 3.0833333333333336e-06,
"loss": 3.8684,
"step": 112
},
{
"epoch": 0.6277777777777778,
"grad_norm": 17.995576858520508,
"learning_rate": 3.1111111111111116e-06,
"loss": 3.8839,
"step": 113
},
{
"epoch": 0.6333333333333333,
"grad_norm": 21.545984268188477,
"learning_rate": 3.138888888888889e-06,
"loss": 4.0223,
"step": 114
},
{
"epoch": 0.6388888888888888,
"grad_norm": 11.332695960998535,
"learning_rate": 3.1666666666666667e-06,
"loss": 3.8078,
"step": 115
},
{
"epoch": 0.6444444444444445,
"grad_norm": 8.465174674987793,
"learning_rate": 3.1944444444444443e-06,
"loss": 3.9519,
"step": 116
},
{
"epoch": 0.65,
"grad_norm": 56.93085861206055,
"learning_rate": 3.2222222222222227e-06,
"loss": 3.9012,
"step": 117
},
{
"epoch": 0.6555555555555556,
"grad_norm": 9.845236778259277,
"learning_rate": 3.2500000000000002e-06,
"loss": 3.7278,
"step": 118
},
{
"epoch": 0.6611111111111111,
"grad_norm": 11.970979690551758,
"learning_rate": 3.277777777777778e-06,
"loss": 3.8381,
"step": 119
},
{
"epoch": 0.6666666666666666,
"grad_norm": 21.02793312072754,
"learning_rate": 3.3055555555555558e-06,
"loss": 3.84,
"step": 120
},
{
"epoch": 0.6722222222222223,
"grad_norm": 9.825695037841797,
"learning_rate": 3.3333333333333333e-06,
"loss": 3.9232,
"step": 121
},
{
"epoch": 0.6777777777777778,
"grad_norm": 21.204036712646484,
"learning_rate": 3.3611111111111117e-06,
"loss": 3.9972,
"step": 122
},
{
"epoch": 0.6833333333333333,
"grad_norm": 11.562796592712402,
"learning_rate": 3.3888888888888893e-06,
"loss": 3.792,
"step": 123
},
{
"epoch": 0.6888888888888889,
"grad_norm": 11.700199127197266,
"learning_rate": 3.416666666666667e-06,
"loss": 3.8183,
"step": 124
},
{
"epoch": 0.6944444444444444,
"grad_norm": 15.186004638671875,
"learning_rate": 3.444444444444445e-06,
"loss": 3.7746,
"step": 125
},
{
"epoch": 0.7,
"grad_norm": 11.123403549194336,
"learning_rate": 3.4722222222222224e-06,
"loss": 3.8802,
"step": 126
},
{
"epoch": 0.7055555555555556,
"grad_norm": 40.5022087097168,
"learning_rate": 3.5e-06,
"loss": 3.7373,
"step": 127
},
{
"epoch": 0.7111111111111111,
"grad_norm": 10.47311019897461,
"learning_rate": 3.5277777777777784e-06,
"loss": 3.6909,
"step": 128
},
{
"epoch": 0.7166666666666667,
"grad_norm": 10.855074882507324,
"learning_rate": 3.555555555555556e-06,
"loss": 3.5673,
"step": 129
},
{
"epoch": 0.7222222222222222,
"grad_norm": 7.8327484130859375,
"learning_rate": 3.5833333333333335e-06,
"loss": 3.6915,
"step": 130
},
{
"epoch": 0.7277777777777777,
"grad_norm": 10.074577331542969,
"learning_rate": 3.6111111111111115e-06,
"loss": 3.854,
"step": 131
},
{
"epoch": 0.7333333333333333,
"grad_norm": 20.432024002075195,
"learning_rate": 3.638888888888889e-06,
"loss": 3.843,
"step": 132
},
{
"epoch": 0.7388888888888889,
"grad_norm": 25.029422760009766,
"learning_rate": 3.6666666666666666e-06,
"loss": 3.8326,
"step": 133
},
{
"epoch": 0.7444444444444445,
"grad_norm": 15.255012512207031,
"learning_rate": 3.694444444444445e-06,
"loss": 3.7599,
"step": 134
},
{
"epoch": 0.75,
"grad_norm": 15.387999534606934,
"learning_rate": 3.7222222222222225e-06,
"loss": 3.8546,
"step": 135
},
{
"epoch": 0.7555555555555555,
"grad_norm": 43.293087005615234,
"learning_rate": 3.7500000000000005e-06,
"loss": 3.8668,
"step": 136
},
{
"epoch": 0.7611111111111111,
"grad_norm": 11.588981628417969,
"learning_rate": 3.777777777777778e-06,
"loss": 3.691,
"step": 137
},
{
"epoch": 0.7666666666666667,
"grad_norm": 13.909408569335938,
"learning_rate": 3.8055555555555556e-06,
"loss": 3.7808,
"step": 138
},
{
"epoch": 0.7722222222222223,
"grad_norm": 20.30463409423828,
"learning_rate": 3.833333333333334e-06,
"loss": 3.783,
"step": 139
},
{
"epoch": 0.7777777777777778,
"grad_norm": 11.529065132141113,
"learning_rate": 3.861111111111112e-06,
"loss": 3.7478,
"step": 140
},
{
"epoch": 0.7833333333333333,
"grad_norm": 10.10379695892334,
"learning_rate": 3.88888888888889e-06,
"loss": 3.7624,
"step": 141
},
{
"epoch": 0.7888888888888889,
"grad_norm": 17.192270278930664,
"learning_rate": 3.916666666666667e-06,
"loss": 4.0045,
"step": 142
},
{
"epoch": 0.7944444444444444,
"grad_norm": 13.458148956298828,
"learning_rate": 3.944444444444445e-06,
"loss": 3.7876,
"step": 143
},
{
"epoch": 0.8,
"grad_norm": 13.866207122802734,
"learning_rate": 3.972222222222223e-06,
"loss": 3.7564,
"step": 144
},
{
"epoch": 0.8055555555555556,
"grad_norm": 31.844999313354492,
"learning_rate": 4.000000000000001e-06,
"loss": 3.8899,
"step": 145
},
{
"epoch": 0.8111111111111111,
"grad_norm": 12.092936515808105,
"learning_rate": 4.027777777777779e-06,
"loss": 3.8429,
"step": 146
},
{
"epoch": 0.8166666666666667,
"grad_norm": 9.821207046508789,
"learning_rate": 4.055555555555556e-06,
"loss": 3.7832,
"step": 147
},
{
"epoch": 0.8222222222222222,
"grad_norm": 50.11216354370117,
"learning_rate": 4.083333333333334e-06,
"loss": 3.9738,
"step": 148
},
{
"epoch": 0.8277777777777777,
"grad_norm": 10.7877779006958,
"learning_rate": 4.111111111111111e-06,
"loss": 3.6765,
"step": 149
},
{
"epoch": 0.8333333333333334,
"grad_norm": 14.481493949890137,
"learning_rate": 4.138888888888889e-06,
"loss": 3.8735,
"step": 150
},
{
"epoch": 0.8388888888888889,
"grad_norm": 11.584037780761719,
"learning_rate": 4.166666666666667e-06,
"loss": 3.7551,
"step": 151
},
{
"epoch": 0.8444444444444444,
"grad_norm": 14.807415008544922,
"learning_rate": 4.194444444444445e-06,
"loss": 3.6984,
"step": 152
},
{
"epoch": 0.85,
"grad_norm": 11.977572441101074,
"learning_rate": 4.222222222222223e-06,
"loss": 3.6604,
"step": 153
},
{
"epoch": 0.8555555555555555,
"grad_norm": 17.68842124938965,
"learning_rate": 4.25e-06,
"loss": 3.7205,
"step": 154
},
{
"epoch": 0.8611111111111112,
"grad_norm": 10.264474868774414,
"learning_rate": 4.277777777777778e-06,
"loss": 3.7822,
"step": 155
},
{
"epoch": 0.8666666666666667,
"grad_norm": 28.634002685546875,
"learning_rate": 4.305555555555556e-06,
"loss": 3.7703,
"step": 156
},
{
"epoch": 0.8722222222222222,
"grad_norm": 24.525835037231445,
"learning_rate": 4.333333333333334e-06,
"loss": 3.7661,
"step": 157
},
{
"epoch": 0.8777777777777778,
"grad_norm": 14.709070205688477,
"learning_rate": 4.361111111111112e-06,
"loss": 3.5583,
"step": 158
},
{
"epoch": 0.8833333333333333,
"grad_norm": 10.394603729248047,
"learning_rate": 4.388888888888889e-06,
"loss": 3.666,
"step": 159
},
{
"epoch": 0.8888888888888888,
"grad_norm": 28.80780792236328,
"learning_rate": 4.416666666666667e-06,
"loss": 3.8239,
"step": 160
},
{
"epoch": 0.8944444444444445,
"grad_norm": 26.468658447265625,
"learning_rate": 4.444444444444444e-06,
"loss": 3.6905,
"step": 161
},
{
"epoch": 0.9,
"grad_norm": 18.3535099029541,
"learning_rate": 4.472222222222223e-06,
"loss": 3.8097,
"step": 162
},
{
"epoch": 0.9055555555555556,
"grad_norm": 13.889976501464844,
"learning_rate": 4.5e-06,
"loss": 3.6188,
"step": 163
},
{
"epoch": 0.9111111111111111,
"grad_norm": 24.621137619018555,
"learning_rate": 4.527777777777778e-06,
"loss": 3.7464,
"step": 164
},
{
"epoch": 0.9166666666666666,
"grad_norm": 19.453725814819336,
"learning_rate": 4.555555555555556e-06,
"loss": 3.8346,
"step": 165
},
{
"epoch": 0.9222222222222223,
"grad_norm": 33.41889953613281,
"learning_rate": 4.583333333333333e-06,
"loss": 3.5193,
"step": 166
},
{
"epoch": 0.9277777777777778,
"grad_norm": 10.799073219299316,
"learning_rate": 4.611111111111112e-06,
"loss": 3.7953,
"step": 167
},
{
"epoch": 0.9333333333333333,
"grad_norm": 12.916830062866211,
"learning_rate": 4.638888888888889e-06,
"loss": 3.4687,
"step": 168
},
{
"epoch": 0.9388888888888889,
"grad_norm": 20.555818557739258,
"learning_rate": 4.666666666666667e-06,
"loss": 3.7847,
"step": 169
},
{
"epoch": 0.9444444444444444,
"grad_norm": 41.626956939697266,
"learning_rate": 4.694444444444445e-06,
"loss": 3.6883,
"step": 170
},
{
"epoch": 0.95,
"grad_norm": 12.75953483581543,
"learning_rate": 4.722222222222222e-06,
"loss": 3.7081,
"step": 171
},
{
"epoch": 0.9555555555555556,
"grad_norm": 13.735243797302246,
"learning_rate": 4.75e-06,
"loss": 3.7429,
"step": 172
},
{
"epoch": 0.9611111111111111,
"grad_norm": 10.36295223236084,
"learning_rate": 4.777777777777778e-06,
"loss": 3.5511,
"step": 173
},
{
"epoch": 0.9666666666666667,
"grad_norm": 16.746732711791992,
"learning_rate": 4.805555555555556e-06,
"loss": 3.6114,
"step": 174
},
{
"epoch": 0.9722222222222222,
"grad_norm": 15.615875244140625,
"learning_rate": 4.833333333333333e-06,
"loss": 3.6589,
"step": 175
},
{
"epoch": 0.9777777777777777,
"grad_norm": 15.995009422302246,
"learning_rate": 4.861111111111111e-06,
"loss": 3.7229,
"step": 176
},
{
"epoch": 0.9833333333333333,
"grad_norm": 8.263944625854492,
"learning_rate": 4.888888888888889e-06,
"loss": 3.8258,
"step": 177
},
{
"epoch": 0.9888888888888889,
"grad_norm": 23.647302627563477,
"learning_rate": 4.9166666666666665e-06,
"loss": 3.794,
"step": 178
},
{
"epoch": 0.9944444444444445,
"grad_norm": 11.301065444946289,
"learning_rate": 4.944444444444445e-06,
"loss": 3.672,
"step": 179
},
{
"epoch": 1.0,
"grad_norm": 18.397125244140625,
"learning_rate": 4.9722222222222224e-06,
"loss": 3.6893,
"step": 180
},
{
"epoch": 1.0,
"eval_accuracy": 0.12001967535661584,
"eval_f1": 0.04535683373295075,
"eval_loss": 3.579214334487915,
"eval_runtime": 2.8914,
"eval_samples_per_second": 703.116,
"eval_steps_per_second": 5.534,
"step": 180
},
{
"epoch": 1.0055555555555555,
"grad_norm": 22.7191162109375,
"learning_rate": 5e-06,
"loss": 3.5931,
"step": 181
},
{
"epoch": 1.011111111111111,
"grad_norm": 24.69613265991211,
"learning_rate": 5.027777777777778e-06,
"loss": 3.6878,
"step": 182
},
{
"epoch": 1.0166666666666666,
"grad_norm": 15.228057861328125,
"learning_rate": 5.0555555555555555e-06,
"loss": 3.8653,
"step": 183
},
{
"epoch": 1.0222222222222221,
"grad_norm": 14.06668472290039,
"learning_rate": 5.0833333333333335e-06,
"loss": 3.7833,
"step": 184
},
{
"epoch": 1.0277777777777777,
"grad_norm": 12.420816421508789,
"learning_rate": 5.1111111111111115e-06,
"loss": 3.7899,
"step": 185
},
{
"epoch": 1.0333333333333334,
"grad_norm": 15.338077545166016,
"learning_rate": 5.138888888888889e-06,
"loss": 3.6671,
"step": 186
},
{
"epoch": 1.038888888888889,
"grad_norm": 15.325353622436523,
"learning_rate": 5.1666666666666675e-06,
"loss": 3.4967,
"step": 187
},
{
"epoch": 1.0444444444444445,
"grad_norm": 18.684890747070312,
"learning_rate": 5.1944444444444454e-06,
"loss": 3.538,
"step": 188
},
{
"epoch": 1.05,
"grad_norm": 15.555322647094727,
"learning_rate": 5.2222222222222226e-06,
"loss": 3.6119,
"step": 189
},
{
"epoch": 1.0555555555555556,
"grad_norm": 19.726924896240234,
"learning_rate": 5.2500000000000006e-06,
"loss": 3.617,
"step": 190
},
{
"epoch": 1.0611111111111111,
"grad_norm": 11.480026245117188,
"learning_rate": 5.2777777777777785e-06,
"loss": 3.5904,
"step": 191
},
{
"epoch": 1.0666666666666667,
"grad_norm": 9.713390350341797,
"learning_rate": 5.305555555555556e-06,
"loss": 3.4844,
"step": 192
},
{
"epoch": 1.0722222222222222,
"grad_norm": 13.147812843322754,
"learning_rate": 5.333333333333334e-06,
"loss": 3.6065,
"step": 193
},
{
"epoch": 1.0777777777777777,
"grad_norm": 22.2036075592041,
"learning_rate": 5.361111111111112e-06,
"loss": 3.6436,
"step": 194
},
{
"epoch": 1.0833333333333333,
"grad_norm": 11.390979766845703,
"learning_rate": 5.388888888888889e-06,
"loss": 3.525,
"step": 195
},
{
"epoch": 1.0888888888888888,
"grad_norm": 18.610198974609375,
"learning_rate": 5.416666666666667e-06,
"loss": 3.471,
"step": 196
},
{
"epoch": 1.0944444444444446,
"grad_norm": 16.214649200439453,
"learning_rate": 5.444444444444445e-06,
"loss": 3.558,
"step": 197
},
{
"epoch": 1.1,
"grad_norm": 13.904134750366211,
"learning_rate": 5.4722222222222236e-06,
"loss": 3.4583,
"step": 198
},
{
"epoch": 1.1055555555555556,
"grad_norm": 12.090760231018066,
"learning_rate": 5.500000000000001e-06,
"loss": 3.5855,
"step": 199
},
{
"epoch": 1.1111111111111112,
"grad_norm": 9.406524658203125,
"learning_rate": 5.527777777777779e-06,
"loss": 3.6545,
"step": 200
},
{
"epoch": 1.1166666666666667,
"grad_norm": 23.59896469116211,
"learning_rate": 5.555555555555557e-06,
"loss": 3.5735,
"step": 201
},
{
"epoch": 1.1222222222222222,
"grad_norm": 11.156173706054688,
"learning_rate": 5.583333333333334e-06,
"loss": 3.5771,
"step": 202
},
{
"epoch": 1.1277777777777778,
"grad_norm": 11.13250732421875,
"learning_rate": 5.611111111111112e-06,
"loss": 3.3528,
"step": 203
},
{
"epoch": 1.1333333333333333,
"grad_norm": 36.53647994995117,
"learning_rate": 5.638888888888889e-06,
"loss": 3.583,
"step": 204
},
{
"epoch": 1.1388888888888888,
"grad_norm": 14.955141067504883,
"learning_rate": 5.666666666666667e-06,
"loss": 3.3883,
"step": 205
},
{
"epoch": 1.1444444444444444,
"grad_norm": 11.572168350219727,
"learning_rate": 5.694444444444445e-06,
"loss": 3.3846,
"step": 206
},
{
"epoch": 1.15,
"grad_norm": 16.62725257873535,
"learning_rate": 5.722222222222222e-06,
"loss": 3.4832,
"step": 207
},
{
"epoch": 1.1555555555555554,
"grad_norm": 21.308473587036133,
"learning_rate": 5.75e-06,
"loss": 3.4023,
"step": 208
},
{
"epoch": 1.1611111111111112,
"grad_norm": 43.056724548339844,
"learning_rate": 5.777777777777778e-06,
"loss": 3.3994,
"step": 209
},
{
"epoch": 1.1666666666666667,
"grad_norm": 11.334895133972168,
"learning_rate": 5.805555555555557e-06,
"loss": 3.5975,
"step": 210
},
{
"epoch": 1.1722222222222223,
"grad_norm": 16.92284393310547,
"learning_rate": 5.833333333333334e-06,
"loss": 3.4485,
"step": 211
},
{
"epoch": 1.1777777777777778,
"grad_norm": 12.656438827514648,
"learning_rate": 5.861111111111112e-06,
"loss": 3.325,
"step": 212
},
{
"epoch": 1.1833333333333333,
"grad_norm": 24.20313835144043,
"learning_rate": 5.88888888888889e-06,
"loss": 3.3566,
"step": 213
},
{
"epoch": 1.1888888888888889,
"grad_norm": 18.851669311523438,
"learning_rate": 5.916666666666667e-06,
"loss": 3.1616,
"step": 214
},
{
"epoch": 1.1944444444444444,
"grad_norm": 11.211307525634766,
"learning_rate": 5.944444444444445e-06,
"loss": 3.4888,
"step": 215
},
{
"epoch": 1.2,
"grad_norm": 11.438482284545898,
"learning_rate": 5.972222222222222e-06,
"loss": 3.3552,
"step": 216
},
{
"epoch": 1.2055555555555555,
"grad_norm": 11.509745597839355,
"learning_rate": 6e-06,
"loss": 3.3466,
"step": 217
},
{
"epoch": 1.211111111111111,
"grad_norm": 13.9913911819458,
"learning_rate": 6.027777777777778e-06,
"loss": 3.2673,
"step": 218
},
{
"epoch": 1.2166666666666668,
"grad_norm": 130.21192932128906,
"learning_rate": 6.055555555555555e-06,
"loss": 3.5651,
"step": 219
},
{
"epoch": 1.2222222222222223,
"grad_norm": 21.862506866455078,
"learning_rate": 6.083333333333333e-06,
"loss": 3.3409,
"step": 220
},
{
"epoch": 1.2277777777777779,
"grad_norm": 23.765527725219727,
"learning_rate": 6.111111111111112e-06,
"loss": 3.2403,
"step": 221
},
{
"epoch": 1.2333333333333334,
"grad_norm": 11.672707557678223,
"learning_rate": 6.13888888888889e-06,
"loss": 3.2493,
"step": 222
},
{
"epoch": 1.238888888888889,
"grad_norm": 17.45976448059082,
"learning_rate": 6.166666666666667e-06,
"loss": 3.1824,
"step": 223
},
{
"epoch": 1.2444444444444445,
"grad_norm": 16.412628173828125,
"learning_rate": 6.194444444444445e-06,
"loss": 3.5488,
"step": 224
},
{
"epoch": 1.25,
"grad_norm": 34.69322967529297,
"learning_rate": 6.222222222222223e-06,
"loss": 3.2423,
"step": 225
},
{
"epoch": 1.2555555555555555,
"grad_norm": 22.06356430053711,
"learning_rate": 6.25e-06,
"loss": 3.1933,
"step": 226
},
{
"epoch": 1.261111111111111,
"grad_norm": 16.41312599182129,
"learning_rate": 6.277777777777778e-06,
"loss": 3.5204,
"step": 227
},
{
"epoch": 1.2666666666666666,
"grad_norm": 14.862792015075684,
"learning_rate": 6.305555555555556e-06,
"loss": 3.3176,
"step": 228
},
{
"epoch": 1.2722222222222221,
"grad_norm": 23.367313385009766,
"learning_rate": 6.333333333333333e-06,
"loss": 2.9674,
"step": 229
},
{
"epoch": 1.2777777777777777,
"grad_norm": 13.833514213562012,
"learning_rate": 6.361111111111111e-06,
"loss": 3.105,
"step": 230
},
{
"epoch": 1.2833333333333332,
"grad_norm": 12.70186996459961,
"learning_rate": 6.3888888888888885e-06,
"loss": 3.2252,
"step": 231
},
{
"epoch": 1.2888888888888888,
"grad_norm": 40.14986801147461,
"learning_rate": 6.416666666666667e-06,
"loss": 3.0691,
"step": 232
},
{
"epoch": 1.2944444444444445,
"grad_norm": 16.90121078491211,
"learning_rate": 6.444444444444445e-06,
"loss": 3.2575,
"step": 233
},
{
"epoch": 1.3,
"grad_norm": 16.685184478759766,
"learning_rate": 6.472222222222223e-06,
"loss": 3.0708,
"step": 234
},
{
"epoch": 1.3055555555555556,
"grad_norm": 23.850502014160156,
"learning_rate": 6.5000000000000004e-06,
"loss": 3.1854,
"step": 235
},
{
"epoch": 1.3111111111111111,
"grad_norm": 14.032386779785156,
"learning_rate": 6.5277777777777784e-06,
"loss": 3.1015,
"step": 236
},
{
"epoch": 1.3166666666666667,
"grad_norm": 14.467909812927246,
"learning_rate": 6.555555555555556e-06,
"loss": 2.9402,
"step": 237
},
{
"epoch": 1.3222222222222222,
"grad_norm": 17.02686309814453,
"learning_rate": 6.5833333333333335e-06,
"loss": 3.016,
"step": 238
},
{
"epoch": 1.3277777777777777,
"grad_norm": 14.61024284362793,
"learning_rate": 6.6111111111111115e-06,
"loss": 3.2595,
"step": 239
},
{
"epoch": 1.3333333333333333,
"grad_norm": 17.891231536865234,
"learning_rate": 6.6388888888888895e-06,
"loss": 3.1616,
"step": 240
},
{
"epoch": 1.338888888888889,
"grad_norm": 23.58655548095703,
"learning_rate": 6.666666666666667e-06,
"loss": 2.9068,
"step": 241
},
{
"epoch": 1.3444444444444446,
"grad_norm": 15.087101936340332,
"learning_rate": 6.694444444444445e-06,
"loss": 2.9812,
"step": 242
},
{
"epoch": 1.35,
"grad_norm": 24.139636993408203,
"learning_rate": 6.7222222222222235e-06,
"loss": 2.9226,
"step": 243
},
{
"epoch": 1.3555555555555556,
"grad_norm": 15.565838813781738,
"learning_rate": 6.750000000000001e-06,
"loss": 2.9012,
"step": 244
},
{
"epoch": 1.3611111111111112,
"grad_norm": 23.724470138549805,
"learning_rate": 6.777777777777779e-06,
"loss": 3.1138,
"step": 245
},
{
"epoch": 1.3666666666666667,
"grad_norm": 22.047719955444336,
"learning_rate": 6.8055555555555566e-06,
"loss": 3.0031,
"step": 246
},
{
"epoch": 1.3722222222222222,
"grad_norm": 16.867589950561523,
"learning_rate": 6.833333333333334e-06,
"loss": 3.1366,
"step": 247
},
{
"epoch": 1.3777777777777778,
"grad_norm": 20.046964645385742,
"learning_rate": 6.861111111111112e-06,
"loss": 2.9137,
"step": 248
},
{
"epoch": 1.3833333333333333,
"grad_norm": 15.02257251739502,
"learning_rate": 6.88888888888889e-06,
"loss": 2.934,
"step": 249
},
{
"epoch": 1.3888888888888888,
"grad_norm": 42.61557388305664,
"learning_rate": 6.916666666666667e-06,
"loss": 2.8577,
"step": 250
},
{
"epoch": 1.3944444444444444,
"grad_norm": 18.856422424316406,
"learning_rate": 6.944444444444445e-06,
"loss": 2.8576,
"step": 251
},
{
"epoch": 1.4,
"grad_norm": 16.575502395629883,
"learning_rate": 6.972222222222223e-06,
"loss": 2.8727,
"step": 252
},
{
"epoch": 1.4055555555555554,
"grad_norm": 13.752829551696777,
"learning_rate": 7e-06,
"loss": 3.0375,
"step": 253
},
{
"epoch": 1.411111111111111,
"grad_norm": 49.23650360107422,
"learning_rate": 7.027777777777778e-06,
"loss": 2.9384,
"step": 254
},
{
"epoch": 1.4166666666666667,
"grad_norm": 13.141080856323242,
"learning_rate": 7.055555555555557e-06,
"loss": 2.5641,
"step": 255
},
{
"epoch": 1.4222222222222223,
"grad_norm": 31.133256912231445,
"learning_rate": 7.083333333333335e-06,
"loss": 2.5926,
"step": 256
},
{
"epoch": 1.4277777777777778,
"grad_norm": 16.165122985839844,
"learning_rate": 7.111111111111112e-06,
"loss": 2.8669,
"step": 257
},
{
"epoch": 1.4333333333333333,
"grad_norm": 14.4251070022583,
"learning_rate": 7.13888888888889e-06,
"loss": 2.8429,
"step": 258
},
{
"epoch": 1.4388888888888889,
"grad_norm": 13.628756523132324,
"learning_rate": 7.166666666666667e-06,
"loss": 2.7703,
"step": 259
},
{
"epoch": 1.4444444444444444,
"grad_norm": 22.358509063720703,
"learning_rate": 7.194444444444445e-06,
"loss": 2.8326,
"step": 260
},
{
"epoch": 1.45,
"grad_norm": 14.839126586914062,
"learning_rate": 7.222222222222223e-06,
"loss": 2.8008,
"step": 261
},
{
"epoch": 1.4555555555555555,
"grad_norm": 17.905973434448242,
"learning_rate": 7.25e-06,
"loss": 2.525,
"step": 262
},
{
"epoch": 1.4611111111111112,
"grad_norm": 18.278423309326172,
"learning_rate": 7.277777777777778e-06,
"loss": 2.5985,
"step": 263
},
{
"epoch": 1.4666666666666668,
"grad_norm": 19.472043991088867,
"learning_rate": 7.305555555555556e-06,
"loss": 2.9013,
"step": 264
},
{
"epoch": 1.4722222222222223,
"grad_norm": 24.77790069580078,
"learning_rate": 7.333333333333333e-06,
"loss": 2.9599,
"step": 265
},
{
"epoch": 1.4777777777777779,
"grad_norm": 20.52468490600586,
"learning_rate": 7.361111111111112e-06,
"loss": 2.8339,
"step": 266
},
{
"epoch": 1.4833333333333334,
"grad_norm": 15.552793502807617,
"learning_rate": 7.38888888888889e-06,
"loss": 2.5508,
"step": 267
},
{
"epoch": 1.488888888888889,
"grad_norm": 16.640884399414062,
"learning_rate": 7.416666666666668e-06,
"loss": 2.7068,
"step": 268
},
{
"epoch": 1.4944444444444445,
"grad_norm": 22.086748123168945,
"learning_rate": 7.444444444444445e-06,
"loss": 2.3745,
"step": 269
},
{
"epoch": 1.5,
"grad_norm": 28.595386505126953,
"learning_rate": 7.472222222222223e-06,
"loss": 2.2807,
"step": 270
},
{
"epoch": 1.5055555555555555,
"grad_norm": 22.305665969848633,
"learning_rate": 7.500000000000001e-06,
"loss": 2.4879,
"step": 271
},
{
"epoch": 1.511111111111111,
"grad_norm": 21.8713436126709,
"learning_rate": 7.527777777777778e-06,
"loss": 2.3203,
"step": 272
},
{
"epoch": 1.5166666666666666,
"grad_norm": 48.42641830444336,
"learning_rate": 7.555555555555556e-06,
"loss": 2.4605,
"step": 273
},
{
"epoch": 1.5222222222222221,
"grad_norm": 38.696590423583984,
"learning_rate": 7.583333333333333e-06,
"loss": 2.3577,
"step": 274
},
{
"epoch": 1.5277777777777777,
"grad_norm": 15.727502822875977,
"learning_rate": 7.611111111111111e-06,
"loss": 2.3625,
"step": 275
},
{
"epoch": 1.5333333333333332,
"grad_norm": 21.75139045715332,
"learning_rate": 7.638888888888888e-06,
"loss": 2.3435,
"step": 276
},
{
"epoch": 1.5388888888888888,
"grad_norm": 14.364039421081543,
"learning_rate": 7.666666666666667e-06,
"loss": 2.6589,
"step": 277
},
{
"epoch": 1.5444444444444443,
"grad_norm": 22.9813175201416,
"learning_rate": 7.694444444444446e-06,
"loss": 2.369,
"step": 278
},
{
"epoch": 1.55,
"grad_norm": 21.34369468688965,
"learning_rate": 7.722222222222223e-06,
"loss": 2.4665,
"step": 279
},
{
"epoch": 1.5555555555555556,
"grad_norm": 22.814451217651367,
"learning_rate": 7.75e-06,
"loss": 2.1296,
"step": 280
},
{
"epoch": 1.5611111111111111,
"grad_norm": 17.855846405029297,
"learning_rate": 7.77777777777778e-06,
"loss": 2.4808,
"step": 281
},
{
"epoch": 1.5666666666666667,
"grad_norm": 18.308576583862305,
"learning_rate": 7.805555555555556e-06,
"loss": 2.4327,
"step": 282
},
{
"epoch": 1.5722222222222222,
"grad_norm": 18.071813583374023,
"learning_rate": 7.833333333333333e-06,
"loss": 2.5731,
"step": 283
},
{
"epoch": 1.5777777777777777,
"grad_norm": 16.409578323364258,
"learning_rate": 7.861111111111112e-06,
"loss": 2.6145,
"step": 284
},
{
"epoch": 1.5833333333333335,
"grad_norm": 22.855844497680664,
"learning_rate": 7.88888888888889e-06,
"loss": 2.266,
"step": 285
},
{
"epoch": 1.588888888888889,
"grad_norm": 19.853328704833984,
"learning_rate": 7.916666666666667e-06,
"loss": 2.2657,
"step": 286
},
{
"epoch": 1.5944444444444446,
"grad_norm": 16.35372543334961,
"learning_rate": 7.944444444444445e-06,
"loss": 2.5587,
"step": 287
},
{
"epoch": 1.6,
"grad_norm": 21.4392147064209,
"learning_rate": 7.972222222222224e-06,
"loss": 2.1677,
"step": 288
},
{
"epoch": 1.6055555555555556,
"grad_norm": 46.995506286621094,
"learning_rate": 8.000000000000001e-06,
"loss": 2.372,
"step": 289
},
{
"epoch": 1.6111111111111112,
"grad_norm": 15.186579704284668,
"learning_rate": 8.027777777777778e-06,
"loss": 1.907,
"step": 290
},
{
"epoch": 1.6166666666666667,
"grad_norm": 22.092735290527344,
"learning_rate": 8.055555555555557e-06,
"loss": 2.2826,
"step": 291
},
{
"epoch": 1.6222222222222222,
"grad_norm": 16.98384666442871,
"learning_rate": 8.083333333333334e-06,
"loss": 2.1729,
"step": 292
},
{
"epoch": 1.6277777777777778,
"grad_norm": 18.72526741027832,
"learning_rate": 8.111111111111112e-06,
"loss": 2.5985,
"step": 293
},
{
"epoch": 1.6333333333333333,
"grad_norm": 17.541606903076172,
"learning_rate": 8.138888888888889e-06,
"loss": 2.4052,
"step": 294
},
{
"epoch": 1.6388888888888888,
"grad_norm": 24.825504302978516,
"learning_rate": 8.166666666666668e-06,
"loss": 2.2735,
"step": 295
},
{
"epoch": 1.6444444444444444,
"grad_norm": 32.080352783203125,
"learning_rate": 8.194444444444445e-06,
"loss": 2.1695,
"step": 296
},
{
"epoch": 1.65,
"grad_norm": 23.4326171875,
"learning_rate": 8.222222222222222e-06,
"loss": 2.513,
"step": 297
},
{
"epoch": 1.6555555555555554,
"grad_norm": 14.355706214904785,
"learning_rate": 8.25e-06,
"loss": 2.2118,
"step": 298
},
{
"epoch": 1.661111111111111,
"grad_norm": 13.754494667053223,
"learning_rate": 8.277777777777778e-06,
"loss": 2.1299,
"step": 299
},
{
"epoch": 1.6666666666666665,
"grad_norm": 19.46533203125,
"learning_rate": 8.305555555555557e-06,
"loss": 2.4587,
"step": 300
},
{
"epoch": 1.6722222222222223,
"grad_norm": 21.071548461914062,
"learning_rate": 8.333333333333334e-06,
"loss": 2.0699,
"step": 301
},
{
"epoch": 1.6777777777777778,
"grad_norm": 19.370567321777344,
"learning_rate": 8.361111111111113e-06,
"loss": 1.9161,
"step": 302
},
{
"epoch": 1.6833333333333333,
"grad_norm": 13.328511238098145,
"learning_rate": 8.38888888888889e-06,
"loss": 2.5353,
"step": 303
},
{
"epoch": 1.6888888888888889,
"grad_norm": 28.2664794921875,
"learning_rate": 8.416666666666667e-06,
"loss": 2.1742,
"step": 304
},
{
"epoch": 1.6944444444444444,
"grad_norm": 19.19120979309082,
"learning_rate": 8.444444444444446e-06,
"loss": 2.0403,
"step": 305
},
{
"epoch": 1.7,
"grad_norm": 26.475072860717773,
"learning_rate": 8.472222222222223e-06,
"loss": 2.181,
"step": 306
},
{
"epoch": 1.7055555555555557,
"grad_norm": 17.578105926513672,
"learning_rate": 8.5e-06,
"loss": 2.1551,
"step": 307
},
{
"epoch": 1.7111111111111112,
"grad_norm": 13.226629257202148,
"learning_rate": 8.527777777777779e-06,
"loss": 2.1772,
"step": 308
},
{
"epoch": 1.7166666666666668,
"grad_norm": 13.378127098083496,
"learning_rate": 8.555555555555556e-06,
"loss": 2.0563,
"step": 309
},
{
"epoch": 1.7222222222222223,
"grad_norm": 19.902542114257812,
"learning_rate": 8.583333333333333e-06,
"loss": 2.319,
"step": 310
},
{
"epoch": 1.7277777777777779,
"grad_norm": 21.442649841308594,
"learning_rate": 8.611111111111112e-06,
"loss": 1.952,
"step": 311
},
{
"epoch": 1.7333333333333334,
"grad_norm": 19.3289852142334,
"learning_rate": 8.63888888888889e-06,
"loss": 1.9582,
"step": 312
},
{
"epoch": 1.738888888888889,
"grad_norm": 20.37160873413086,
"learning_rate": 8.666666666666668e-06,
"loss": 2.1145,
"step": 313
},
{
"epoch": 1.7444444444444445,
"grad_norm": 16.45627784729004,
"learning_rate": 8.694444444444445e-06,
"loss": 2.0508,
"step": 314
},
{
"epoch": 1.75,
"grad_norm": 18.682024002075195,
"learning_rate": 8.722222222222224e-06,
"loss": 1.9561,
"step": 315
},
{
"epoch": 1.7555555555555555,
"grad_norm": 26.4896240234375,
"learning_rate": 8.750000000000001e-06,
"loss": 1.9889,
"step": 316
},
{
"epoch": 1.761111111111111,
"grad_norm": 23.66691017150879,
"learning_rate": 8.777777777777778e-06,
"loss": 1.9223,
"step": 317
},
{
"epoch": 1.7666666666666666,
"grad_norm": 14.029779434204102,
"learning_rate": 8.805555555555557e-06,
"loss": 1.8923,
"step": 318
},
{
"epoch": 1.7722222222222221,
"grad_norm": 16.57061195373535,
"learning_rate": 8.833333333333334e-06,
"loss": 2.0714,
"step": 319
},
{
"epoch": 1.7777777777777777,
"grad_norm": 17.75753402709961,
"learning_rate": 8.861111111111111e-06,
"loss": 1.7821,
"step": 320
},
{
"epoch": 1.7833333333333332,
"grad_norm": 14.73956298828125,
"learning_rate": 8.888888888888888e-06,
"loss": 1.7483,
"step": 321
},
{
"epoch": 1.7888888888888888,
"grad_norm": 20.903541564941406,
"learning_rate": 8.916666666666667e-06,
"loss": 1.9771,
"step": 322
},
{
"epoch": 1.7944444444444443,
"grad_norm": 18.499048233032227,
"learning_rate": 8.944444444444446e-06,
"loss": 1.8105,
"step": 323
},
{
"epoch": 1.8,
"grad_norm": 15.95904541015625,
"learning_rate": 8.972222222222223e-06,
"loss": 1.8252,
"step": 324
},
{
"epoch": 1.8055555555555556,
"grad_norm": 36.13191604614258,
"learning_rate": 9e-06,
"loss": 1.9707,
"step": 325
},
{
"epoch": 1.8111111111111111,
"grad_norm": 13.875724792480469,
"learning_rate": 9.027777777777779e-06,
"loss": 1.7275,
"step": 326
},
{
"epoch": 1.8166666666666667,
"grad_norm": 15.674965858459473,
"learning_rate": 9.055555555555556e-06,
"loss": 1.9271,
"step": 327
},
{
"epoch": 1.8222222222222222,
"grad_norm": 24.358997344970703,
"learning_rate": 9.083333333333333e-06,
"loss": 1.9306,
"step": 328
},
{
"epoch": 1.8277777777777777,
"grad_norm": 13.678277015686035,
"learning_rate": 9.111111111111112e-06,
"loss": 1.8447,
"step": 329
},
{
"epoch": 1.8333333333333335,
"grad_norm": 39.43601608276367,
"learning_rate": 9.13888888888889e-06,
"loss": 1.8097,
"step": 330
},
{
"epoch": 1.838888888888889,
"grad_norm": 34.79096984863281,
"learning_rate": 9.166666666666666e-06,
"loss": 1.8734,
"step": 331
},
{
"epoch": 1.8444444444444446,
"grad_norm": 27.337646484375,
"learning_rate": 9.194444444444445e-06,
"loss": 1.9912,
"step": 332
},
{
"epoch": 1.85,
"grad_norm": 24.282135009765625,
"learning_rate": 9.222222222222224e-06,
"loss": 1.6245,
"step": 333
},
{
"epoch": 1.8555555555555556,
"grad_norm": 29.253034591674805,
"learning_rate": 9.250000000000001e-06,
"loss": 1.7628,
"step": 334
},
{
"epoch": 1.8611111111111112,
"grad_norm": 16.027637481689453,
"learning_rate": 9.277777777777778e-06,
"loss": 1.9186,
"step": 335
},
{
"epoch": 1.8666666666666667,
"grad_norm": 19.844345092773438,
"learning_rate": 9.305555555555557e-06,
"loss": 1.7416,
"step": 336
},
{
"epoch": 1.8722222222222222,
"grad_norm": 15.048466682434082,
"learning_rate": 9.333333333333334e-06,
"loss": 1.2775,
"step": 337
},
{
"epoch": 1.8777777777777778,
"grad_norm": 14.998923301696777,
"learning_rate": 9.361111111111111e-06,
"loss": 1.651,
"step": 338
},
{
"epoch": 1.8833333333333333,
"grad_norm": 18.69540786743164,
"learning_rate": 9.38888888888889e-06,
"loss": 1.5596,
"step": 339
},
{
"epoch": 1.8888888888888888,
"grad_norm": 30.10553550720215,
"learning_rate": 9.416666666666667e-06,
"loss": 1.9366,
"step": 340
},
{
"epoch": 1.8944444444444444,
"grad_norm": 22.98797607421875,
"learning_rate": 9.444444444444445e-06,
"loss": 1.5739,
"step": 341
},
{
"epoch": 1.9,
"grad_norm": 46.54941177368164,
"learning_rate": 9.472222222222223e-06,
"loss": 1.3321,
"step": 342
},
{
"epoch": 1.9055555555555554,
"grad_norm": 17.774749755859375,
"learning_rate": 9.5e-06,
"loss": 1.7083,
"step": 343
},
{
"epoch": 1.911111111111111,
"grad_norm": 16.54140853881836,
"learning_rate": 9.527777777777778e-06,
"loss": 1.7137,
"step": 344
},
{
"epoch": 1.9166666666666665,
"grad_norm": 14.296022415161133,
"learning_rate": 9.555555555555556e-06,
"loss": 1.4554,
"step": 345
},
{
"epoch": 1.9222222222222223,
"grad_norm": 26.51090431213379,
"learning_rate": 9.583333333333335e-06,
"loss": 1.7057,
"step": 346
},
{
"epoch": 1.9277777777777778,
"grad_norm": 15.130067825317383,
"learning_rate": 9.611111111111112e-06,
"loss": 1.6924,
"step": 347
},
{
"epoch": 1.9333333333333333,
"grad_norm": 14.738222122192383,
"learning_rate": 9.63888888888889e-06,
"loss": 1.467,
"step": 348
},
{
"epoch": 1.9388888888888889,
"grad_norm": 16.576757431030273,
"learning_rate": 9.666666666666667e-06,
"loss": 1.6356,
"step": 349
},
{
"epoch": 1.9444444444444444,
"grad_norm": 27.14195442199707,
"learning_rate": 9.694444444444446e-06,
"loss": 1.5427,
"step": 350
},
{
"epoch": 1.95,
"grad_norm": 14.98337459564209,
"learning_rate": 9.722222222222223e-06,
"loss": 1.6452,
"step": 351
},
{
"epoch": 1.9555555555555557,
"grad_norm": 15.703158378601074,
"learning_rate": 9.75e-06,
"loss": 1.4651,
"step": 352
},
{
"epoch": 1.9611111111111112,
"grad_norm": 19.87487030029297,
"learning_rate": 9.777777777777779e-06,
"loss": 1.7653,
"step": 353
},
{
"epoch": 1.9666666666666668,
"grad_norm": 25.070276260375977,
"learning_rate": 9.805555555555556e-06,
"loss": 1.5378,
"step": 354
},
{
"epoch": 1.9722222222222223,
"grad_norm": 21.710493087768555,
"learning_rate": 9.833333333333333e-06,
"loss": 1.5154,
"step": 355
},
{
"epoch": 1.9777777777777779,
"grad_norm": 103.46601867675781,
"learning_rate": 9.861111111111112e-06,
"loss": 1.8748,
"step": 356
},
{
"epoch": 1.9833333333333334,
"grad_norm": 18.06473731994629,
"learning_rate": 9.88888888888889e-06,
"loss": 1.588,
"step": 357
},
{
"epoch": 1.988888888888889,
"grad_norm": 27.67949676513672,
"learning_rate": 9.916666666666668e-06,
"loss": 1.4883,
"step": 358
},
{
"epoch": 1.9944444444444445,
"grad_norm": 21.220842361450195,
"learning_rate": 9.944444444444445e-06,
"loss": 1.4997,
"step": 359
},
{
"epoch": 2.0,
"grad_norm": 16.899511337280273,
"learning_rate": 9.972222222222224e-06,
"loss": 1.8012,
"step": 360
},
{
"epoch": 2.0,
"eval_accuracy": 0.692080668962125,
"eval_f1": 0.6449624489307108,
"eval_loss": 1.308667778968811,
"eval_runtime": 2.8459,
"eval_samples_per_second": 714.365,
"eval_steps_per_second": 5.622,
"step": 360
},
{
"epoch": 2.0055555555555555,
"grad_norm": 21.62255859375,
"learning_rate": 1e-05,
"loss": 1.5445,
"step": 361
},
{
"epoch": 2.011111111111111,
"grad_norm": 32.52965545654297,
"learning_rate": 9.996913580246915e-06,
"loss": 1.4491,
"step": 362
},
{
"epoch": 2.0166666666666666,
"grad_norm": 16.93292808532715,
"learning_rate": 9.993827160493827e-06,
"loss": 1.2142,
"step": 363
},
{
"epoch": 2.022222222222222,
"grad_norm": 20.835256576538086,
"learning_rate": 9.990740740740741e-06,
"loss": 1.3098,
"step": 364
},
{
"epoch": 2.0277777777777777,
"grad_norm": 22.384275436401367,
"learning_rate": 9.987654320987655e-06,
"loss": 1.6411,
"step": 365
},
{
"epoch": 2.033333333333333,
"grad_norm": 55.34566879272461,
"learning_rate": 9.98456790123457e-06,
"loss": 1.3867,
"step": 366
},
{
"epoch": 2.0388888888888888,
"grad_norm": 17.221656799316406,
"learning_rate": 9.981481481481482e-06,
"loss": 1.6166,
"step": 367
},
{
"epoch": 2.0444444444444443,
"grad_norm": 18.79058837890625,
"learning_rate": 9.978395061728396e-06,
"loss": 1.5602,
"step": 368
},
{
"epoch": 2.05,
"grad_norm": 24.828041076660156,
"learning_rate": 9.97530864197531e-06,
"loss": 1.4528,
"step": 369
},
{
"epoch": 2.0555555555555554,
"grad_norm": 15.111597061157227,
"learning_rate": 9.972222222222224e-06,
"loss": 1.5901,
"step": 370
},
{
"epoch": 2.061111111111111,
"grad_norm": 19.16140365600586,
"learning_rate": 9.969135802469136e-06,
"loss": 1.6298,
"step": 371
},
{
"epoch": 2.066666666666667,
"grad_norm": 25.3825626373291,
"learning_rate": 9.96604938271605e-06,
"loss": 1.4654,
"step": 372
},
{
"epoch": 2.0722222222222224,
"grad_norm": 31.765539169311523,
"learning_rate": 9.962962962962964e-06,
"loss": 1.2992,
"step": 373
},
{
"epoch": 2.077777777777778,
"grad_norm": 30.338050842285156,
"learning_rate": 9.959876543209878e-06,
"loss": 1.6509,
"step": 374
},
{
"epoch": 2.0833333333333335,
"grad_norm": 22.79159927368164,
"learning_rate": 9.95679012345679e-06,
"loss": 1.2732,
"step": 375
},
{
"epoch": 2.088888888888889,
"grad_norm": 16.882936477661133,
"learning_rate": 9.953703703703704e-06,
"loss": 1.236,
"step": 376
},
{
"epoch": 2.0944444444444446,
"grad_norm": 34.00654983520508,
"learning_rate": 9.950617283950618e-06,
"loss": 1.5689,
"step": 377
},
{
"epoch": 2.1,
"grad_norm": 20.750045776367188,
"learning_rate": 9.947530864197533e-06,
"loss": 1.2894,
"step": 378
},
{
"epoch": 2.1055555555555556,
"grad_norm": 49.82916259765625,
"learning_rate": 9.944444444444445e-06,
"loss": 1.3407,
"step": 379
},
{
"epoch": 2.111111111111111,
"grad_norm": 21.216991424560547,
"learning_rate": 9.941358024691359e-06,
"loss": 1.4267,
"step": 380
},
{
"epoch": 2.1166666666666667,
"grad_norm": 16.638078689575195,
"learning_rate": 9.938271604938273e-06,
"loss": 1.5586,
"step": 381
},
{
"epoch": 2.1222222222222222,
"grad_norm": 22.361387252807617,
"learning_rate": 9.935185185185185e-06,
"loss": 1.3824,
"step": 382
},
{
"epoch": 2.1277777777777778,
"grad_norm": 18.626235961914062,
"learning_rate": 9.9320987654321e-06,
"loss": 1.1581,
"step": 383
},
{
"epoch": 2.1333333333333333,
"grad_norm": 19.192506790161133,
"learning_rate": 9.929012345679013e-06,
"loss": 1.1898,
"step": 384
},
{
"epoch": 2.138888888888889,
"grad_norm": 32.02525329589844,
"learning_rate": 9.925925925925927e-06,
"loss": 1.4225,
"step": 385
},
{
"epoch": 2.1444444444444444,
"grad_norm": 17.418107986450195,
"learning_rate": 9.92283950617284e-06,
"loss": 1.2027,
"step": 386
},
{
"epoch": 2.15,
"grad_norm": 13.825376510620117,
"learning_rate": 9.919753086419754e-06,
"loss": 1.3352,
"step": 387
},
{
"epoch": 2.1555555555555554,
"grad_norm": 16.182647705078125,
"learning_rate": 9.916666666666668e-06,
"loss": 1.3373,
"step": 388
},
{
"epoch": 2.161111111111111,
"grad_norm": 21.38442039489746,
"learning_rate": 9.913580246913582e-06,
"loss": 1.4349,
"step": 389
},
{
"epoch": 2.1666666666666665,
"grad_norm": 17.070302963256836,
"learning_rate": 9.910493827160494e-06,
"loss": 1.5032,
"step": 390
},
{
"epoch": 2.172222222222222,
"grad_norm": 56.54159164428711,
"learning_rate": 9.907407407407408e-06,
"loss": 1.108,
"step": 391
},
{
"epoch": 2.1777777777777776,
"grad_norm": 46.233482360839844,
"learning_rate": 9.904320987654322e-06,
"loss": 1.293,
"step": 392
},
{
"epoch": 2.183333333333333,
"grad_norm": 17.229312896728516,
"learning_rate": 9.901234567901236e-06,
"loss": 1.2533,
"step": 393
},
{
"epoch": 2.188888888888889,
"grad_norm": 16.614501953125,
"learning_rate": 9.898148148148148e-06,
"loss": 1.3725,
"step": 394
},
{
"epoch": 2.1944444444444446,
"grad_norm": 16.37877655029297,
"learning_rate": 9.895061728395063e-06,
"loss": 1.2493,
"step": 395
},
{
"epoch": 2.2,
"grad_norm": 31.646865844726562,
"learning_rate": 9.891975308641975e-06,
"loss": 1.2158,
"step": 396
},
{
"epoch": 2.2055555555555557,
"grad_norm": 14.920503616333008,
"learning_rate": 9.88888888888889e-06,
"loss": 1.4401,
"step": 397
},
{
"epoch": 2.2111111111111112,
"grad_norm": 35.997467041015625,
"learning_rate": 9.885802469135803e-06,
"loss": 1.5062,
"step": 398
},
{
"epoch": 2.216666666666667,
"grad_norm": 44.084293365478516,
"learning_rate": 9.882716049382717e-06,
"loss": 1.1882,
"step": 399
},
{
"epoch": 2.2222222222222223,
"grad_norm": 23.025571823120117,
"learning_rate": 9.87962962962963e-06,
"loss": 1.3237,
"step": 400
},
{
"epoch": 2.227777777777778,
"grad_norm": 32.66119384765625,
"learning_rate": 9.876543209876543e-06,
"loss": 1.415,
"step": 401
},
{
"epoch": 2.2333333333333334,
"grad_norm": 23.338048934936523,
"learning_rate": 9.873456790123457e-06,
"loss": 1.5723,
"step": 402
},
{
"epoch": 2.238888888888889,
"grad_norm": 21.447002410888672,
"learning_rate": 9.870370370370371e-06,
"loss": 1.2495,
"step": 403
},
{
"epoch": 2.2444444444444445,
"grad_norm": 21.151247024536133,
"learning_rate": 9.867283950617285e-06,
"loss": 1.2289,
"step": 404
},
{
"epoch": 2.25,
"grad_norm": 22.759418487548828,
"learning_rate": 9.864197530864198e-06,
"loss": 1.4598,
"step": 405
},
{
"epoch": 2.2555555555555555,
"grad_norm": 30.194000244140625,
"learning_rate": 9.861111111111112e-06,
"loss": 1.1891,
"step": 406
},
{
"epoch": 2.261111111111111,
"grad_norm": 28.339340209960938,
"learning_rate": 9.858024691358026e-06,
"loss": 0.9991,
"step": 407
},
{
"epoch": 2.2666666666666666,
"grad_norm": 13.873931884765625,
"learning_rate": 9.85493827160494e-06,
"loss": 1.0106,
"step": 408
},
{
"epoch": 2.272222222222222,
"grad_norm": 23.029664993286133,
"learning_rate": 9.851851851851852e-06,
"loss": 1.1849,
"step": 409
},
{
"epoch": 2.2777777777777777,
"grad_norm": 25.43478775024414,
"learning_rate": 9.848765432098766e-06,
"loss": 1.2864,
"step": 410
},
{
"epoch": 2.283333333333333,
"grad_norm": 14.368673324584961,
"learning_rate": 9.84567901234568e-06,
"loss": 1.3753,
"step": 411
},
{
"epoch": 2.2888888888888888,
"grad_norm": 20.924335479736328,
"learning_rate": 9.842592592592594e-06,
"loss": 1.4221,
"step": 412
},
{
"epoch": 2.2944444444444443,
"grad_norm": 19.0470027923584,
"learning_rate": 9.839506172839507e-06,
"loss": 1.1479,
"step": 413
},
{
"epoch": 2.3,
"grad_norm": 22.0178279876709,
"learning_rate": 9.83641975308642e-06,
"loss": 1.0447,
"step": 414
},
{
"epoch": 2.3055555555555554,
"grad_norm": 282.4730224609375,
"learning_rate": 9.833333333333333e-06,
"loss": 1.0751,
"step": 415
},
{
"epoch": 2.311111111111111,
"grad_norm": 17.71878433227539,
"learning_rate": 9.830246913580249e-06,
"loss": 0.9892,
"step": 416
},
{
"epoch": 2.3166666666666664,
"grad_norm": 25.03251075744629,
"learning_rate": 9.827160493827161e-06,
"loss": 1.0775,
"step": 417
},
{
"epoch": 2.3222222222222224,
"grad_norm": 36.97362518310547,
"learning_rate": 9.824074074074075e-06,
"loss": 1.0379,
"step": 418
},
{
"epoch": 2.327777777777778,
"grad_norm": 33.098106384277344,
"learning_rate": 9.820987654320987e-06,
"loss": 1.3965,
"step": 419
},
{
"epoch": 2.3333333333333335,
"grad_norm": 24.77194595336914,
"learning_rate": 9.817901234567903e-06,
"loss": 1.0397,
"step": 420
},
{
"epoch": 2.338888888888889,
"grad_norm": 31.86960220336914,
"learning_rate": 9.814814814814815e-06,
"loss": 1.3408,
"step": 421
},
{
"epoch": 2.3444444444444446,
"grad_norm": 34.47334289550781,
"learning_rate": 9.81172839506173e-06,
"loss": 1.1827,
"step": 422
},
{
"epoch": 2.35,
"grad_norm": 21.66546630859375,
"learning_rate": 9.808641975308642e-06,
"loss": 1.1541,
"step": 423
},
{
"epoch": 2.3555555555555556,
"grad_norm": 14.667912483215332,
"learning_rate": 9.805555555555556e-06,
"loss": 1.0333,
"step": 424
},
{
"epoch": 2.361111111111111,
"grad_norm": 16.649307250976562,
"learning_rate": 9.80246913580247e-06,
"loss": 1.0008,
"step": 425
},
{
"epoch": 2.3666666666666667,
"grad_norm": 46.52693557739258,
"learning_rate": 9.799382716049384e-06,
"loss": 1.0354,
"step": 426
},
{
"epoch": 2.3722222222222222,
"grad_norm": 18.253042221069336,
"learning_rate": 9.796296296296298e-06,
"loss": 1.283,
"step": 427
},
{
"epoch": 2.3777777777777778,
"grad_norm": 54.7445068359375,
"learning_rate": 9.79320987654321e-06,
"loss": 1.3608,
"step": 428
},
{
"epoch": 2.3833333333333333,
"grad_norm": 23.576839447021484,
"learning_rate": 9.790123456790124e-06,
"loss": 1.0039,
"step": 429
},
{
"epoch": 2.388888888888889,
"grad_norm": 25.952224731445312,
"learning_rate": 9.787037037037038e-06,
"loss": 1.256,
"step": 430
},
{
"epoch": 2.3944444444444444,
"grad_norm": 22.296466827392578,
"learning_rate": 9.783950617283952e-06,
"loss": 1.2383,
"step": 431
},
{
"epoch": 2.4,
"grad_norm": 19.27615737915039,
"learning_rate": 9.780864197530865e-06,
"loss": 0.9251,
"step": 432
},
{
"epoch": 2.4055555555555554,
"grad_norm": 17.2935791015625,
"learning_rate": 9.777777777777779e-06,
"loss": 1.1163,
"step": 433
},
{
"epoch": 2.411111111111111,
"grad_norm": 18.822887420654297,
"learning_rate": 9.774691358024693e-06,
"loss": 1.1865,
"step": 434
},
{
"epoch": 2.4166666666666665,
"grad_norm": 17.657682418823242,
"learning_rate": 9.771604938271607e-06,
"loss": 1.1392,
"step": 435
},
{
"epoch": 2.422222222222222,
"grad_norm": 32.9812126159668,
"learning_rate": 9.768518518518519e-06,
"loss": 1.2668,
"step": 436
},
{
"epoch": 2.4277777777777776,
"grad_norm": 30.27857780456543,
"learning_rate": 9.765432098765433e-06,
"loss": 0.9585,
"step": 437
},
{
"epoch": 2.4333333333333336,
"grad_norm": 16.87225914001465,
"learning_rate": 9.762345679012345e-06,
"loss": 1.2062,
"step": 438
},
{
"epoch": 2.438888888888889,
"grad_norm": 23.46126365661621,
"learning_rate": 9.759259259259261e-06,
"loss": 1.1269,
"step": 439
},
{
"epoch": 2.4444444444444446,
"grad_norm": 17.96172332763672,
"learning_rate": 9.756172839506173e-06,
"loss": 0.7477,
"step": 440
},
{
"epoch": 2.45,
"grad_norm": 15.149947166442871,
"learning_rate": 9.753086419753087e-06,
"loss": 1.0782,
"step": 441
},
{
"epoch": 2.4555555555555557,
"grad_norm": 24.318538665771484,
"learning_rate": 9.75e-06,
"loss": 1.1458,
"step": 442
},
{
"epoch": 2.4611111111111112,
"grad_norm": 60.819908142089844,
"learning_rate": 9.746913580246914e-06,
"loss": 1.1006,
"step": 443
},
{
"epoch": 2.466666666666667,
"grad_norm": 20.373018264770508,
"learning_rate": 9.743827160493828e-06,
"loss": 1.2616,
"step": 444
},
{
"epoch": 2.4722222222222223,
"grad_norm": 23.294248580932617,
"learning_rate": 9.740740740740742e-06,
"loss": 1.2102,
"step": 445
},
{
"epoch": 2.477777777777778,
"grad_norm": 25.91476821899414,
"learning_rate": 9.737654320987654e-06,
"loss": 1.0653,
"step": 446
},
{
"epoch": 2.4833333333333334,
"grad_norm": 21.011720657348633,
"learning_rate": 9.734567901234568e-06,
"loss": 1.1757,
"step": 447
},
{
"epoch": 2.488888888888889,
"grad_norm": 16.654071807861328,
"learning_rate": 9.731481481481482e-06,
"loss": 1.0495,
"step": 448
},
{
"epoch": 2.4944444444444445,
"grad_norm": 21.70490074157715,
"learning_rate": 9.728395061728396e-06,
"loss": 1.1317,
"step": 449
},
{
"epoch": 2.5,
"grad_norm": 22.119829177856445,
"learning_rate": 9.72530864197531e-06,
"loss": 1.287,
"step": 450
},
{
"epoch": 2.5055555555555555,
"grad_norm": 15.430317878723145,
"learning_rate": 9.722222222222223e-06,
"loss": 1.1367,
"step": 451
},
{
"epoch": 2.511111111111111,
"grad_norm": 26.152713775634766,
"learning_rate": 9.719135802469137e-06,
"loss": 1.3201,
"step": 452
},
{
"epoch": 2.5166666666666666,
"grad_norm": 19.43636703491211,
"learning_rate": 9.71604938271605e-06,
"loss": 1.1981,
"step": 453
},
{
"epoch": 2.522222222222222,
"grad_norm": 19.344690322875977,
"learning_rate": 9.712962962962965e-06,
"loss": 0.8925,
"step": 454
},
{
"epoch": 2.5277777777777777,
"grad_norm": 18.0750732421875,
"learning_rate": 9.709876543209877e-06,
"loss": 0.9716,
"step": 455
},
{
"epoch": 2.533333333333333,
"grad_norm": 23.320098876953125,
"learning_rate": 9.706790123456791e-06,
"loss": 0.9992,
"step": 456
},
{
"epoch": 2.5388888888888888,
"grad_norm": 18.664140701293945,
"learning_rate": 9.703703703703703e-06,
"loss": 0.8085,
"step": 457
},
{
"epoch": 2.5444444444444443,
"grad_norm": 18.784709930419922,
"learning_rate": 9.70061728395062e-06,
"loss": 1.0238,
"step": 458
},
{
"epoch": 2.55,
"grad_norm": 23.291831970214844,
"learning_rate": 9.697530864197532e-06,
"loss": 1.0404,
"step": 459
},
{
"epoch": 2.5555555555555554,
"grad_norm": 17.002042770385742,
"learning_rate": 9.694444444444446e-06,
"loss": 1.0453,
"step": 460
},
{
"epoch": 2.561111111111111,
"grad_norm": 23.9116153717041,
"learning_rate": 9.691358024691358e-06,
"loss": 0.9326,
"step": 461
},
{
"epoch": 2.5666666666666664,
"grad_norm": 15.554929733276367,
"learning_rate": 9.688271604938272e-06,
"loss": 0.8883,
"step": 462
},
{
"epoch": 2.572222222222222,
"grad_norm": 59.8626708984375,
"learning_rate": 9.685185185185186e-06,
"loss": 1.2756,
"step": 463
},
{
"epoch": 2.5777777777777775,
"grad_norm": 20.679241180419922,
"learning_rate": 9.6820987654321e-06,
"loss": 0.9293,
"step": 464
},
{
"epoch": 2.5833333333333335,
"grad_norm": 22.562185287475586,
"learning_rate": 9.679012345679012e-06,
"loss": 0.7988,
"step": 465
},
{
"epoch": 2.588888888888889,
"grad_norm": 16.000017166137695,
"learning_rate": 9.675925925925926e-06,
"loss": 0.9411,
"step": 466
},
{
"epoch": 2.5944444444444446,
"grad_norm": 45.946746826171875,
"learning_rate": 9.67283950617284e-06,
"loss": 1.4079,
"step": 467
},
{
"epoch": 2.6,
"grad_norm": 20.07754135131836,
"learning_rate": 9.669753086419754e-06,
"loss": 1.0215,
"step": 468
},
{
"epoch": 2.6055555555555556,
"grad_norm": 36.56315994262695,
"learning_rate": 9.666666666666667e-06,
"loss": 0.9487,
"step": 469
},
{
"epoch": 2.611111111111111,
"grad_norm": 24.703495025634766,
"learning_rate": 9.66358024691358e-06,
"loss": 0.9765,
"step": 470
},
{
"epoch": 2.6166666666666667,
"grad_norm": 16.428977966308594,
"learning_rate": 9.660493827160495e-06,
"loss": 1.1659,
"step": 471
},
{
"epoch": 2.6222222222222222,
"grad_norm": 22.219968795776367,
"learning_rate": 9.657407407407409e-06,
"loss": 0.6951,
"step": 472
},
{
"epoch": 2.6277777777777778,
"grad_norm": 17.122400283813477,
"learning_rate": 9.654320987654323e-06,
"loss": 0.6877,
"step": 473
},
{
"epoch": 2.6333333333333333,
"grad_norm": 21.7871036529541,
"learning_rate": 9.651234567901235e-06,
"loss": 0.9869,
"step": 474
},
{
"epoch": 2.638888888888889,
"grad_norm": 91.609619140625,
"learning_rate": 9.64814814814815e-06,
"loss": 1.0805,
"step": 475
},
{
"epoch": 2.6444444444444444,
"grad_norm": 19.052690505981445,
"learning_rate": 9.645061728395062e-06,
"loss": 1.4167,
"step": 476
},
{
"epoch": 2.65,
"grad_norm": 33.31120681762695,
"learning_rate": 9.641975308641977e-06,
"loss": 1.1309,
"step": 477
},
{
"epoch": 2.6555555555555554,
"grad_norm": 17.935144424438477,
"learning_rate": 9.63888888888889e-06,
"loss": 0.9795,
"step": 478
},
{
"epoch": 2.661111111111111,
"grad_norm": 25.230844497680664,
"learning_rate": 9.635802469135804e-06,
"loss": 0.9398,
"step": 479
},
{
"epoch": 2.6666666666666665,
"grad_norm": 34.700374603271484,
"learning_rate": 9.632716049382716e-06,
"loss": 0.9378,
"step": 480
},
{
"epoch": 2.6722222222222225,
"grad_norm": 21.50897789001465,
"learning_rate": 9.62962962962963e-06,
"loss": 0.9797,
"step": 481
},
{
"epoch": 2.677777777777778,
"grad_norm": 17.423683166503906,
"learning_rate": 9.626543209876544e-06,
"loss": 1.0864,
"step": 482
},
{
"epoch": 2.6833333333333336,
"grad_norm": 21.6640625,
"learning_rate": 9.623456790123458e-06,
"loss": 0.8409,
"step": 483
},
{
"epoch": 2.688888888888889,
"grad_norm": 21.914379119873047,
"learning_rate": 9.62037037037037e-06,
"loss": 1.1016,
"step": 484
},
{
"epoch": 2.6944444444444446,
"grad_norm": 19.956562042236328,
"learning_rate": 9.617283950617284e-06,
"loss": 1.0477,
"step": 485
},
{
"epoch": 2.7,
"grad_norm": 25.772077560424805,
"learning_rate": 9.614197530864198e-06,
"loss": 1.1558,
"step": 486
},
{
"epoch": 2.7055555555555557,
"grad_norm": 21.039695739746094,
"learning_rate": 9.611111111111112e-06,
"loss": 1.0504,
"step": 487
},
{
"epoch": 2.7111111111111112,
"grad_norm": 19.880800247192383,
"learning_rate": 9.608024691358025e-06,
"loss": 1.1814,
"step": 488
},
{
"epoch": 2.716666666666667,
"grad_norm": 34.607635498046875,
"learning_rate": 9.604938271604939e-06,
"loss": 1.0108,
"step": 489
},
{
"epoch": 2.7222222222222223,
"grad_norm": 15.856334686279297,
"learning_rate": 9.601851851851853e-06,
"loss": 1.0807,
"step": 490
},
{
"epoch": 2.727777777777778,
"grad_norm": 17.11734962463379,
"learning_rate": 9.598765432098767e-06,
"loss": 1.113,
"step": 491
},
{
"epoch": 2.7333333333333334,
"grad_norm": 22.41156578063965,
"learning_rate": 9.59567901234568e-06,
"loss": 1.1612,
"step": 492
},
{
"epoch": 2.738888888888889,
"grad_norm": 27.259435653686523,
"learning_rate": 9.592592592592593e-06,
"loss": 0.9263,
"step": 493
},
{
"epoch": 2.7444444444444445,
"grad_norm": 15.454346656799316,
"learning_rate": 9.589506172839507e-06,
"loss": 1.1015,
"step": 494
},
{
"epoch": 2.75,
"grad_norm": 18.497671127319336,
"learning_rate": 9.58641975308642e-06,
"loss": 1.1075,
"step": 495
},
{
"epoch": 2.7555555555555555,
"grad_norm": 44.14335632324219,
"learning_rate": 9.583333333333335e-06,
"loss": 0.772,
"step": 496
},
{
"epoch": 2.761111111111111,
"grad_norm": 16.747512817382812,
"learning_rate": 9.580246913580248e-06,
"loss": 0.7795,
"step": 497
},
{
"epoch": 2.7666666666666666,
"grad_norm": 13.939385414123535,
"learning_rate": 9.577160493827162e-06,
"loss": 0.9716,
"step": 498
},
{
"epoch": 2.772222222222222,
"grad_norm": 21.01386260986328,
"learning_rate": 9.574074074074074e-06,
"loss": 0.8072,
"step": 499
},
{
"epoch": 2.7777777777777777,
"grad_norm": 38.50996017456055,
"learning_rate": 9.57098765432099e-06,
"loss": 1.1509,
"step": 500
},
{
"epoch": 2.783333333333333,
"grad_norm": 14.630939483642578,
"learning_rate": 9.567901234567902e-06,
"loss": 0.669,
"step": 501
},
{
"epoch": 2.7888888888888888,
"grad_norm": 13.529491424560547,
"learning_rate": 9.564814814814816e-06,
"loss": 0.8293,
"step": 502
},
{
"epoch": 2.7944444444444443,
"grad_norm": 14.893417358398438,
"learning_rate": 9.561728395061728e-06,
"loss": 0.7992,
"step": 503
},
{
"epoch": 2.8,
"grad_norm": 33.374732971191406,
"learning_rate": 9.558641975308642e-06,
"loss": 1.1141,
"step": 504
},
{
"epoch": 2.8055555555555554,
"grad_norm": 14.682233810424805,
"learning_rate": 9.555555555555556e-06,
"loss": 0.8992,
"step": 505
},
{
"epoch": 2.811111111111111,
"grad_norm": 21.0645694732666,
"learning_rate": 9.55246913580247e-06,
"loss": 1.0185,
"step": 506
},
{
"epoch": 2.8166666666666664,
"grad_norm": 15.41943073272705,
"learning_rate": 9.549382716049383e-06,
"loss": 0.8796,
"step": 507
},
{
"epoch": 2.822222222222222,
"grad_norm": 13.958263397216797,
"learning_rate": 9.546296296296297e-06,
"loss": 0.9513,
"step": 508
},
{
"epoch": 2.8277777777777775,
"grad_norm": 13.088967323303223,
"learning_rate": 9.543209876543211e-06,
"loss": 0.8344,
"step": 509
},
{
"epoch": 2.8333333333333335,
"grad_norm": 47.25247573852539,
"learning_rate": 9.540123456790125e-06,
"loss": 1.1443,
"step": 510
},
{
"epoch": 2.838888888888889,
"grad_norm": 36.55316162109375,
"learning_rate": 9.537037037037037e-06,
"loss": 0.7753,
"step": 511
},
{
"epoch": 2.8444444444444446,
"grad_norm": 48.560691833496094,
"learning_rate": 9.533950617283951e-06,
"loss": 0.8473,
"step": 512
},
{
"epoch": 2.85,
"grad_norm": 13.397860527038574,
"learning_rate": 9.530864197530865e-06,
"loss": 0.6204,
"step": 513
},
{
"epoch": 2.8555555555555556,
"grad_norm": 21.49095344543457,
"learning_rate": 9.527777777777778e-06,
"loss": 0.9997,
"step": 514
},
{
"epoch": 2.861111111111111,
"grad_norm": 211.44015502929688,
"learning_rate": 9.524691358024692e-06,
"loss": 0.8196,
"step": 515
},
{
"epoch": 2.8666666666666667,
"grad_norm": 12.474881172180176,
"learning_rate": 9.521604938271606e-06,
"loss": 1.0015,
"step": 516
},
{
"epoch": 2.8722222222222222,
"grad_norm": 25.981674194335938,
"learning_rate": 9.51851851851852e-06,
"loss": 0.8363,
"step": 517
},
{
"epoch": 2.8777777777777778,
"grad_norm": 16.580049514770508,
"learning_rate": 9.515432098765432e-06,
"loss": 0.9084,
"step": 518
},
{
"epoch": 2.8833333333333333,
"grad_norm": 43.33476638793945,
"learning_rate": 9.512345679012348e-06,
"loss": 1.0428,
"step": 519
},
{
"epoch": 2.888888888888889,
"grad_norm": 26.326826095581055,
"learning_rate": 9.50925925925926e-06,
"loss": 0.8356,
"step": 520
},
{
"epoch": 2.8944444444444444,
"grad_norm": 18.888883590698242,
"learning_rate": 9.506172839506174e-06,
"loss": 0.9034,
"step": 521
},
{
"epoch": 2.9,
"grad_norm": 20.63212776184082,
"learning_rate": 9.503086419753086e-06,
"loss": 1.0237,
"step": 522
},
{
"epoch": 2.9055555555555554,
"grad_norm": 31.02515983581543,
"learning_rate": 9.5e-06,
"loss": 0.8089,
"step": 523
},
{
"epoch": 2.911111111111111,
"grad_norm": 23.162607192993164,
"learning_rate": 9.496913580246915e-06,
"loss": 1.1281,
"step": 524
},
{
"epoch": 2.9166666666666665,
"grad_norm": 62.52622985839844,
"learning_rate": 9.493827160493829e-06,
"loss": 0.9039,
"step": 525
},
{
"epoch": 2.9222222222222225,
"grad_norm": 10.379598617553711,
"learning_rate": 9.490740740740741e-06,
"loss": 0.5081,
"step": 526
},
{
"epoch": 2.927777777777778,
"grad_norm": 11.010148048400879,
"learning_rate": 9.487654320987655e-06,
"loss": 0.6551,
"step": 527
},
{
"epoch": 2.9333333333333336,
"grad_norm": 14.1155366897583,
"learning_rate": 9.484567901234569e-06,
"loss": 0.9181,
"step": 528
},
{
"epoch": 2.938888888888889,
"grad_norm": 18.28863525390625,
"learning_rate": 9.481481481481483e-06,
"loss": 0.8155,
"step": 529
},
{
"epoch": 2.9444444444444446,
"grad_norm": 25.089689254760742,
"learning_rate": 9.478395061728395e-06,
"loss": 0.6941,
"step": 530
},
{
"epoch": 2.95,
"grad_norm": 43.111576080322266,
"learning_rate": 9.47530864197531e-06,
"loss": 0.7414,
"step": 531
},
{
"epoch": 2.9555555555555557,
"grad_norm": 30.386062622070312,
"learning_rate": 9.472222222222223e-06,
"loss": 0.9925,
"step": 532
},
{
"epoch": 2.9611111111111112,
"grad_norm": 29.2484188079834,
"learning_rate": 9.469135802469137e-06,
"loss": 0.8757,
"step": 533
},
{
"epoch": 2.966666666666667,
"grad_norm": 22.40903663635254,
"learning_rate": 9.46604938271605e-06,
"loss": 1.0593,
"step": 534
},
{
"epoch": 2.9722222222222223,
"grad_norm": 20.73932647705078,
"learning_rate": 9.462962962962964e-06,
"loss": 0.7037,
"step": 535
},
{
"epoch": 2.977777777777778,
"grad_norm": 118.01354217529297,
"learning_rate": 9.459876543209878e-06,
"loss": 1.1417,
"step": 536
},
{
"epoch": 2.9833333333333334,
"grad_norm": 25.890869140625,
"learning_rate": 9.45679012345679e-06,
"loss": 0.9838,
"step": 537
},
{
"epoch": 2.988888888888889,
"grad_norm": 19.529226303100586,
"learning_rate": 9.453703703703704e-06,
"loss": 1.1061,
"step": 538
},
{
"epoch": 2.9944444444444445,
"grad_norm": 26.854000091552734,
"learning_rate": 9.450617283950618e-06,
"loss": 0.9104,
"step": 539
},
{
"epoch": 3.0,
"grad_norm": 19.042705535888672,
"learning_rate": 9.447530864197532e-06,
"loss": 0.8549,
"step": 540
},
{
"epoch": 3.0,
"eval_accuracy": 0.8199704869650762,
"eval_f1": 0.8044556796496066,
"eval_loss": 0.7430828809738159,
"eval_runtime": 2.8402,
"eval_samples_per_second": 715.795,
"eval_steps_per_second": 5.633,
"step": 540
},
{
"epoch": 3.0055555555555555,
"grad_norm": 16.5549259185791,
"learning_rate": 9.444444444444445e-06,
"loss": 0.7988,
"step": 541
},
{
"epoch": 3.011111111111111,
"grad_norm": 14.626434326171875,
"learning_rate": 9.441358024691359e-06,
"loss": 0.7893,
"step": 542
},
{
"epoch": 3.0166666666666666,
"grad_norm": 15.759276390075684,
"learning_rate": 9.438271604938273e-06,
"loss": 0.8387,
"step": 543
},
{
"epoch": 3.022222222222222,
"grad_norm": 17.202632904052734,
"learning_rate": 9.435185185185187e-06,
"loss": 0.7283,
"step": 544
},
{
"epoch": 3.0277777777777777,
"grad_norm": 24.44295883178711,
"learning_rate": 9.432098765432099e-06,
"loss": 0.6052,
"step": 545
},
{
"epoch": 3.033333333333333,
"grad_norm": 27.198862075805664,
"learning_rate": 9.429012345679013e-06,
"loss": 0.7196,
"step": 546
},
{
"epoch": 3.0388888888888888,
"grad_norm": 15.250130653381348,
"learning_rate": 9.425925925925925e-06,
"loss": 1.1276,
"step": 547
},
{
"epoch": 3.0444444444444443,
"grad_norm": 17.109773635864258,
"learning_rate": 9.422839506172841e-06,
"loss": 0.6831,
"step": 548
},
{
"epoch": 3.05,
"grad_norm": 28.091346740722656,
"learning_rate": 9.419753086419753e-06,
"loss": 0.8733,
"step": 549
},
{
"epoch": 3.0555555555555554,
"grad_norm": 11.885051727294922,
"learning_rate": 9.416666666666667e-06,
"loss": 0.7101,
"step": 550
},
{
"epoch": 3.061111111111111,
"grad_norm": 31.442752838134766,
"learning_rate": 9.413580246913581e-06,
"loss": 0.8528,
"step": 551
},
{
"epoch": 3.066666666666667,
"grad_norm": 14.666029930114746,
"learning_rate": 9.410493827160495e-06,
"loss": 0.5693,
"step": 552
},
{
"epoch": 3.0722222222222224,
"grad_norm": 37.16005325317383,
"learning_rate": 9.407407407407408e-06,
"loss": 0.6851,
"step": 553
},
{
"epoch": 3.077777777777778,
"grad_norm": 37.66290283203125,
"learning_rate": 9.404320987654322e-06,
"loss": 0.6935,
"step": 554
},
{
"epoch": 3.0833333333333335,
"grad_norm": 11.797327995300293,
"learning_rate": 9.401234567901236e-06,
"loss": 0.5693,
"step": 555
},
{
"epoch": 3.088888888888889,
"grad_norm": 12.820536613464355,
"learning_rate": 9.398148148148148e-06,
"loss": 0.6846,
"step": 556
},
{
"epoch": 3.0944444444444446,
"grad_norm": 18.215307235717773,
"learning_rate": 9.395061728395062e-06,
"loss": 1.0943,
"step": 557
},
{
"epoch": 3.1,
"grad_norm": 18.066146850585938,
"learning_rate": 9.391975308641976e-06,
"loss": 0.6353,
"step": 558
},
{
"epoch": 3.1055555555555556,
"grad_norm": 15.18871784210205,
"learning_rate": 9.38888888888889e-06,
"loss": 0.6623,
"step": 559
},
{
"epoch": 3.111111111111111,
"grad_norm": 20.28233528137207,
"learning_rate": 9.385802469135803e-06,
"loss": 0.8721,
"step": 560
},
{
"epoch": 3.1166666666666667,
"grad_norm": 22.33995819091797,
"learning_rate": 9.382716049382717e-06,
"loss": 0.873,
"step": 561
},
{
"epoch": 3.1222222222222222,
"grad_norm": 16.040441513061523,
"learning_rate": 9.37962962962963e-06,
"loss": 0.7332,
"step": 562
},
{
"epoch": 3.1277777777777778,
"grad_norm": 12.489974975585938,
"learning_rate": 9.376543209876545e-06,
"loss": 0.7027,
"step": 563
},
{
"epoch": 3.1333333333333333,
"grad_norm": 18.8903751373291,
"learning_rate": 9.373456790123457e-06,
"loss": 0.5703,
"step": 564
},
{
"epoch": 3.138888888888889,
"grad_norm": 30.798154830932617,
"learning_rate": 9.370370370370371e-06,
"loss": 0.789,
"step": 565
},
{
"epoch": 3.1444444444444444,
"grad_norm": 29.265974044799805,
"learning_rate": 9.367283950617285e-06,
"loss": 0.8219,
"step": 566
},
{
"epoch": 3.15,
"grad_norm": 16.925291061401367,
"learning_rate": 9.364197530864199e-06,
"loss": 0.7891,
"step": 567
},
{
"epoch": 3.1555555555555554,
"grad_norm": 11.850492477416992,
"learning_rate": 9.361111111111111e-06,
"loss": 0.8267,
"step": 568
},
{
"epoch": 3.161111111111111,
"grad_norm": 21.11591339111328,
"learning_rate": 9.358024691358025e-06,
"loss": 0.9044,
"step": 569
},
{
"epoch": 3.1666666666666665,
"grad_norm": 18.554092407226562,
"learning_rate": 9.354938271604938e-06,
"loss": 0.6546,
"step": 570
},
{
"epoch": 3.172222222222222,
"grad_norm": 13.860138893127441,
"learning_rate": 9.351851851851854e-06,
"loss": 0.6392,
"step": 571
},
{
"epoch": 3.1777777777777776,
"grad_norm": 21.15414047241211,
"learning_rate": 9.348765432098766e-06,
"loss": 0.6768,
"step": 572
},
{
"epoch": 3.183333333333333,
"grad_norm": 31.619298934936523,
"learning_rate": 9.34567901234568e-06,
"loss": 0.7892,
"step": 573
},
{
"epoch": 3.188888888888889,
"grad_norm": 11.869976043701172,
"learning_rate": 9.342592592592594e-06,
"loss": 0.5288,
"step": 574
},
{
"epoch": 3.1944444444444446,
"grad_norm": 25.5703067779541,
"learning_rate": 9.339506172839506e-06,
"loss": 1.0047,
"step": 575
},
{
"epoch": 3.2,
"grad_norm": 10.807881355285645,
"learning_rate": 9.33641975308642e-06,
"loss": 0.5325,
"step": 576
},
{
"epoch": 3.2055555555555557,
"grad_norm": 15.406116485595703,
"learning_rate": 9.333333333333334e-06,
"loss": 0.7621,
"step": 577
},
{
"epoch": 3.2111111111111112,
"grad_norm": 25.4089412689209,
"learning_rate": 9.330246913580248e-06,
"loss": 0.6244,
"step": 578
},
{
"epoch": 3.216666666666667,
"grad_norm": 19.481765747070312,
"learning_rate": 9.32716049382716e-06,
"loss": 0.9776,
"step": 579
},
{
"epoch": 3.2222222222222223,
"grad_norm": 17.055843353271484,
"learning_rate": 9.324074074074075e-06,
"loss": 0.7155,
"step": 580
},
{
"epoch": 3.227777777777778,
"grad_norm": 18.227087020874023,
"learning_rate": 9.320987654320989e-06,
"loss": 0.9204,
"step": 581
},
{
"epoch": 3.2333333333333334,
"grad_norm": 17.754993438720703,
"learning_rate": 9.317901234567903e-06,
"loss": 0.9637,
"step": 582
},
{
"epoch": 3.238888888888889,
"grad_norm": 15.476292610168457,
"learning_rate": 9.314814814814815e-06,
"loss": 0.6817,
"step": 583
},
{
"epoch": 3.2444444444444445,
"grad_norm": 17.658662796020508,
"learning_rate": 9.311728395061729e-06,
"loss": 0.5983,
"step": 584
},
{
"epoch": 3.25,
"grad_norm": 16.734052658081055,
"learning_rate": 9.308641975308643e-06,
"loss": 0.6404,
"step": 585
},
{
"epoch": 3.2555555555555555,
"grad_norm": 39.49653244018555,
"learning_rate": 9.305555555555557e-06,
"loss": 0.8367,
"step": 586
},
{
"epoch": 3.261111111111111,
"grad_norm": 22.998476028442383,
"learning_rate": 9.30246913580247e-06,
"loss": 0.7485,
"step": 587
},
{
"epoch": 3.2666666666666666,
"grad_norm": 20.594993591308594,
"learning_rate": 9.299382716049384e-06,
"loss": 0.7544,
"step": 588
},
{
"epoch": 3.272222222222222,
"grad_norm": 23.350372314453125,
"learning_rate": 9.296296296296296e-06,
"loss": 0.6188,
"step": 589
},
{
"epoch": 3.2777777777777777,
"grad_norm": 14.929303169250488,
"learning_rate": 9.293209876543212e-06,
"loss": 0.7094,
"step": 590
},
{
"epoch": 3.283333333333333,
"grad_norm": 16.80654525756836,
"learning_rate": 9.290123456790124e-06,
"loss": 0.6396,
"step": 591
},
{
"epoch": 3.2888888888888888,
"grad_norm": 17.275081634521484,
"learning_rate": 9.287037037037038e-06,
"loss": 0.5868,
"step": 592
},
{
"epoch": 3.2944444444444443,
"grad_norm": 46.41587829589844,
"learning_rate": 9.28395061728395e-06,
"loss": 0.5997,
"step": 593
},
{
"epoch": 3.3,
"grad_norm": 18.010562896728516,
"learning_rate": 9.280864197530864e-06,
"loss": 0.7443,
"step": 594
},
{
"epoch": 3.3055555555555554,
"grad_norm": 28.455062866210938,
"learning_rate": 9.277777777777778e-06,
"loss": 0.6611,
"step": 595
},
{
"epoch": 3.311111111111111,
"grad_norm": 17.500980377197266,
"learning_rate": 9.274691358024692e-06,
"loss": 0.7041,
"step": 596
},
{
"epoch": 3.3166666666666664,
"grad_norm": 17.716360092163086,
"learning_rate": 9.271604938271606e-06,
"loss": 0.705,
"step": 597
},
{
"epoch": 3.3222222222222224,
"grad_norm": 15.842692375183105,
"learning_rate": 9.268518518518519e-06,
"loss": 0.5552,
"step": 598
},
{
"epoch": 3.327777777777778,
"grad_norm": 13.67244815826416,
"learning_rate": 9.265432098765433e-06,
"loss": 0.8785,
"step": 599
},
{
"epoch": 3.3333333333333335,
"grad_norm": 21.753572463989258,
"learning_rate": 9.262345679012347e-06,
"loss": 0.7411,
"step": 600
},
{
"epoch": 3.338888888888889,
"grad_norm": 12.901546478271484,
"learning_rate": 9.25925925925926e-06,
"loss": 0.7152,
"step": 601
},
{
"epoch": 3.3444444444444446,
"grad_norm": 20.223011016845703,
"learning_rate": 9.256172839506173e-06,
"loss": 0.6519,
"step": 602
},
{
"epoch": 3.35,
"grad_norm": 15.598219871520996,
"learning_rate": 9.253086419753087e-06,
"loss": 0.9315,
"step": 603
},
{
"epoch": 3.3555555555555556,
"grad_norm": 15.07571792602539,
"learning_rate": 9.250000000000001e-06,
"loss": 0.5284,
"step": 604
},
{
"epoch": 3.361111111111111,
"grad_norm": 28.654457092285156,
"learning_rate": 9.246913580246915e-06,
"loss": 0.6691,
"step": 605
},
{
"epoch": 3.3666666666666667,
"grad_norm": 15.968894004821777,
"learning_rate": 9.243827160493828e-06,
"loss": 0.7513,
"step": 606
},
{
"epoch": 3.3722222222222222,
"grad_norm": 17.6177978515625,
"learning_rate": 9.240740740740742e-06,
"loss": 0.6182,
"step": 607
},
{
"epoch": 3.3777777777777778,
"grad_norm": 19.356529235839844,
"learning_rate": 9.237654320987654e-06,
"loss": 0.6246,
"step": 608
},
{
"epoch": 3.3833333333333333,
"grad_norm": 16.434839248657227,
"learning_rate": 9.23456790123457e-06,
"loss": 0.5652,
"step": 609
},
{
"epoch": 3.388888888888889,
"grad_norm": 16.195755004882812,
"learning_rate": 9.231481481481482e-06,
"loss": 0.6181,
"step": 610
},
{
"epoch": 3.3944444444444444,
"grad_norm": 19.308162689208984,
"learning_rate": 9.228395061728396e-06,
"loss": 0.8898,
"step": 611
},
{
"epoch": 3.4,
"grad_norm": 32.14164733886719,
"learning_rate": 9.225308641975308e-06,
"loss": 0.7339,
"step": 612
},
{
"epoch": 3.4055555555555554,
"grad_norm": 11.192728042602539,
"learning_rate": 9.222222222222224e-06,
"loss": 0.48,
"step": 613
},
{
"epoch": 3.411111111111111,
"grad_norm": 19.909944534301758,
"learning_rate": 9.219135802469136e-06,
"loss": 0.7129,
"step": 614
},
{
"epoch": 3.4166666666666665,
"grad_norm": 23.619930267333984,
"learning_rate": 9.21604938271605e-06,
"loss": 1.0226,
"step": 615
},
{
"epoch": 3.422222222222222,
"grad_norm": 22.611101150512695,
"learning_rate": 9.212962962962963e-06,
"loss": 0.6193,
"step": 616
},
{
"epoch": 3.4277777777777776,
"grad_norm": 15.623575210571289,
"learning_rate": 9.209876543209877e-06,
"loss": 0.7039,
"step": 617
},
{
"epoch": 3.4333333333333336,
"grad_norm": 15.70071029663086,
"learning_rate": 9.20679012345679e-06,
"loss": 0.8492,
"step": 618
},
{
"epoch": 3.438888888888889,
"grad_norm": 40.2573127746582,
"learning_rate": 9.203703703703705e-06,
"loss": 1.0023,
"step": 619
},
{
"epoch": 3.4444444444444446,
"grad_norm": 16.588714599609375,
"learning_rate": 9.200617283950617e-06,
"loss": 0.5114,
"step": 620
},
{
"epoch": 3.45,
"grad_norm": 10.60702133178711,
"learning_rate": 9.197530864197531e-06,
"loss": 0.66,
"step": 621
},
{
"epoch": 3.4555555555555557,
"grad_norm": 10.607470512390137,
"learning_rate": 9.194444444444445e-06,
"loss": 0.4586,
"step": 622
},
{
"epoch": 3.4611111111111112,
"grad_norm": 11.146430015563965,
"learning_rate": 9.19135802469136e-06,
"loss": 0.7712,
"step": 623
},
{
"epoch": 3.466666666666667,
"grad_norm": 20.957414627075195,
"learning_rate": 9.188271604938273e-06,
"loss": 0.5349,
"step": 624
},
{
"epoch": 3.4722222222222223,
"grad_norm": 13.655133247375488,
"learning_rate": 9.185185185185186e-06,
"loss": 0.45,
"step": 625
},
{
"epoch": 3.477777777777778,
"grad_norm": 16.187732696533203,
"learning_rate": 9.1820987654321e-06,
"loss": 0.7623,
"step": 626
},
{
"epoch": 3.4833333333333334,
"grad_norm": 22.698122024536133,
"learning_rate": 9.179012345679012e-06,
"loss": 0.9132,
"step": 627
},
{
"epoch": 3.488888888888889,
"grad_norm": 18.00724220275879,
"learning_rate": 9.175925925925928e-06,
"loss": 0.7473,
"step": 628
},
{
"epoch": 3.4944444444444445,
"grad_norm": 27.93900489807129,
"learning_rate": 9.17283950617284e-06,
"loss": 0.546,
"step": 629
},
{
"epoch": 3.5,
"grad_norm": 16.591876983642578,
"learning_rate": 9.169753086419754e-06,
"loss": 0.6094,
"step": 630
},
{
"epoch": 3.5055555555555555,
"grad_norm": 32.1339111328125,
"learning_rate": 9.166666666666666e-06,
"loss": 0.5741,
"step": 631
},
{
"epoch": 3.511111111111111,
"grad_norm": 14.264232635498047,
"learning_rate": 9.163580246913582e-06,
"loss": 0.6038,
"step": 632
},
{
"epoch": 3.5166666666666666,
"grad_norm": 14.961528778076172,
"learning_rate": 9.160493827160494e-06,
"loss": 0.6064,
"step": 633
},
{
"epoch": 3.522222222222222,
"grad_norm": 17.746173858642578,
"learning_rate": 9.157407407407409e-06,
"loss": 0.6147,
"step": 634
},
{
"epoch": 3.5277777777777777,
"grad_norm": 17.457937240600586,
"learning_rate": 9.15432098765432e-06,
"loss": 0.6512,
"step": 635
},
{
"epoch": 3.533333333333333,
"grad_norm": 21.183460235595703,
"learning_rate": 9.151234567901235e-06,
"loss": 0.3655,
"step": 636
},
{
"epoch": 3.5388888888888888,
"grad_norm": 14.870631217956543,
"learning_rate": 9.148148148148149e-06,
"loss": 0.5417,
"step": 637
},
{
"epoch": 3.5444444444444443,
"grad_norm": 24.757856369018555,
"learning_rate": 9.145061728395063e-06,
"loss": 1.0688,
"step": 638
},
{
"epoch": 3.55,
"grad_norm": 15.744243621826172,
"learning_rate": 9.141975308641975e-06,
"loss": 0.8601,
"step": 639
},
{
"epoch": 3.5555555555555554,
"grad_norm": 16.559350967407227,
"learning_rate": 9.13888888888889e-06,
"loss": 1.0046,
"step": 640
},
{
"epoch": 3.561111111111111,
"grad_norm": 23.673757553100586,
"learning_rate": 9.135802469135803e-06,
"loss": 0.6845,
"step": 641
},
{
"epoch": 3.5666666666666664,
"grad_norm": 22.983318328857422,
"learning_rate": 9.132716049382717e-06,
"loss": 0.7106,
"step": 642
},
{
"epoch": 3.572222222222222,
"grad_norm": 13.164534568786621,
"learning_rate": 9.12962962962963e-06,
"loss": 0.4555,
"step": 643
},
{
"epoch": 3.5777777777777775,
"grad_norm": 20.777469635009766,
"learning_rate": 9.126543209876544e-06,
"loss": 0.9375,
"step": 644
},
{
"epoch": 3.5833333333333335,
"grad_norm": 16.73868751525879,
"learning_rate": 9.123456790123458e-06,
"loss": 0.6817,
"step": 645
},
{
"epoch": 3.588888888888889,
"grad_norm": 16.01927947998047,
"learning_rate": 9.120370370370372e-06,
"loss": 0.4983,
"step": 646
},
{
"epoch": 3.5944444444444446,
"grad_norm": 27.305980682373047,
"learning_rate": 9.117283950617286e-06,
"loss": 0.5503,
"step": 647
},
{
"epoch": 3.6,
"grad_norm": 17.53700065612793,
"learning_rate": 9.114197530864198e-06,
"loss": 0.7147,
"step": 648
},
{
"epoch": 3.6055555555555556,
"grad_norm": 12.461562156677246,
"learning_rate": 9.111111111111112e-06,
"loss": 0.6493,
"step": 649
},
{
"epoch": 3.611111111111111,
"grad_norm": 14.6154146194458,
"learning_rate": 9.108024691358024e-06,
"loss": 0.7067,
"step": 650
},
{
"epoch": 3.6166666666666667,
"grad_norm": 18.934053421020508,
"learning_rate": 9.10493827160494e-06,
"loss": 0.4784,
"step": 651
},
{
"epoch": 3.6222222222222222,
"grad_norm": 31.40237808227539,
"learning_rate": 9.101851851851853e-06,
"loss": 0.7975,
"step": 652
},
{
"epoch": 3.6277777777777778,
"grad_norm": 10.939482688903809,
"learning_rate": 9.098765432098767e-06,
"loss": 0.5747,
"step": 653
},
{
"epoch": 3.6333333333333333,
"grad_norm": 25.574121475219727,
"learning_rate": 9.095679012345679e-06,
"loss": 0.6472,
"step": 654
},
{
"epoch": 3.638888888888889,
"grad_norm": 18.108610153198242,
"learning_rate": 9.092592592592593e-06,
"loss": 0.6899,
"step": 655
},
{
"epoch": 3.6444444444444444,
"grad_norm": 16.675331115722656,
"learning_rate": 9.089506172839507e-06,
"loss": 0.6691,
"step": 656
},
{
"epoch": 3.65,
"grad_norm": 21.19760513305664,
"learning_rate": 9.086419753086421e-06,
"loss": 0.6764,
"step": 657
},
{
"epoch": 3.6555555555555554,
"grad_norm": 15.48531723022461,
"learning_rate": 9.083333333333333e-06,
"loss": 0.5477,
"step": 658
},
{
"epoch": 3.661111111111111,
"grad_norm": 23.12394142150879,
"learning_rate": 9.080246913580247e-06,
"loss": 0.6071,
"step": 659
},
{
"epoch": 3.6666666666666665,
"grad_norm": 25.71583366394043,
"learning_rate": 9.077160493827161e-06,
"loss": 0.6048,
"step": 660
},
{
"epoch": 3.6722222222222225,
"grad_norm": 15.405563354492188,
"learning_rate": 9.074074074074075e-06,
"loss": 0.6131,
"step": 661
},
{
"epoch": 3.677777777777778,
"grad_norm": 22.763952255249023,
"learning_rate": 9.070987654320988e-06,
"loss": 0.6363,
"step": 662
},
{
"epoch": 3.6833333333333336,
"grad_norm": 33.49644088745117,
"learning_rate": 9.067901234567902e-06,
"loss": 0.6464,
"step": 663
},
{
"epoch": 3.688888888888889,
"grad_norm": 31.969093322753906,
"learning_rate": 9.064814814814816e-06,
"loss": 0.757,
"step": 664
},
{
"epoch": 3.6944444444444446,
"grad_norm": 19.101903915405273,
"learning_rate": 9.06172839506173e-06,
"loss": 0.5089,
"step": 665
},
{
"epoch": 3.7,
"grad_norm": 24.31672477722168,
"learning_rate": 9.058641975308642e-06,
"loss": 0.9219,
"step": 666
},
{
"epoch": 3.7055555555555557,
"grad_norm": 20.79106330871582,
"learning_rate": 9.055555555555556e-06,
"loss": 0.5958,
"step": 667
},
{
"epoch": 3.7111111111111112,
"grad_norm": 29.51933479309082,
"learning_rate": 9.05246913580247e-06,
"loss": 0.6961,
"step": 668
},
{
"epoch": 3.716666666666667,
"grad_norm": 23.477502822875977,
"learning_rate": 9.049382716049383e-06,
"loss": 0.7093,
"step": 669
},
{
"epoch": 3.7222222222222223,
"grad_norm": 19.536151885986328,
"learning_rate": 9.046296296296298e-06,
"loss": 0.4635,
"step": 670
},
{
"epoch": 3.727777777777778,
"grad_norm": 15.866363525390625,
"learning_rate": 9.04320987654321e-06,
"loss": 0.3737,
"step": 671
},
{
"epoch": 3.7333333333333334,
"grad_norm": 21.574115753173828,
"learning_rate": 9.040123456790125e-06,
"loss": 0.7271,
"step": 672
},
{
"epoch": 3.738888888888889,
"grad_norm": 25.03012466430664,
"learning_rate": 9.037037037037037e-06,
"loss": 0.7023,
"step": 673
},
{
"epoch": 3.7444444444444445,
"grad_norm": 16.97786521911621,
"learning_rate": 9.033950617283951e-06,
"loss": 0.4697,
"step": 674
},
{
"epoch": 3.75,
"grad_norm": 26.971641540527344,
"learning_rate": 9.030864197530865e-06,
"loss": 0.5392,
"step": 675
},
{
"epoch": 3.7555555555555555,
"grad_norm": 15.743075370788574,
"learning_rate": 9.027777777777779e-06,
"loss": 0.5776,
"step": 676
},
{
"epoch": 3.761111111111111,
"grad_norm": 14.024499893188477,
"learning_rate": 9.024691358024691e-06,
"loss": 0.5634,
"step": 677
},
{
"epoch": 3.7666666666666666,
"grad_norm": 18.959421157836914,
"learning_rate": 9.021604938271605e-06,
"loss": 0.5036,
"step": 678
},
{
"epoch": 3.772222222222222,
"grad_norm": 16.229045867919922,
"learning_rate": 9.01851851851852e-06,
"loss": 1.1612,
"step": 679
},
{
"epoch": 3.7777777777777777,
"grad_norm": 30.457162857055664,
"learning_rate": 9.015432098765433e-06,
"loss": 0.5275,
"step": 680
},
{
"epoch": 3.783333333333333,
"grad_norm": 33.41271209716797,
"learning_rate": 9.012345679012346e-06,
"loss": 0.645,
"step": 681
},
{
"epoch": 3.7888888888888888,
"grad_norm": 22.111900329589844,
"learning_rate": 9.00925925925926e-06,
"loss": 0.868,
"step": 682
},
{
"epoch": 3.7944444444444443,
"grad_norm": 18.137083053588867,
"learning_rate": 9.006172839506174e-06,
"loss": 0.7002,
"step": 683
},
{
"epoch": 3.8,
"grad_norm": 13.36413860321045,
"learning_rate": 9.003086419753088e-06,
"loss": 0.6085,
"step": 684
},
{
"epoch": 3.8055555555555554,
"grad_norm": 14.389131546020508,
"learning_rate": 9e-06,
"loss": 0.8092,
"step": 685
},
{
"epoch": 3.811111111111111,
"grad_norm": 13.729713439941406,
"learning_rate": 8.996913580246914e-06,
"loss": 0.4765,
"step": 686
},
{
"epoch": 3.8166666666666664,
"grad_norm": 26.075780868530273,
"learning_rate": 8.993827160493828e-06,
"loss": 0.8261,
"step": 687
},
{
"epoch": 3.822222222222222,
"grad_norm": 17.264720916748047,
"learning_rate": 8.99074074074074e-06,
"loss": 0.4704,
"step": 688
},
{
"epoch": 3.8277777777777775,
"grad_norm": 25.14128303527832,
"learning_rate": 8.987654320987655e-06,
"loss": 0.8707,
"step": 689
},
{
"epoch": 3.8333333333333335,
"grad_norm": 15.374534606933594,
"learning_rate": 8.984567901234569e-06,
"loss": 0.5167,
"step": 690
},
{
"epoch": 3.838888888888889,
"grad_norm": 31.216812133789062,
"learning_rate": 8.981481481481483e-06,
"loss": 0.607,
"step": 691
},
{
"epoch": 3.8444444444444446,
"grad_norm": 30.137184143066406,
"learning_rate": 8.978395061728395e-06,
"loss": 0.6082,
"step": 692
},
{
"epoch": 3.85,
"grad_norm": 14.966889381408691,
"learning_rate": 8.975308641975309e-06,
"loss": 0.5482,
"step": 693
},
{
"epoch": 3.8555555555555556,
"grad_norm": 8.753317832946777,
"learning_rate": 8.972222222222223e-06,
"loss": 0.435,
"step": 694
},
{
"epoch": 3.861111111111111,
"grad_norm": 34.25310516357422,
"learning_rate": 8.969135802469137e-06,
"loss": 0.7353,
"step": 695
},
{
"epoch": 3.8666666666666667,
"grad_norm": 12.877778053283691,
"learning_rate": 8.96604938271605e-06,
"loss": 0.4608,
"step": 696
},
{
"epoch": 3.8722222222222222,
"grad_norm": 14.511269569396973,
"learning_rate": 8.962962962962963e-06,
"loss": 0.6105,
"step": 697
},
{
"epoch": 3.8777777777777778,
"grad_norm": 17.272348403930664,
"learning_rate": 8.959876543209878e-06,
"loss": 0.4586,
"step": 698
},
{
"epoch": 3.8833333333333333,
"grad_norm": 18.791168212890625,
"learning_rate": 8.956790123456792e-06,
"loss": 0.838,
"step": 699
},
{
"epoch": 3.888888888888889,
"grad_norm": 15.736895561218262,
"learning_rate": 8.953703703703704e-06,
"loss": 0.5747,
"step": 700
},
{
"epoch": 3.8944444444444444,
"grad_norm": 12.22475528717041,
"learning_rate": 8.950617283950618e-06,
"loss": 0.4267,
"step": 701
},
{
"epoch": 3.9,
"grad_norm": 25.614973068237305,
"learning_rate": 8.947530864197532e-06,
"loss": 0.785,
"step": 702
},
{
"epoch": 3.9055555555555554,
"grad_norm": 13.748687744140625,
"learning_rate": 8.944444444444446e-06,
"loss": 0.6915,
"step": 703
},
{
"epoch": 3.911111111111111,
"grad_norm": 17.33505630493164,
"learning_rate": 8.941358024691358e-06,
"loss": 0.6068,
"step": 704
},
{
"epoch": 3.9166666666666665,
"grad_norm": 10.916605949401855,
"learning_rate": 8.938271604938272e-06,
"loss": 0.5185,
"step": 705
},
{
"epoch": 3.9222222222222225,
"grad_norm": 18.64676856994629,
"learning_rate": 8.935185185185186e-06,
"loss": 0.4519,
"step": 706
},
{
"epoch": 3.927777777777778,
"grad_norm": 23.35108757019043,
"learning_rate": 8.932098765432099e-06,
"loss": 0.9695,
"step": 707
},
{
"epoch": 3.9333333333333336,
"grad_norm": 19.011865615844727,
"learning_rate": 8.929012345679013e-06,
"loss": 0.5701,
"step": 708
},
{
"epoch": 3.938888888888889,
"grad_norm": 12.141427993774414,
"learning_rate": 8.925925925925927e-06,
"loss": 0.6008,
"step": 709
},
{
"epoch": 3.9444444444444446,
"grad_norm": 9.531394958496094,
"learning_rate": 8.92283950617284e-06,
"loss": 0.7595,
"step": 710
},
{
"epoch": 3.95,
"grad_norm": 13.701532363891602,
"learning_rate": 8.919753086419753e-06,
"loss": 0.773,
"step": 711
},
{
"epoch": 3.9555555555555557,
"grad_norm": 16.876903533935547,
"learning_rate": 8.916666666666667e-06,
"loss": 0.3825,
"step": 712
},
{
"epoch": 3.9611111111111112,
"grad_norm": 16.813692092895508,
"learning_rate": 8.913580246913581e-06,
"loss": 0.5438,
"step": 713
},
{
"epoch": 3.966666666666667,
"grad_norm": 17.988662719726562,
"learning_rate": 8.910493827160495e-06,
"loss": 0.4428,
"step": 714
},
{
"epoch": 3.9722222222222223,
"grad_norm": 25.35084342956543,
"learning_rate": 8.907407407407408e-06,
"loss": 0.5684,
"step": 715
},
{
"epoch": 3.977777777777778,
"grad_norm": 22.71883773803711,
"learning_rate": 8.904320987654322e-06,
"loss": 0.8601,
"step": 716
},
{
"epoch": 3.9833333333333334,
"grad_norm": 25.50968360900879,
"learning_rate": 8.901234567901236e-06,
"loss": 0.7322,
"step": 717
},
{
"epoch": 3.988888888888889,
"grad_norm": 25.797161102294922,
"learning_rate": 8.89814814814815e-06,
"loss": 0.7149,
"step": 718
},
{
"epoch": 3.9944444444444445,
"grad_norm": 17.746795654296875,
"learning_rate": 8.895061728395062e-06,
"loss": 0.5966,
"step": 719
},
{
"epoch": 4.0,
"grad_norm": 16.720645904541016,
"learning_rate": 8.891975308641976e-06,
"loss": 0.5718,
"step": 720
},
{
"epoch": 4.0,
"eval_accuracy": 0.8558780127889818,
"eval_f1": 0.8511215539105644,
"eval_loss": 0.5960990190505981,
"eval_runtime": 2.8432,
"eval_samples_per_second": 715.043,
"eval_steps_per_second": 5.627,
"step": 720
},
{
"epoch": 4.0055555555555555,
"grad_norm": 18.65631675720215,
"learning_rate": 8.888888888888888e-06,
"loss": 0.6622,
"step": 721
},
{
"epoch": 4.011111111111111,
"grad_norm": 23.166629791259766,
"learning_rate": 8.885802469135804e-06,
"loss": 0.5034,
"step": 722
},
{
"epoch": 4.016666666666667,
"grad_norm": 31.60239601135254,
"learning_rate": 8.882716049382716e-06,
"loss": 0.4737,
"step": 723
},
{
"epoch": 4.022222222222222,
"grad_norm": 12.673126220703125,
"learning_rate": 8.87962962962963e-06,
"loss": 0.5225,
"step": 724
},
{
"epoch": 4.027777777777778,
"grad_norm": 14.534958839416504,
"learning_rate": 8.876543209876544e-06,
"loss": 0.4724,
"step": 725
},
{
"epoch": 4.033333333333333,
"grad_norm": 33.59807205200195,
"learning_rate": 8.873456790123458e-06,
"loss": 0.6537,
"step": 726
},
{
"epoch": 4.038888888888889,
"grad_norm": 16.496828079223633,
"learning_rate": 8.87037037037037e-06,
"loss": 0.7239,
"step": 727
},
{
"epoch": 4.044444444444444,
"grad_norm": 29.68638801574707,
"learning_rate": 8.867283950617285e-06,
"loss": 0.3486,
"step": 728
},
{
"epoch": 4.05,
"grad_norm": 12.28073501586914,
"learning_rate": 8.864197530864199e-06,
"loss": 0.7942,
"step": 729
},
{
"epoch": 4.055555555555555,
"grad_norm": 13.227290153503418,
"learning_rate": 8.861111111111111e-06,
"loss": 0.5356,
"step": 730
},
{
"epoch": 4.061111111111111,
"grad_norm": 10.79533576965332,
"learning_rate": 8.858024691358025e-06,
"loss": 0.4167,
"step": 731
},
{
"epoch": 4.066666666666666,
"grad_norm": 9.73001766204834,
"learning_rate": 8.85493827160494e-06,
"loss": 0.3423,
"step": 732
},
{
"epoch": 4.072222222222222,
"grad_norm": 14.941519737243652,
"learning_rate": 8.851851851851853e-06,
"loss": 0.6794,
"step": 733
},
{
"epoch": 4.0777777777777775,
"grad_norm": 24.651830673217773,
"learning_rate": 8.848765432098766e-06,
"loss": 0.5116,
"step": 734
},
{
"epoch": 4.083333333333333,
"grad_norm": 14.781612396240234,
"learning_rate": 8.84567901234568e-06,
"loss": 0.4926,
"step": 735
},
{
"epoch": 4.088888888888889,
"grad_norm": 18.740571975708008,
"learning_rate": 8.842592592592594e-06,
"loss": 0.4071,
"step": 736
},
{
"epoch": 4.094444444444444,
"grad_norm": 22.705121994018555,
"learning_rate": 8.839506172839508e-06,
"loss": 0.5307,
"step": 737
},
{
"epoch": 4.1,
"grad_norm": 12.600275993347168,
"learning_rate": 8.83641975308642e-06,
"loss": 0.378,
"step": 738
},
{
"epoch": 4.105555555555555,
"grad_norm": 24.5230712890625,
"learning_rate": 8.833333333333334e-06,
"loss": 0.3442,
"step": 739
},
{
"epoch": 4.111111111111111,
"grad_norm": 12.460128784179688,
"learning_rate": 8.830246913580246e-06,
"loss": 0.5128,
"step": 740
},
{
"epoch": 4.116666666666666,
"grad_norm": 14.723420143127441,
"learning_rate": 8.827160493827162e-06,
"loss": 0.4446,
"step": 741
},
{
"epoch": 4.122222222222222,
"grad_norm": 8.89914608001709,
"learning_rate": 8.824074074074074e-06,
"loss": 0.3123,
"step": 742
},
{
"epoch": 4.127777777777778,
"grad_norm": 11.381391525268555,
"learning_rate": 8.820987654320988e-06,
"loss": 0.2673,
"step": 743
},
{
"epoch": 4.133333333333334,
"grad_norm": 11.488757133483887,
"learning_rate": 8.8179012345679e-06,
"loss": 0.4913,
"step": 744
},
{
"epoch": 4.138888888888889,
"grad_norm": 16.916728973388672,
"learning_rate": 8.814814814814817e-06,
"loss": 0.8002,
"step": 745
},
{
"epoch": 4.144444444444445,
"grad_norm": 21.353578567504883,
"learning_rate": 8.811728395061729e-06,
"loss": 0.4788,
"step": 746
},
{
"epoch": 4.15,
"grad_norm": 15.028318405151367,
"learning_rate": 8.808641975308643e-06,
"loss": 0.5801,
"step": 747
},
{
"epoch": 4.155555555555556,
"grad_norm": 56.202457427978516,
"learning_rate": 8.805555555555557e-06,
"loss": 0.6184,
"step": 748
},
{
"epoch": 4.161111111111111,
"grad_norm": 12.65611457824707,
"learning_rate": 8.80246913580247e-06,
"loss": 0.4021,
"step": 749
},
{
"epoch": 4.166666666666667,
"grad_norm": 19.3060302734375,
"learning_rate": 8.799382716049383e-06,
"loss": 0.8697,
"step": 750
},
{
"epoch": 4.1722222222222225,
"grad_norm": 24.290172576904297,
"learning_rate": 8.796296296296297e-06,
"loss": 0.5228,
"step": 751
},
{
"epoch": 4.177777777777778,
"grad_norm": 18.594539642333984,
"learning_rate": 8.793209876543211e-06,
"loss": 0.4756,
"step": 752
},
{
"epoch": 4.183333333333334,
"grad_norm": 14.212244033813477,
"learning_rate": 8.790123456790124e-06,
"loss": 0.3455,
"step": 753
},
{
"epoch": 4.188888888888889,
"grad_norm": 245.55152893066406,
"learning_rate": 8.787037037037038e-06,
"loss": 0.3346,
"step": 754
},
{
"epoch": 4.194444444444445,
"grad_norm": 28.92985725402832,
"learning_rate": 8.783950617283952e-06,
"loss": 0.4626,
"step": 755
},
{
"epoch": 4.2,
"grad_norm": 19.841949462890625,
"learning_rate": 8.780864197530866e-06,
"loss": 0.4695,
"step": 756
},
{
"epoch": 4.205555555555556,
"grad_norm": 14.304591178894043,
"learning_rate": 8.777777777777778e-06,
"loss": 0.6841,
"step": 757
},
{
"epoch": 4.211111111111111,
"grad_norm": 15.611128807067871,
"learning_rate": 8.774691358024692e-06,
"loss": 0.5826,
"step": 758
},
{
"epoch": 4.216666666666667,
"grad_norm": 12.774888038635254,
"learning_rate": 8.771604938271606e-06,
"loss": 0.4598,
"step": 759
},
{
"epoch": 4.222222222222222,
"grad_norm": 19.699813842773438,
"learning_rate": 8.76851851851852e-06,
"loss": 0.5903,
"step": 760
},
{
"epoch": 4.227777777777778,
"grad_norm": 18.494253158569336,
"learning_rate": 8.765432098765432e-06,
"loss": 0.543,
"step": 761
},
{
"epoch": 4.233333333333333,
"grad_norm": 29.524717330932617,
"learning_rate": 8.762345679012347e-06,
"loss": 0.3778,
"step": 762
},
{
"epoch": 4.238888888888889,
"grad_norm": 14.297577857971191,
"learning_rate": 8.759259259259259e-06,
"loss": 0.4453,
"step": 763
},
{
"epoch": 4.2444444444444445,
"grad_norm": 10.409721374511719,
"learning_rate": 8.756172839506175e-06,
"loss": 0.4629,
"step": 764
},
{
"epoch": 4.25,
"grad_norm": 16.948129653930664,
"learning_rate": 8.753086419753087e-06,
"loss": 0.7346,
"step": 765
},
{
"epoch": 4.2555555555555555,
"grad_norm": 10.056136131286621,
"learning_rate": 8.750000000000001e-06,
"loss": 0.346,
"step": 766
},
{
"epoch": 4.261111111111111,
"grad_norm": 21.393980026245117,
"learning_rate": 8.746913580246913e-06,
"loss": 0.5435,
"step": 767
},
{
"epoch": 4.266666666666667,
"grad_norm": 23.266908645629883,
"learning_rate": 8.743827160493827e-06,
"loss": 0.549,
"step": 768
},
{
"epoch": 4.272222222222222,
"grad_norm": 19.02581787109375,
"learning_rate": 8.740740740740741e-06,
"loss": 0.5,
"step": 769
},
{
"epoch": 4.277777777777778,
"grad_norm": 15.653654098510742,
"learning_rate": 8.737654320987655e-06,
"loss": 0.7734,
"step": 770
},
{
"epoch": 4.283333333333333,
"grad_norm": 25.532291412353516,
"learning_rate": 8.73456790123457e-06,
"loss": 0.3558,
"step": 771
},
{
"epoch": 4.288888888888889,
"grad_norm": 20.221200942993164,
"learning_rate": 8.731481481481482e-06,
"loss": 0.4728,
"step": 772
},
{
"epoch": 4.294444444444444,
"grad_norm": 14.985522270202637,
"learning_rate": 8.728395061728396e-06,
"loss": 0.4685,
"step": 773
},
{
"epoch": 4.3,
"grad_norm": 22.214859008789062,
"learning_rate": 8.72530864197531e-06,
"loss": 0.5244,
"step": 774
},
{
"epoch": 4.305555555555555,
"grad_norm": 26.8780460357666,
"learning_rate": 8.722222222222224e-06,
"loss": 0.4147,
"step": 775
},
{
"epoch": 4.311111111111111,
"grad_norm": 16.539508819580078,
"learning_rate": 8.719135802469136e-06,
"loss": 0.5035,
"step": 776
},
{
"epoch": 4.316666666666666,
"grad_norm": 8.931195259094238,
"learning_rate": 8.71604938271605e-06,
"loss": 0.4416,
"step": 777
},
{
"epoch": 4.322222222222222,
"grad_norm": 28.190427780151367,
"learning_rate": 8.712962962962964e-06,
"loss": 0.7189,
"step": 778
},
{
"epoch": 4.3277777777777775,
"grad_norm": 15.663671493530273,
"learning_rate": 8.709876543209878e-06,
"loss": 0.3424,
"step": 779
},
{
"epoch": 4.333333333333333,
"grad_norm": 14.375828742980957,
"learning_rate": 8.70679012345679e-06,
"loss": 0.4014,
"step": 780
},
{
"epoch": 4.338888888888889,
"grad_norm": 22.598970413208008,
"learning_rate": 8.703703703703705e-06,
"loss": 0.6786,
"step": 781
},
{
"epoch": 4.344444444444444,
"grad_norm": 11.055100440979004,
"learning_rate": 8.700617283950617e-06,
"loss": 0.6201,
"step": 782
},
{
"epoch": 4.35,
"grad_norm": 11.375622749328613,
"learning_rate": 8.697530864197533e-06,
"loss": 0.3433,
"step": 783
},
{
"epoch": 4.355555555555555,
"grad_norm": 21.58877182006836,
"learning_rate": 8.694444444444445e-06,
"loss": 0.4696,
"step": 784
},
{
"epoch": 4.361111111111111,
"grad_norm": 13.949239730834961,
"learning_rate": 8.691358024691359e-06,
"loss": 0.674,
"step": 785
},
{
"epoch": 4.366666666666666,
"grad_norm": 22.768238067626953,
"learning_rate": 8.688271604938271e-06,
"loss": 0.6242,
"step": 786
},
{
"epoch": 4.372222222222222,
"grad_norm": 16.96993064880371,
"learning_rate": 8.685185185185185e-06,
"loss": 0.5035,
"step": 787
},
{
"epoch": 4.377777777777778,
"grad_norm": 28.044849395751953,
"learning_rate": 8.6820987654321e-06,
"loss": 0.6814,
"step": 788
},
{
"epoch": 4.383333333333334,
"grad_norm": 17.218509674072266,
"learning_rate": 8.679012345679013e-06,
"loss": 0.3799,
"step": 789
},
{
"epoch": 4.388888888888889,
"grad_norm": 29.069774627685547,
"learning_rate": 8.675925925925926e-06,
"loss": 0.707,
"step": 790
},
{
"epoch": 4.394444444444445,
"grad_norm": 16.448474884033203,
"learning_rate": 8.67283950617284e-06,
"loss": 0.6829,
"step": 791
},
{
"epoch": 4.4,
"grad_norm": 19.360740661621094,
"learning_rate": 8.669753086419754e-06,
"loss": 0.6152,
"step": 792
},
{
"epoch": 4.405555555555556,
"grad_norm": 24.0657901763916,
"learning_rate": 8.666666666666668e-06,
"loss": 0.5875,
"step": 793
},
{
"epoch": 4.411111111111111,
"grad_norm": 26.00684356689453,
"learning_rate": 8.663580246913582e-06,
"loss": 0.3914,
"step": 794
},
{
"epoch": 4.416666666666667,
"grad_norm": 32.4747314453125,
"learning_rate": 8.660493827160494e-06,
"loss": 0.6821,
"step": 795
},
{
"epoch": 4.4222222222222225,
"grad_norm": 28.572830200195312,
"learning_rate": 8.657407407407408e-06,
"loss": 0.4298,
"step": 796
},
{
"epoch": 4.427777777777778,
"grad_norm": 16.99812126159668,
"learning_rate": 8.654320987654322e-06,
"loss": 0.4659,
"step": 797
},
{
"epoch": 4.433333333333334,
"grad_norm": 19.992013931274414,
"learning_rate": 8.651234567901236e-06,
"loss": 0.4735,
"step": 798
},
{
"epoch": 4.438888888888889,
"grad_norm": 25.926891326904297,
"learning_rate": 8.648148148148149e-06,
"loss": 0.5852,
"step": 799
},
{
"epoch": 4.444444444444445,
"grad_norm": 24.482112884521484,
"learning_rate": 8.645061728395063e-06,
"loss": 0.3667,
"step": 800
},
{
"epoch": 4.45,
"grad_norm": 30.76417350769043,
"learning_rate": 8.641975308641975e-06,
"loss": 0.7462,
"step": 801
},
{
"epoch": 4.455555555555556,
"grad_norm": 22.247135162353516,
"learning_rate": 8.63888888888889e-06,
"loss": 0.5666,
"step": 802
},
{
"epoch": 4.461111111111111,
"grad_norm": 27.1633358001709,
"learning_rate": 8.635802469135803e-06,
"loss": 0.477,
"step": 803
},
{
"epoch": 4.466666666666667,
"grad_norm": 20.604455947875977,
"learning_rate": 8.632716049382717e-06,
"loss": 0.5632,
"step": 804
},
{
"epoch": 4.472222222222222,
"grad_norm": 10.812111854553223,
"learning_rate": 8.62962962962963e-06,
"loss": 0.358,
"step": 805
},
{
"epoch": 4.477777777777778,
"grad_norm": 16.50082015991211,
"learning_rate": 8.626543209876543e-06,
"loss": 0.5076,
"step": 806
},
{
"epoch": 4.483333333333333,
"grad_norm": 19.90973472595215,
"learning_rate": 8.623456790123457e-06,
"loss": 0.6094,
"step": 807
},
{
"epoch": 4.488888888888889,
"grad_norm": 15.760126113891602,
"learning_rate": 8.620370370370371e-06,
"loss": 0.4051,
"step": 808
},
{
"epoch": 4.4944444444444445,
"grad_norm": 57.194053649902344,
"learning_rate": 8.617283950617284e-06,
"loss": 0.4337,
"step": 809
},
{
"epoch": 4.5,
"grad_norm": 17.12649154663086,
"learning_rate": 8.614197530864198e-06,
"loss": 0.4297,
"step": 810
},
{
"epoch": 4.5055555555555555,
"grad_norm": 23.242645263671875,
"learning_rate": 8.611111111111112e-06,
"loss": 0.4333,
"step": 811
},
{
"epoch": 4.511111111111111,
"grad_norm": 17.099470138549805,
"learning_rate": 8.608024691358026e-06,
"loss": 0.7701,
"step": 812
},
{
"epoch": 4.516666666666667,
"grad_norm": 13.897005081176758,
"learning_rate": 8.604938271604938e-06,
"loss": 0.3584,
"step": 813
},
{
"epoch": 4.522222222222222,
"grad_norm": 16.195846557617188,
"learning_rate": 8.601851851851852e-06,
"loss": 0.5203,
"step": 814
},
{
"epoch": 4.527777777777778,
"grad_norm": 11.307642936706543,
"learning_rate": 8.598765432098766e-06,
"loss": 0.4654,
"step": 815
},
{
"epoch": 4.533333333333333,
"grad_norm": 14.804153442382812,
"learning_rate": 8.59567901234568e-06,
"loss": 0.6957,
"step": 816
},
{
"epoch": 4.538888888888889,
"grad_norm": 31.17090606689453,
"learning_rate": 8.592592592592593e-06,
"loss": 0.414,
"step": 817
},
{
"epoch": 4.544444444444444,
"grad_norm": 12.374228477478027,
"learning_rate": 8.589506172839507e-06,
"loss": 0.475,
"step": 818
},
{
"epoch": 4.55,
"grad_norm": 21.71500587463379,
"learning_rate": 8.58641975308642e-06,
"loss": 0.5077,
"step": 819
},
{
"epoch": 4.555555555555555,
"grad_norm": 22.110288619995117,
"learning_rate": 8.583333333333333e-06,
"loss": 0.4722,
"step": 820
},
{
"epoch": 4.561111111111111,
"grad_norm": 14.233537673950195,
"learning_rate": 8.580246913580249e-06,
"loss": 0.4159,
"step": 821
},
{
"epoch": 4.566666666666666,
"grad_norm": 13.813685417175293,
"learning_rate": 8.577160493827161e-06,
"loss": 0.4518,
"step": 822
},
{
"epoch": 4.572222222222222,
"grad_norm": 19.93982696533203,
"learning_rate": 8.574074074074075e-06,
"loss": 0.3097,
"step": 823
},
{
"epoch": 4.5777777777777775,
"grad_norm": 18.751399993896484,
"learning_rate": 8.570987654320987e-06,
"loss": 0.6019,
"step": 824
},
{
"epoch": 4.583333333333333,
"grad_norm": 17.501331329345703,
"learning_rate": 8.567901234567903e-06,
"loss": 0.4849,
"step": 825
},
{
"epoch": 4.588888888888889,
"grad_norm": 17.303667068481445,
"learning_rate": 8.564814814814816e-06,
"loss": 0.586,
"step": 826
},
{
"epoch": 4.594444444444444,
"grad_norm": 35.515525817871094,
"learning_rate": 8.56172839506173e-06,
"loss": 0.6715,
"step": 827
},
{
"epoch": 4.6,
"grad_norm": 18.049251556396484,
"learning_rate": 8.558641975308642e-06,
"loss": 0.3848,
"step": 828
},
{
"epoch": 4.605555555555555,
"grad_norm": 24.437461853027344,
"learning_rate": 8.555555555555556e-06,
"loss": 0.3772,
"step": 829
},
{
"epoch": 4.611111111111111,
"grad_norm": 10.942232131958008,
"learning_rate": 8.55246913580247e-06,
"loss": 0.3941,
"step": 830
},
{
"epoch": 4.616666666666667,
"grad_norm": 8.364413261413574,
"learning_rate": 8.549382716049384e-06,
"loss": 0.4585,
"step": 831
},
{
"epoch": 4.622222222222222,
"grad_norm": 11.149219512939453,
"learning_rate": 8.546296296296296e-06,
"loss": 0.2881,
"step": 832
},
{
"epoch": 4.627777777777778,
"grad_norm": 8.898666381835938,
"learning_rate": 8.54320987654321e-06,
"loss": 0.4959,
"step": 833
},
{
"epoch": 4.633333333333333,
"grad_norm": 15.481371879577637,
"learning_rate": 8.540123456790124e-06,
"loss": 0.4618,
"step": 834
},
{
"epoch": 4.638888888888889,
"grad_norm": 15.174581527709961,
"learning_rate": 8.537037037037038e-06,
"loss": 0.7706,
"step": 835
},
{
"epoch": 4.644444444444445,
"grad_norm": 11.719181060791016,
"learning_rate": 8.53395061728395e-06,
"loss": 0.5501,
"step": 836
},
{
"epoch": 4.65,
"grad_norm": 12.273602485656738,
"learning_rate": 8.530864197530865e-06,
"loss": 0.4092,
"step": 837
},
{
"epoch": 4.655555555555556,
"grad_norm": 29.038755416870117,
"learning_rate": 8.527777777777779e-06,
"loss": 0.627,
"step": 838
},
{
"epoch": 4.661111111111111,
"grad_norm": 13.3413667678833,
"learning_rate": 8.524691358024693e-06,
"loss": 0.3694,
"step": 839
},
{
"epoch": 4.666666666666667,
"grad_norm": 20.8958683013916,
"learning_rate": 8.521604938271605e-06,
"loss": 0.3951,
"step": 840
},
{
"epoch": 4.6722222222222225,
"grad_norm": 15.5842924118042,
"learning_rate": 8.518518518518519e-06,
"loss": 0.6659,
"step": 841
},
{
"epoch": 4.677777777777778,
"grad_norm": 12.584623336791992,
"learning_rate": 8.515432098765433e-06,
"loss": 0.3986,
"step": 842
},
{
"epoch": 4.683333333333334,
"grad_norm": 15.762527465820312,
"learning_rate": 8.512345679012346e-06,
"loss": 0.4249,
"step": 843
},
{
"epoch": 4.688888888888889,
"grad_norm": 16.59547996520996,
"learning_rate": 8.509259259259261e-06,
"loss": 0.4341,
"step": 844
},
{
"epoch": 4.694444444444445,
"grad_norm": 17.25592041015625,
"learning_rate": 8.506172839506174e-06,
"loss": 0.6525,
"step": 845
},
{
"epoch": 4.7,
"grad_norm": 18.5655517578125,
"learning_rate": 8.503086419753088e-06,
"loss": 0.3794,
"step": 846
},
{
"epoch": 4.705555555555556,
"grad_norm": 21.072689056396484,
"learning_rate": 8.5e-06,
"loss": 0.7516,
"step": 847
},
{
"epoch": 4.711111111111111,
"grad_norm": 10.87837028503418,
"learning_rate": 8.496913580246914e-06,
"loss": 0.2471,
"step": 848
},
{
"epoch": 4.716666666666667,
"grad_norm": 14.980316162109375,
"learning_rate": 8.493827160493828e-06,
"loss": 0.7328,
"step": 849
},
{
"epoch": 4.722222222222222,
"grad_norm": 21.583118438720703,
"learning_rate": 8.490740740740742e-06,
"loss": 0.4137,
"step": 850
},
{
"epoch": 4.727777777777778,
"grad_norm": 35.45997619628906,
"learning_rate": 8.487654320987654e-06,
"loss": 0.7645,
"step": 851
},
{
"epoch": 4.733333333333333,
"grad_norm": 11.314993858337402,
"learning_rate": 8.484567901234568e-06,
"loss": 0.3099,
"step": 852
},
{
"epoch": 4.738888888888889,
"grad_norm": 8.86207103729248,
"learning_rate": 8.481481481481482e-06,
"loss": 0.5461,
"step": 853
},
{
"epoch": 4.7444444444444445,
"grad_norm": 14.366178512573242,
"learning_rate": 8.478395061728396e-06,
"loss": 0.5408,
"step": 854
},
{
"epoch": 4.75,
"grad_norm": 14.328187942504883,
"learning_rate": 8.475308641975309e-06,
"loss": 0.3602,
"step": 855
},
{
"epoch": 4.7555555555555555,
"grad_norm": 13.543745994567871,
"learning_rate": 8.472222222222223e-06,
"loss": 0.5003,
"step": 856
},
{
"epoch": 4.761111111111111,
"grad_norm": 22.046802520751953,
"learning_rate": 8.469135802469137e-06,
"loss": 0.5614,
"step": 857
},
{
"epoch": 4.766666666666667,
"grad_norm": 28.54222869873047,
"learning_rate": 8.466049382716051e-06,
"loss": 0.4009,
"step": 858
},
{
"epoch": 4.772222222222222,
"grad_norm": 16.681034088134766,
"learning_rate": 8.462962962962963e-06,
"loss": 0.3142,
"step": 859
},
{
"epoch": 4.777777777777778,
"grad_norm": 43.25300598144531,
"learning_rate": 8.459876543209877e-06,
"loss": 0.4156,
"step": 860
},
{
"epoch": 4.783333333333333,
"grad_norm": 10.724509239196777,
"learning_rate": 8.456790123456791e-06,
"loss": 0.4335,
"step": 861
},
{
"epoch": 4.788888888888889,
"grad_norm": 21.650609970092773,
"learning_rate": 8.453703703703704e-06,
"loss": 0.5598,
"step": 862
},
{
"epoch": 4.794444444444444,
"grad_norm": 23.953426361083984,
"learning_rate": 8.450617283950618e-06,
"loss": 0.6387,
"step": 863
},
{
"epoch": 4.8,
"grad_norm": 21.83122444152832,
"learning_rate": 8.447530864197532e-06,
"loss": 0.7582,
"step": 864
},
{
"epoch": 4.805555555555555,
"grad_norm": 17.28409194946289,
"learning_rate": 8.444444444444446e-06,
"loss": 0.3136,
"step": 865
},
{
"epoch": 4.811111111111111,
"grad_norm": 17.18514060974121,
"learning_rate": 8.441358024691358e-06,
"loss": 0.5966,
"step": 866
},
{
"epoch": 4.816666666666666,
"grad_norm": 18.162811279296875,
"learning_rate": 8.438271604938272e-06,
"loss": 0.4819,
"step": 867
},
{
"epoch": 4.822222222222222,
"grad_norm": 18.217239379882812,
"learning_rate": 8.435185185185186e-06,
"loss": 0.5703,
"step": 868
},
{
"epoch": 4.8277777777777775,
"grad_norm": 14.398390769958496,
"learning_rate": 8.4320987654321e-06,
"loss": 0.4885,
"step": 869
},
{
"epoch": 4.833333333333333,
"grad_norm": 9.580870628356934,
"learning_rate": 8.429012345679012e-06,
"loss": 0.2997,
"step": 870
},
{
"epoch": 4.838888888888889,
"grad_norm": 16.308378219604492,
"learning_rate": 8.425925925925926e-06,
"loss": 0.2902,
"step": 871
},
{
"epoch": 4.844444444444444,
"grad_norm": 25.160934448242188,
"learning_rate": 8.42283950617284e-06,
"loss": 0.3516,
"step": 872
},
{
"epoch": 4.85,
"grad_norm": 26.116060256958008,
"learning_rate": 8.419753086419754e-06,
"loss": 0.4718,
"step": 873
},
{
"epoch": 4.855555555555555,
"grad_norm": 22.947628021240234,
"learning_rate": 8.416666666666667e-06,
"loss": 0.4692,
"step": 874
},
{
"epoch": 4.861111111111111,
"grad_norm": 18.54252815246582,
"learning_rate": 8.413580246913581e-06,
"loss": 0.4316,
"step": 875
},
{
"epoch": 4.866666666666667,
"grad_norm": 23.331586837768555,
"learning_rate": 8.410493827160495e-06,
"loss": 0.6016,
"step": 876
},
{
"epoch": 4.872222222222222,
"grad_norm": 20.33098030090332,
"learning_rate": 8.407407407407409e-06,
"loss": 0.6549,
"step": 877
},
{
"epoch": 4.877777777777778,
"grad_norm": 10.560401916503906,
"learning_rate": 8.404320987654321e-06,
"loss": 0.2911,
"step": 878
},
{
"epoch": 4.883333333333333,
"grad_norm": 27.942914962768555,
"learning_rate": 8.401234567901235e-06,
"loss": 0.4907,
"step": 879
},
{
"epoch": 4.888888888888889,
"grad_norm": 14.45740032196045,
"learning_rate": 8.39814814814815e-06,
"loss": 0.588,
"step": 880
},
{
"epoch": 4.894444444444445,
"grad_norm": 20.92599105834961,
"learning_rate": 8.395061728395062e-06,
"loss": 0.4587,
"step": 881
},
{
"epoch": 4.9,
"grad_norm": 17.305904388427734,
"learning_rate": 8.391975308641976e-06,
"loss": 0.4774,
"step": 882
},
{
"epoch": 4.905555555555556,
"grad_norm": 21.06772804260254,
"learning_rate": 8.38888888888889e-06,
"loss": 0.6486,
"step": 883
},
{
"epoch": 4.911111111111111,
"grad_norm": 15.468618392944336,
"learning_rate": 8.385802469135804e-06,
"loss": 0.3967,
"step": 884
},
{
"epoch": 4.916666666666667,
"grad_norm": 16.755640029907227,
"learning_rate": 8.382716049382716e-06,
"loss": 0.5551,
"step": 885
},
{
"epoch": 4.9222222222222225,
"grad_norm": 21.62795066833496,
"learning_rate": 8.37962962962963e-06,
"loss": 0.5789,
"step": 886
},
{
"epoch": 4.927777777777778,
"grad_norm": 17.327972412109375,
"learning_rate": 8.376543209876544e-06,
"loss": 0.3864,
"step": 887
},
{
"epoch": 4.933333333333334,
"grad_norm": 13.771781921386719,
"learning_rate": 8.373456790123458e-06,
"loss": 0.4177,
"step": 888
},
{
"epoch": 4.938888888888889,
"grad_norm": 30.814905166625977,
"learning_rate": 8.37037037037037e-06,
"loss": 0.576,
"step": 889
},
{
"epoch": 4.944444444444445,
"grad_norm": 12.91354751586914,
"learning_rate": 8.367283950617285e-06,
"loss": 0.3486,
"step": 890
},
{
"epoch": 4.95,
"grad_norm": 21.149139404296875,
"learning_rate": 8.364197530864199e-06,
"loss": 0.6243,
"step": 891
},
{
"epoch": 4.955555555555556,
"grad_norm": 11.770221710205078,
"learning_rate": 8.361111111111113e-06,
"loss": 0.3991,
"step": 892
},
{
"epoch": 4.961111111111111,
"grad_norm": 11.918582916259766,
"learning_rate": 8.358024691358025e-06,
"loss": 0.2799,
"step": 893
},
{
"epoch": 4.966666666666667,
"grad_norm": 16.054378509521484,
"learning_rate": 8.354938271604939e-06,
"loss": 0.439,
"step": 894
},
{
"epoch": 4.972222222222222,
"grad_norm": 19.463388442993164,
"learning_rate": 8.351851851851851e-06,
"loss": 0.3958,
"step": 895
},
{
"epoch": 4.977777777777778,
"grad_norm": 16.706642150878906,
"learning_rate": 8.348765432098767e-06,
"loss": 0.6595,
"step": 896
},
{
"epoch": 4.983333333333333,
"grad_norm": 18.5977840423584,
"learning_rate": 8.34567901234568e-06,
"loss": 0.2558,
"step": 897
},
{
"epoch": 4.988888888888889,
"grad_norm": 22.62540626525879,
"learning_rate": 8.342592592592593e-06,
"loss": 0.6212,
"step": 898
},
{
"epoch": 4.9944444444444445,
"grad_norm": 15.402458190917969,
"learning_rate": 8.339506172839507e-06,
"loss": 0.401,
"step": 899
},
{
"epoch": 5.0,
"grad_norm": 28.00405502319336,
"learning_rate": 8.33641975308642e-06,
"loss": 0.5927,
"step": 900
},
{
"epoch": 5.0,
"eval_accuracy": 0.8760452533202164,
"eval_f1": 0.8736486802762851,
"eval_loss": 0.5418870449066162,
"eval_runtime": 2.8416,
"eval_samples_per_second": 715.444,
"eval_steps_per_second": 5.631,
"step": 900
},
{
"epoch": 5.0055555555555555,
"grad_norm": 15.406761169433594,
"learning_rate": 8.333333333333334e-06,
"loss": 0.3703,
"step": 901
},
{
"epoch": 5.011111111111111,
"grad_norm": 6.3102946281433105,
"learning_rate": 8.330246913580248e-06,
"loss": 0.3949,
"step": 902
},
{
"epoch": 5.016666666666667,
"grad_norm": 10.752458572387695,
"learning_rate": 8.327160493827162e-06,
"loss": 0.4031,
"step": 903
},
{
"epoch": 5.022222222222222,
"grad_norm": 13.93024730682373,
"learning_rate": 8.324074074074074e-06,
"loss": 0.1769,
"step": 904
},
{
"epoch": 5.027777777777778,
"grad_norm": 11.461437225341797,
"learning_rate": 8.320987654320988e-06,
"loss": 0.3916,
"step": 905
},
{
"epoch": 5.033333333333333,
"grad_norm": 41.082828521728516,
"learning_rate": 8.317901234567902e-06,
"loss": 0.3623,
"step": 906
},
{
"epoch": 5.038888888888889,
"grad_norm": 15.181744575500488,
"learning_rate": 8.314814814814816e-06,
"loss": 0.4712,
"step": 907
},
{
"epoch": 5.044444444444444,
"grad_norm": 9.552958488464355,
"learning_rate": 8.311728395061729e-06,
"loss": 0.504,
"step": 908
},
{
"epoch": 5.05,
"grad_norm": 21.95808982849121,
"learning_rate": 8.308641975308643e-06,
"loss": 0.4292,
"step": 909
},
{
"epoch": 5.055555555555555,
"grad_norm": 10.555428504943848,
"learning_rate": 8.305555555555557e-06,
"loss": 0.3115,
"step": 910
},
{
"epoch": 5.061111111111111,
"grad_norm": 12.733278274536133,
"learning_rate": 8.30246913580247e-06,
"loss": 0.4094,
"step": 911
},
{
"epoch": 5.066666666666666,
"grad_norm": 14.666433334350586,
"learning_rate": 8.299382716049383e-06,
"loss": 0.3276,
"step": 912
},
{
"epoch": 5.072222222222222,
"grad_norm": 16.59703826904297,
"learning_rate": 8.296296296296297e-06,
"loss": 0.342,
"step": 913
},
{
"epoch": 5.0777777777777775,
"grad_norm": 22.9014835357666,
"learning_rate": 8.29320987654321e-06,
"loss": 0.4778,
"step": 914
},
{
"epoch": 5.083333333333333,
"grad_norm": 11.608020782470703,
"learning_rate": 8.290123456790125e-06,
"loss": 0.6971,
"step": 915
},
{
"epoch": 5.088888888888889,
"grad_norm": 10.085397720336914,
"learning_rate": 8.287037037037037e-06,
"loss": 0.1892,
"step": 916
},
{
"epoch": 5.094444444444444,
"grad_norm": 23.465362548828125,
"learning_rate": 8.283950617283951e-06,
"loss": 0.4736,
"step": 917
},
{
"epoch": 5.1,
"grad_norm": 20.25006103515625,
"learning_rate": 8.280864197530864e-06,
"loss": 0.3885,
"step": 918
},
{
"epoch": 5.105555555555555,
"grad_norm": 19.402090072631836,
"learning_rate": 8.277777777777778e-06,
"loss": 0.4871,
"step": 919
},
{
"epoch": 5.111111111111111,
"grad_norm": 14.869335174560547,
"learning_rate": 8.274691358024692e-06,
"loss": 0.6305,
"step": 920
},
{
"epoch": 5.116666666666666,
"grad_norm": 17.50324058532715,
"learning_rate": 8.271604938271606e-06,
"loss": 0.3482,
"step": 921
},
{
"epoch": 5.122222222222222,
"grad_norm": 12.98111343383789,
"learning_rate": 8.26851851851852e-06,
"loss": 0.3724,
"step": 922
},
{
"epoch": 5.127777777777778,
"grad_norm": 20.554723739624023,
"learning_rate": 8.265432098765432e-06,
"loss": 0.2753,
"step": 923
},
{
"epoch": 5.133333333333334,
"grad_norm": 19.079635620117188,
"learning_rate": 8.262345679012346e-06,
"loss": 0.3706,
"step": 924
},
{
"epoch": 5.138888888888889,
"grad_norm": 35.26353073120117,
"learning_rate": 8.25925925925926e-06,
"loss": 0.4723,
"step": 925
},
{
"epoch": 5.144444444444445,
"grad_norm": 10.232580184936523,
"learning_rate": 8.256172839506174e-06,
"loss": 0.4666,
"step": 926
},
{
"epoch": 5.15,
"grad_norm": 16.127304077148438,
"learning_rate": 8.253086419753087e-06,
"loss": 0.5275,
"step": 927
},
{
"epoch": 5.155555555555556,
"grad_norm": 15.718029022216797,
"learning_rate": 8.25e-06,
"loss": 0.4841,
"step": 928
},
{
"epoch": 5.161111111111111,
"grad_norm": 15.551223754882812,
"learning_rate": 8.246913580246915e-06,
"loss": 0.5804,
"step": 929
},
{
"epoch": 5.166666666666667,
"grad_norm": 19.83995246887207,
"learning_rate": 8.243827160493829e-06,
"loss": 0.2737,
"step": 930
},
{
"epoch": 5.1722222222222225,
"grad_norm": 15.971796989440918,
"learning_rate": 8.240740740740741e-06,
"loss": 0.3878,
"step": 931
},
{
"epoch": 5.177777777777778,
"grad_norm": 22.177865982055664,
"learning_rate": 8.237654320987655e-06,
"loss": 0.2916,
"step": 932
},
{
"epoch": 5.183333333333334,
"grad_norm": 9.027350425720215,
"learning_rate": 8.234567901234567e-06,
"loss": 0.3782,
"step": 933
},
{
"epoch": 5.188888888888889,
"grad_norm": 11.89077091217041,
"learning_rate": 8.231481481481483e-06,
"loss": 0.334,
"step": 934
},
{
"epoch": 5.194444444444445,
"grad_norm": 19.829364776611328,
"learning_rate": 8.228395061728395e-06,
"loss": 0.65,
"step": 935
},
{
"epoch": 5.2,
"grad_norm": 16.116426467895508,
"learning_rate": 8.22530864197531e-06,
"loss": 0.2898,
"step": 936
},
{
"epoch": 5.205555555555556,
"grad_norm": 15.972787857055664,
"learning_rate": 8.222222222222222e-06,
"loss": 0.4311,
"step": 937
},
{
"epoch": 5.211111111111111,
"grad_norm": 18.0800838470459,
"learning_rate": 8.219135802469138e-06,
"loss": 0.4185,
"step": 938
},
{
"epoch": 5.216666666666667,
"grad_norm": 24.232620239257812,
"learning_rate": 8.21604938271605e-06,
"loss": 0.2696,
"step": 939
},
{
"epoch": 5.222222222222222,
"grad_norm": 26.06591796875,
"learning_rate": 8.212962962962964e-06,
"loss": 0.3911,
"step": 940
},
{
"epoch": 5.227777777777778,
"grad_norm": 12.250744819641113,
"learning_rate": 8.209876543209876e-06,
"loss": 0.3516,
"step": 941
},
{
"epoch": 5.233333333333333,
"grad_norm": 24.61111831665039,
"learning_rate": 8.20679012345679e-06,
"loss": 0.4143,
"step": 942
},
{
"epoch": 5.238888888888889,
"grad_norm": 11.262822151184082,
"learning_rate": 8.203703703703704e-06,
"loss": 0.4713,
"step": 943
},
{
"epoch": 5.2444444444444445,
"grad_norm": 16.94364356994629,
"learning_rate": 8.200617283950618e-06,
"loss": 0.4131,
"step": 944
},
{
"epoch": 5.25,
"grad_norm": 14.955778121948242,
"learning_rate": 8.197530864197532e-06,
"loss": 0.5513,
"step": 945
},
{
"epoch": 5.2555555555555555,
"grad_norm": 18.809206008911133,
"learning_rate": 8.194444444444445e-06,
"loss": 0.3721,
"step": 946
},
{
"epoch": 5.261111111111111,
"grad_norm": 14.033462524414062,
"learning_rate": 8.191358024691359e-06,
"loss": 0.4245,
"step": 947
},
{
"epoch": 5.266666666666667,
"grad_norm": 16.5278377532959,
"learning_rate": 8.188271604938273e-06,
"loss": 0.3974,
"step": 948
},
{
"epoch": 5.272222222222222,
"grad_norm": 15.156519889831543,
"learning_rate": 8.185185185185187e-06,
"loss": 0.3049,
"step": 949
},
{
"epoch": 5.277777777777778,
"grad_norm": 11.715588569641113,
"learning_rate": 8.182098765432099e-06,
"loss": 0.4629,
"step": 950
},
{
"epoch": 5.283333333333333,
"grad_norm": 10.499783515930176,
"learning_rate": 8.179012345679013e-06,
"loss": 0.3293,
"step": 951
},
{
"epoch": 5.288888888888889,
"grad_norm": 21.634489059448242,
"learning_rate": 8.175925925925925e-06,
"loss": 0.5053,
"step": 952
},
{
"epoch": 5.294444444444444,
"grad_norm": 15.405562400817871,
"learning_rate": 8.172839506172841e-06,
"loss": 0.3491,
"step": 953
},
{
"epoch": 5.3,
"grad_norm": 30.764324188232422,
"learning_rate": 8.169753086419754e-06,
"loss": 0.4541,
"step": 954
},
{
"epoch": 5.305555555555555,
"grad_norm": 19.161483764648438,
"learning_rate": 8.166666666666668e-06,
"loss": 0.2623,
"step": 955
},
{
"epoch": 5.311111111111111,
"grad_norm": 12.378495216369629,
"learning_rate": 8.16358024691358e-06,
"loss": 0.4322,
"step": 956
},
{
"epoch": 5.316666666666666,
"grad_norm": 15.872624397277832,
"learning_rate": 8.160493827160496e-06,
"loss": 0.4732,
"step": 957
},
{
"epoch": 5.322222222222222,
"grad_norm": 20.600618362426758,
"learning_rate": 8.157407407407408e-06,
"loss": 0.3363,
"step": 958
},
{
"epoch": 5.3277777777777775,
"grad_norm": 18.330320358276367,
"learning_rate": 8.154320987654322e-06,
"loss": 0.6463,
"step": 959
},
{
"epoch": 5.333333333333333,
"grad_norm": 5.381742000579834,
"learning_rate": 8.151234567901234e-06,
"loss": 0.2587,
"step": 960
},
{
"epoch": 5.338888888888889,
"grad_norm": 7.641402244567871,
"learning_rate": 8.148148148148148e-06,
"loss": 0.1824,
"step": 961
},
{
"epoch": 5.344444444444444,
"grad_norm": 15.888916015625,
"learning_rate": 8.145061728395062e-06,
"loss": 0.3663,
"step": 962
},
{
"epoch": 5.35,
"grad_norm": 22.692323684692383,
"learning_rate": 8.141975308641976e-06,
"loss": 0.5305,
"step": 963
},
{
"epoch": 5.355555555555555,
"grad_norm": 13.61213493347168,
"learning_rate": 8.138888888888889e-06,
"loss": 0.3299,
"step": 964
},
{
"epoch": 5.361111111111111,
"grad_norm": 13.87636661529541,
"learning_rate": 8.135802469135803e-06,
"loss": 0.5953,
"step": 965
},
{
"epoch": 5.366666666666666,
"grad_norm": 21.12693214416504,
"learning_rate": 8.132716049382717e-06,
"loss": 0.2663,
"step": 966
},
{
"epoch": 5.372222222222222,
"grad_norm": 15.204812049865723,
"learning_rate": 8.12962962962963e-06,
"loss": 0.464,
"step": 967
},
{
"epoch": 5.377777777777778,
"grad_norm": 16.028457641601562,
"learning_rate": 8.126543209876545e-06,
"loss": 0.3978,
"step": 968
},
{
"epoch": 5.383333333333334,
"grad_norm": 15.075647354125977,
"learning_rate": 8.123456790123457e-06,
"loss": 0.2734,
"step": 969
},
{
"epoch": 5.388888888888889,
"grad_norm": 14.820575714111328,
"learning_rate": 8.120370370370371e-06,
"loss": 0.186,
"step": 970
},
{
"epoch": 5.394444444444445,
"grad_norm": 7.6285080909729,
"learning_rate": 8.117283950617285e-06,
"loss": 0.2745,
"step": 971
},
{
"epoch": 5.4,
"grad_norm": 16.675508499145508,
"learning_rate": 8.1141975308642e-06,
"loss": 0.4356,
"step": 972
},
{
"epoch": 5.405555555555556,
"grad_norm": 17.0025691986084,
"learning_rate": 8.111111111111112e-06,
"loss": 0.5742,
"step": 973
},
{
"epoch": 5.411111111111111,
"grad_norm": 13.115673065185547,
"learning_rate": 8.108024691358026e-06,
"loss": 0.4636,
"step": 974
},
{
"epoch": 5.416666666666667,
"grad_norm": 14.074502944946289,
"learning_rate": 8.104938271604938e-06,
"loss": 0.2402,
"step": 975
},
{
"epoch": 5.4222222222222225,
"grad_norm": 23.843425750732422,
"learning_rate": 8.101851851851854e-06,
"loss": 0.3546,
"step": 976
},
{
"epoch": 5.427777777777778,
"grad_norm": 19.858240127563477,
"learning_rate": 8.098765432098766e-06,
"loss": 0.5601,
"step": 977
},
{
"epoch": 5.433333333333334,
"grad_norm": 17.90315818786621,
"learning_rate": 8.09567901234568e-06,
"loss": 0.335,
"step": 978
},
{
"epoch": 5.438888888888889,
"grad_norm": 16.37443733215332,
"learning_rate": 8.092592592592592e-06,
"loss": 0.5106,
"step": 979
},
{
"epoch": 5.444444444444445,
"grad_norm": 10.860307693481445,
"learning_rate": 8.089506172839506e-06,
"loss": 0.312,
"step": 980
},
{
"epoch": 5.45,
"grad_norm": 9.383811950683594,
"learning_rate": 8.08641975308642e-06,
"loss": 0.2738,
"step": 981
},
{
"epoch": 5.455555555555556,
"grad_norm": 34.03207778930664,
"learning_rate": 8.083333333333334e-06,
"loss": 0.3908,
"step": 982
},
{
"epoch": 5.461111111111111,
"grad_norm": 28.67666244506836,
"learning_rate": 8.080246913580247e-06,
"loss": 0.3129,
"step": 983
},
{
"epoch": 5.466666666666667,
"grad_norm": 10.749366760253906,
"learning_rate": 8.07716049382716e-06,
"loss": 0.1689,
"step": 984
},
{
"epoch": 5.472222222222222,
"grad_norm": 20.4220027923584,
"learning_rate": 8.074074074074075e-06,
"loss": 0.3307,
"step": 985
},
{
"epoch": 5.477777777777778,
"grad_norm": 18.146717071533203,
"learning_rate": 8.070987654320989e-06,
"loss": 0.558,
"step": 986
},
{
"epoch": 5.483333333333333,
"grad_norm": 28.5622501373291,
"learning_rate": 8.067901234567901e-06,
"loss": 0.4196,
"step": 987
},
{
"epoch": 5.488888888888889,
"grad_norm": 16.377267837524414,
"learning_rate": 8.064814814814815e-06,
"loss": 0.4386,
"step": 988
},
{
"epoch": 5.4944444444444445,
"grad_norm": 16.05144691467285,
"learning_rate": 8.06172839506173e-06,
"loss": 0.5572,
"step": 989
},
{
"epoch": 5.5,
"grad_norm": 15.861221313476562,
"learning_rate": 8.058641975308643e-06,
"loss": 0.7578,
"step": 990
},
{
"epoch": 5.5055555555555555,
"grad_norm": 17.1833553314209,
"learning_rate": 8.055555555555557e-06,
"loss": 0.4666,
"step": 991
},
{
"epoch": 5.511111111111111,
"grad_norm": 11.853373527526855,
"learning_rate": 8.05246913580247e-06,
"loss": 0.296,
"step": 992
},
{
"epoch": 5.516666666666667,
"grad_norm": 7.886599540710449,
"learning_rate": 8.049382716049384e-06,
"loss": 0.1958,
"step": 993
},
{
"epoch": 5.522222222222222,
"grad_norm": 18.930152893066406,
"learning_rate": 8.046296296296296e-06,
"loss": 0.4084,
"step": 994
},
{
"epoch": 5.527777777777778,
"grad_norm": 10.792703628540039,
"learning_rate": 8.043209876543212e-06,
"loss": 0.2888,
"step": 995
},
{
"epoch": 5.533333333333333,
"grad_norm": 55.35970687866211,
"learning_rate": 8.040123456790124e-06,
"loss": 0.5254,
"step": 996
},
{
"epoch": 5.538888888888889,
"grad_norm": 26.201583862304688,
"learning_rate": 8.037037037037038e-06,
"loss": 0.4708,
"step": 997
},
{
"epoch": 5.544444444444444,
"grad_norm": 16.518232345581055,
"learning_rate": 8.03395061728395e-06,
"loss": 0.371,
"step": 998
},
{
"epoch": 5.55,
"grad_norm": 26.966638565063477,
"learning_rate": 8.030864197530864e-06,
"loss": 0.4132,
"step": 999
},
{
"epoch": 5.555555555555555,
"grad_norm": 20.517305374145508,
"learning_rate": 8.027777777777778e-06,
"loss": 0.5014,
"step": 1000
},
{
"epoch": 5.561111111111111,
"grad_norm": 17.489166259765625,
"learning_rate": 8.024691358024692e-06,
"loss": 0.4514,
"step": 1001
},
{
"epoch": 5.566666666666666,
"grad_norm": 15.035685539245605,
"learning_rate": 8.021604938271605e-06,
"loss": 0.7065,
"step": 1002
},
{
"epoch": 5.572222222222222,
"grad_norm": 17.408788681030273,
"learning_rate": 8.018518518518519e-06,
"loss": 0.2257,
"step": 1003
},
{
"epoch": 5.5777777777777775,
"grad_norm": 16.627120971679688,
"learning_rate": 8.015432098765433e-06,
"loss": 0.3904,
"step": 1004
},
{
"epoch": 5.583333333333333,
"grad_norm": 8.177781105041504,
"learning_rate": 8.012345679012347e-06,
"loss": 0.295,
"step": 1005
},
{
"epoch": 5.588888888888889,
"grad_norm": 13.076864242553711,
"learning_rate": 8.00925925925926e-06,
"loss": 0.2995,
"step": 1006
},
{
"epoch": 5.594444444444444,
"grad_norm": 19.452505111694336,
"learning_rate": 8.006172839506173e-06,
"loss": 0.4319,
"step": 1007
},
{
"epoch": 5.6,
"grad_norm": 11.798609733581543,
"learning_rate": 8.003086419753087e-06,
"loss": 0.3139,
"step": 1008
},
{
"epoch": 5.605555555555555,
"grad_norm": 16.662443161010742,
"learning_rate": 8.000000000000001e-06,
"loss": 0.3286,
"step": 1009
},
{
"epoch": 5.611111111111111,
"grad_norm": 20.248193740844727,
"learning_rate": 7.996913580246914e-06,
"loss": 0.2628,
"step": 1010
},
{
"epoch": 5.616666666666667,
"grad_norm": 13.917230606079102,
"learning_rate": 7.993827160493828e-06,
"loss": 0.2055,
"step": 1011
},
{
"epoch": 5.622222222222222,
"grad_norm": 10.28135871887207,
"learning_rate": 7.990740740740742e-06,
"loss": 0.325,
"step": 1012
},
{
"epoch": 5.627777777777778,
"grad_norm": 12.814302444458008,
"learning_rate": 7.987654320987654e-06,
"loss": 0.1313,
"step": 1013
},
{
"epoch": 5.633333333333333,
"grad_norm": 22.24582862854004,
"learning_rate": 7.984567901234568e-06,
"loss": 0.5459,
"step": 1014
},
{
"epoch": 5.638888888888889,
"grad_norm": 6.826903820037842,
"learning_rate": 7.981481481481482e-06,
"loss": 0.2911,
"step": 1015
},
{
"epoch": 5.644444444444445,
"grad_norm": 22.076688766479492,
"learning_rate": 7.978395061728396e-06,
"loss": 0.3445,
"step": 1016
},
{
"epoch": 5.65,
"grad_norm": 22.35431480407715,
"learning_rate": 7.975308641975308e-06,
"loss": 0.5185,
"step": 1017
},
{
"epoch": 5.655555555555556,
"grad_norm": 16.039209365844727,
"learning_rate": 7.972222222222224e-06,
"loss": 0.4918,
"step": 1018
},
{
"epoch": 5.661111111111111,
"grad_norm": 17.073875427246094,
"learning_rate": 7.969135802469137e-06,
"loss": 0.5215,
"step": 1019
},
{
"epoch": 5.666666666666667,
"grad_norm": 14.959405899047852,
"learning_rate": 7.96604938271605e-06,
"loss": 0.3922,
"step": 1020
},
{
"epoch": 5.6722222222222225,
"grad_norm": 37.374351501464844,
"learning_rate": 7.962962962962963e-06,
"loss": 0.403,
"step": 1021
},
{
"epoch": 5.677777777777778,
"grad_norm": 15.685274124145508,
"learning_rate": 7.959876543209877e-06,
"loss": 0.3782,
"step": 1022
},
{
"epoch": 5.683333333333334,
"grad_norm": 15.072765350341797,
"learning_rate": 7.956790123456791e-06,
"loss": 0.3231,
"step": 1023
},
{
"epoch": 5.688888888888889,
"grad_norm": 19.986473083496094,
"learning_rate": 7.953703703703705e-06,
"loss": 0.3793,
"step": 1024
},
{
"epoch": 5.694444444444445,
"grad_norm": 13.523053169250488,
"learning_rate": 7.950617283950617e-06,
"loss": 0.3417,
"step": 1025
},
{
"epoch": 5.7,
"grad_norm": 18.199356079101562,
"learning_rate": 7.947530864197531e-06,
"loss": 0.3614,
"step": 1026
},
{
"epoch": 5.705555555555556,
"grad_norm": 13.200125694274902,
"learning_rate": 7.944444444444445e-06,
"loss": 0.5162,
"step": 1027
},
{
"epoch": 5.711111111111111,
"grad_norm": 10.920044898986816,
"learning_rate": 7.94135802469136e-06,
"loss": 0.4385,
"step": 1028
},
{
"epoch": 5.716666666666667,
"grad_norm": 13.774800300598145,
"learning_rate": 7.938271604938272e-06,
"loss": 0.4436,
"step": 1029
},
{
"epoch": 5.722222222222222,
"grad_norm": 15.603097915649414,
"learning_rate": 7.935185185185186e-06,
"loss": 0.337,
"step": 1030
},
{
"epoch": 5.727777777777778,
"grad_norm": 30.628389358520508,
"learning_rate": 7.9320987654321e-06,
"loss": 0.5912,
"step": 1031
},
{
"epoch": 5.733333333333333,
"grad_norm": 36.31143569946289,
"learning_rate": 7.929012345679012e-06,
"loss": 0.384,
"step": 1032
},
{
"epoch": 5.738888888888889,
"grad_norm": 24.652690887451172,
"learning_rate": 7.925925925925926e-06,
"loss": 0.6998,
"step": 1033
},
{
"epoch": 5.7444444444444445,
"grad_norm": 11.123702049255371,
"learning_rate": 7.92283950617284e-06,
"loss": 0.4479,
"step": 1034
},
{
"epoch": 5.75,
"grad_norm": 10.184444427490234,
"learning_rate": 7.919753086419754e-06,
"loss": 0.1797,
"step": 1035
},
{
"epoch": 5.7555555555555555,
"grad_norm": 17.617961883544922,
"learning_rate": 7.916666666666667e-06,
"loss": 0.4116,
"step": 1036
},
{
"epoch": 5.761111111111111,
"grad_norm": 21.36412811279297,
"learning_rate": 7.91358024691358e-06,
"loss": 0.4481,
"step": 1037
},
{
"epoch": 5.766666666666667,
"grad_norm": 16.263256072998047,
"learning_rate": 7.910493827160495e-06,
"loss": 0.2305,
"step": 1038
},
{
"epoch": 5.772222222222222,
"grad_norm": 16.634103775024414,
"learning_rate": 7.907407407407409e-06,
"loss": 0.5835,
"step": 1039
},
{
"epoch": 5.777777777777778,
"grad_norm": 18.563491821289062,
"learning_rate": 7.904320987654321e-06,
"loss": 0.2289,
"step": 1040
},
{
"epoch": 5.783333333333333,
"grad_norm": 20.61016273498535,
"learning_rate": 7.901234567901235e-06,
"loss": 0.4323,
"step": 1041
},
{
"epoch": 5.788888888888889,
"grad_norm": 16.213394165039062,
"learning_rate": 7.898148148148149e-06,
"loss": 0.316,
"step": 1042
},
{
"epoch": 5.794444444444444,
"grad_norm": 24.950937271118164,
"learning_rate": 7.895061728395063e-06,
"loss": 0.3697,
"step": 1043
},
{
"epoch": 5.8,
"grad_norm": 29.531902313232422,
"learning_rate": 7.891975308641975e-06,
"loss": 0.4579,
"step": 1044
},
{
"epoch": 5.805555555555555,
"grad_norm": 13.958169937133789,
"learning_rate": 7.88888888888889e-06,
"loss": 0.349,
"step": 1045
},
{
"epoch": 5.811111111111111,
"grad_norm": 20.32596778869629,
"learning_rate": 7.885802469135803e-06,
"loss": 0.2492,
"step": 1046
},
{
"epoch": 5.816666666666666,
"grad_norm": 11.119446754455566,
"learning_rate": 7.882716049382717e-06,
"loss": 0.3239,
"step": 1047
},
{
"epoch": 5.822222222222222,
"grad_norm": 13.333819389343262,
"learning_rate": 7.87962962962963e-06,
"loss": 0.2195,
"step": 1048
},
{
"epoch": 5.8277777777777775,
"grad_norm": 10.771352767944336,
"learning_rate": 7.876543209876544e-06,
"loss": 0.2709,
"step": 1049
},
{
"epoch": 5.833333333333333,
"grad_norm": 17.558191299438477,
"learning_rate": 7.873456790123458e-06,
"loss": 0.2933,
"step": 1050
},
{
"epoch": 5.838888888888889,
"grad_norm": 20.61951446533203,
"learning_rate": 7.870370370370372e-06,
"loss": 0.5769,
"step": 1051
},
{
"epoch": 5.844444444444444,
"grad_norm": 18.65769386291504,
"learning_rate": 7.867283950617284e-06,
"loss": 0.3102,
"step": 1052
},
{
"epoch": 5.85,
"grad_norm": 9.716289520263672,
"learning_rate": 7.864197530864198e-06,
"loss": 0.3131,
"step": 1053
},
{
"epoch": 5.855555555555555,
"grad_norm": 15.672456741333008,
"learning_rate": 7.861111111111112e-06,
"loss": 0.4108,
"step": 1054
},
{
"epoch": 5.861111111111111,
"grad_norm": 12.297584533691406,
"learning_rate": 7.858024691358025e-06,
"loss": 0.3509,
"step": 1055
},
{
"epoch": 5.866666666666667,
"grad_norm": 12.346840858459473,
"learning_rate": 7.854938271604939e-06,
"loss": 0.2789,
"step": 1056
},
{
"epoch": 5.872222222222222,
"grad_norm": 11.787163734436035,
"learning_rate": 7.851851851851853e-06,
"loss": 0.2129,
"step": 1057
},
{
"epoch": 5.877777777777778,
"grad_norm": 10.568046569824219,
"learning_rate": 7.848765432098767e-06,
"loss": 0.3566,
"step": 1058
},
{
"epoch": 5.883333333333333,
"grad_norm": 15.273694038391113,
"learning_rate": 7.845679012345679e-06,
"loss": 0.3584,
"step": 1059
},
{
"epoch": 5.888888888888889,
"grad_norm": 13.282081604003906,
"learning_rate": 7.842592592592593e-06,
"loss": 0.37,
"step": 1060
},
{
"epoch": 5.894444444444445,
"grad_norm": 19.097129821777344,
"learning_rate": 7.839506172839507e-06,
"loss": 0.5825,
"step": 1061
},
{
"epoch": 5.9,
"grad_norm": 14.569130897521973,
"learning_rate": 7.836419753086421e-06,
"loss": 0.271,
"step": 1062
},
{
"epoch": 5.905555555555556,
"grad_norm": 15.49703598022461,
"learning_rate": 7.833333333333333e-06,
"loss": 0.2682,
"step": 1063
},
{
"epoch": 5.911111111111111,
"grad_norm": 20.997249603271484,
"learning_rate": 7.830246913580247e-06,
"loss": 0.2912,
"step": 1064
},
{
"epoch": 5.916666666666667,
"grad_norm": 10.61372184753418,
"learning_rate": 7.82716049382716e-06,
"loss": 0.4083,
"step": 1065
},
{
"epoch": 5.9222222222222225,
"grad_norm": 13.457418441772461,
"learning_rate": 7.824074074074076e-06,
"loss": 0.3452,
"step": 1066
},
{
"epoch": 5.927777777777778,
"grad_norm": 6.340488910675049,
"learning_rate": 7.820987654320988e-06,
"loss": 0.2289,
"step": 1067
},
{
"epoch": 5.933333333333334,
"grad_norm": 9.599125862121582,
"learning_rate": 7.817901234567902e-06,
"loss": 0.2948,
"step": 1068
},
{
"epoch": 5.938888888888889,
"grad_norm": 15.869513511657715,
"learning_rate": 7.814814814814816e-06,
"loss": 0.3164,
"step": 1069
},
{
"epoch": 5.944444444444445,
"grad_norm": 19.680381774902344,
"learning_rate": 7.81172839506173e-06,
"loss": 0.3809,
"step": 1070
},
{
"epoch": 5.95,
"grad_norm": 9.234379768371582,
"learning_rate": 7.808641975308642e-06,
"loss": 0.3622,
"step": 1071
},
{
"epoch": 5.955555555555556,
"grad_norm": 17.487342834472656,
"learning_rate": 7.805555555555556e-06,
"loss": 0.6377,
"step": 1072
},
{
"epoch": 5.961111111111111,
"grad_norm": 12.99353313446045,
"learning_rate": 7.80246913580247e-06,
"loss": 0.3835,
"step": 1073
},
{
"epoch": 5.966666666666667,
"grad_norm": 20.151302337646484,
"learning_rate": 7.799382716049383e-06,
"loss": 0.391,
"step": 1074
},
{
"epoch": 5.972222222222222,
"grad_norm": 18.664228439331055,
"learning_rate": 7.796296296296297e-06,
"loss": 0.3075,
"step": 1075
},
{
"epoch": 5.977777777777778,
"grad_norm": 24.320371627807617,
"learning_rate": 7.79320987654321e-06,
"loss": 0.5226,
"step": 1076
},
{
"epoch": 5.983333333333333,
"grad_norm": 13.117110252380371,
"learning_rate": 7.790123456790125e-06,
"loss": 0.4465,
"step": 1077
},
{
"epoch": 5.988888888888889,
"grad_norm": 16.577425003051758,
"learning_rate": 7.787037037037037e-06,
"loss": 0.4916,
"step": 1078
},
{
"epoch": 5.9944444444444445,
"grad_norm": 11.056236267089844,
"learning_rate": 7.783950617283951e-06,
"loss": 0.3211,
"step": 1079
},
{
"epoch": 6.0,
"grad_norm": 25.072052001953125,
"learning_rate": 7.780864197530865e-06,
"loss": 0.6134,
"step": 1080
},
{
"epoch": 6.0,
"eval_accuracy": 0.8745696015740285,
"eval_f1": 0.8712733266524848,
"eval_loss": 0.5338748097419739,
"eval_runtime": 2.8311,
"eval_samples_per_second": 718.107,
"eval_steps_per_second": 5.652,
"step": 1080
},
{
"epoch": 6.0055555555555555,
"grad_norm": 7.560239315032959,
"learning_rate": 7.77777777777778e-06,
"loss": 0.1124,
"step": 1081
},
{
"epoch": 6.011111111111111,
"grad_norm": 9.901611328125,
"learning_rate": 7.774691358024692e-06,
"loss": 0.2126,
"step": 1082
},
{
"epoch": 6.016666666666667,
"grad_norm": 14.877492904663086,
"learning_rate": 7.771604938271606e-06,
"loss": 0.2291,
"step": 1083
},
{
"epoch": 6.022222222222222,
"grad_norm": 7.402180194854736,
"learning_rate": 7.76851851851852e-06,
"loss": 0.2346,
"step": 1084
},
{
"epoch": 6.027777777777778,
"grad_norm": 9.319835662841797,
"learning_rate": 7.765432098765434e-06,
"loss": 0.1165,
"step": 1085
},
{
"epoch": 6.033333333333333,
"grad_norm": 12.414939880371094,
"learning_rate": 7.762345679012346e-06,
"loss": 0.3009,
"step": 1086
},
{
"epoch": 6.038888888888889,
"grad_norm": 6.273139953613281,
"learning_rate": 7.75925925925926e-06,
"loss": 0.2336,
"step": 1087
},
{
"epoch": 6.044444444444444,
"grad_norm": 15.231193542480469,
"learning_rate": 7.756172839506172e-06,
"loss": 0.2669,
"step": 1088
},
{
"epoch": 6.05,
"grad_norm": 13.02371597290039,
"learning_rate": 7.753086419753088e-06,
"loss": 0.21,
"step": 1089
},
{
"epoch": 6.055555555555555,
"grad_norm": 35.145904541015625,
"learning_rate": 7.75e-06,
"loss": 0.3193,
"step": 1090
},
{
"epoch": 6.061111111111111,
"grad_norm": 13.974615097045898,
"learning_rate": 7.746913580246914e-06,
"loss": 0.2356,
"step": 1091
},
{
"epoch": 6.066666666666666,
"grad_norm": 13.242432594299316,
"learning_rate": 7.743827160493827e-06,
"loss": 0.2923,
"step": 1092
},
{
"epoch": 6.072222222222222,
"grad_norm": 11.910053253173828,
"learning_rate": 7.74074074074074e-06,
"loss": 0.3543,
"step": 1093
},
{
"epoch": 6.0777777777777775,
"grad_norm": 25.694072723388672,
"learning_rate": 7.737654320987655e-06,
"loss": 0.2408,
"step": 1094
},
{
"epoch": 6.083333333333333,
"grad_norm": 15.267441749572754,
"learning_rate": 7.734567901234569e-06,
"loss": 0.3574,
"step": 1095
},
{
"epoch": 6.088888888888889,
"grad_norm": 11.566980361938477,
"learning_rate": 7.731481481481483e-06,
"loss": 0.3348,
"step": 1096
},
{
"epoch": 6.094444444444444,
"grad_norm": 44.92341613769531,
"learning_rate": 7.728395061728395e-06,
"loss": 0.2378,
"step": 1097
},
{
"epoch": 6.1,
"grad_norm": 12.915955543518066,
"learning_rate": 7.72530864197531e-06,
"loss": 0.3225,
"step": 1098
},
{
"epoch": 6.105555555555555,
"grad_norm": 8.90642261505127,
"learning_rate": 7.722222222222223e-06,
"loss": 0.1715,
"step": 1099
},
{
"epoch": 6.111111111111111,
"grad_norm": 11.226822853088379,
"learning_rate": 7.719135802469137e-06,
"loss": 0.2366,
"step": 1100
},
{
"epoch": 6.116666666666666,
"grad_norm": 8.498125076293945,
"learning_rate": 7.71604938271605e-06,
"loss": 0.205,
"step": 1101
},
{
"epoch": 6.122222222222222,
"grad_norm": 15.950700759887695,
"learning_rate": 7.712962962962964e-06,
"loss": 0.3637,
"step": 1102
},
{
"epoch": 6.127777777777778,
"grad_norm": 25.79600715637207,
"learning_rate": 7.709876543209878e-06,
"loss": 0.3425,
"step": 1103
},
{
"epoch": 6.133333333333334,
"grad_norm": 8.008769989013672,
"learning_rate": 7.706790123456792e-06,
"loss": 0.2097,
"step": 1104
},
{
"epoch": 6.138888888888889,
"grad_norm": 16.743106842041016,
"learning_rate": 7.703703703703704e-06,
"loss": 0.5036,
"step": 1105
},
{
"epoch": 6.144444444444445,
"grad_norm": 16.929655075073242,
"learning_rate": 7.700617283950618e-06,
"loss": 0.367,
"step": 1106
},
{
"epoch": 6.15,
"grad_norm": 14.403095245361328,
"learning_rate": 7.69753086419753e-06,
"loss": 0.4146,
"step": 1107
},
{
"epoch": 6.155555555555556,
"grad_norm": 10.496806144714355,
"learning_rate": 7.694444444444446e-06,
"loss": 0.2151,
"step": 1108
},
{
"epoch": 6.161111111111111,
"grad_norm": 12.011238098144531,
"learning_rate": 7.691358024691358e-06,
"loss": 0.3238,
"step": 1109
},
{
"epoch": 6.166666666666667,
"grad_norm": 18.727020263671875,
"learning_rate": 7.688271604938272e-06,
"loss": 0.5086,
"step": 1110
},
{
"epoch": 6.1722222222222225,
"grad_norm": 15.596710205078125,
"learning_rate": 7.685185185185185e-06,
"loss": 0.4204,
"step": 1111
},
{
"epoch": 6.177777777777778,
"grad_norm": 19.51191520690918,
"learning_rate": 7.682098765432099e-06,
"loss": 0.305,
"step": 1112
},
{
"epoch": 6.183333333333334,
"grad_norm": 20.33986473083496,
"learning_rate": 7.679012345679013e-06,
"loss": 0.3117,
"step": 1113
},
{
"epoch": 6.188888888888889,
"grad_norm": 12.13909912109375,
"learning_rate": 7.675925925925927e-06,
"loss": 0.4183,
"step": 1114
},
{
"epoch": 6.194444444444445,
"grad_norm": 11.940239906311035,
"learning_rate": 7.67283950617284e-06,
"loss": 0.3487,
"step": 1115
},
{
"epoch": 6.2,
"grad_norm": 14.259970664978027,
"learning_rate": 7.669753086419753e-06,
"loss": 0.4169,
"step": 1116
},
{
"epoch": 6.205555555555556,
"grad_norm": 16.459688186645508,
"learning_rate": 7.666666666666667e-06,
"loss": 0.1609,
"step": 1117
},
{
"epoch": 6.211111111111111,
"grad_norm": 14.093705177307129,
"learning_rate": 7.663580246913581e-06,
"loss": 0.4505,
"step": 1118
},
{
"epoch": 6.216666666666667,
"grad_norm": 22.414794921875,
"learning_rate": 7.660493827160495e-06,
"loss": 0.5517,
"step": 1119
},
{
"epoch": 6.222222222222222,
"grad_norm": 13.711812973022461,
"learning_rate": 7.657407407407408e-06,
"loss": 0.3231,
"step": 1120
},
{
"epoch": 6.227777777777778,
"grad_norm": 11.968666076660156,
"learning_rate": 7.654320987654322e-06,
"loss": 0.3485,
"step": 1121
},
{
"epoch": 6.233333333333333,
"grad_norm": 17.047861099243164,
"learning_rate": 7.651234567901236e-06,
"loss": 0.2511,
"step": 1122
},
{
"epoch": 6.238888888888889,
"grad_norm": 17.998977661132812,
"learning_rate": 7.64814814814815e-06,
"loss": 0.3537,
"step": 1123
},
{
"epoch": 6.2444444444444445,
"grad_norm": 7.768537998199463,
"learning_rate": 7.645061728395062e-06,
"loss": 0.1627,
"step": 1124
},
{
"epoch": 6.25,
"grad_norm": 17.230972290039062,
"learning_rate": 7.641975308641976e-06,
"loss": 0.3131,
"step": 1125
},
{
"epoch": 6.2555555555555555,
"grad_norm": 12.922314643859863,
"learning_rate": 7.638888888888888e-06,
"loss": 0.3426,
"step": 1126
},
{
"epoch": 6.261111111111111,
"grad_norm": 10.292222023010254,
"learning_rate": 7.635802469135804e-06,
"loss": 0.46,
"step": 1127
},
{
"epoch": 6.266666666666667,
"grad_norm": 9.794597625732422,
"learning_rate": 7.632716049382716e-06,
"loss": 0.2284,
"step": 1128
},
{
"epoch": 6.272222222222222,
"grad_norm": 10.19261646270752,
"learning_rate": 7.62962962962963e-06,
"loss": 0.2913,
"step": 1129
},
{
"epoch": 6.277777777777778,
"grad_norm": 25.14057731628418,
"learning_rate": 7.626543209876544e-06,
"loss": 0.3837,
"step": 1130
},
{
"epoch": 6.283333333333333,
"grad_norm": 8.539527893066406,
"learning_rate": 7.623456790123458e-06,
"loss": 0.1644,
"step": 1131
},
{
"epoch": 6.288888888888889,
"grad_norm": 10.548667907714844,
"learning_rate": 7.620370370370372e-06,
"loss": 0.3647,
"step": 1132
},
{
"epoch": 6.294444444444444,
"grad_norm": 11.834288597106934,
"learning_rate": 7.617283950617285e-06,
"loss": 0.4488,
"step": 1133
},
{
"epoch": 6.3,
"grad_norm": 9.117725372314453,
"learning_rate": 7.614197530864198e-06,
"loss": 0.2255,
"step": 1134
},
{
"epoch": 6.305555555555555,
"grad_norm": 14.688142776489258,
"learning_rate": 7.611111111111111e-06,
"loss": 0.2137,
"step": 1135
},
{
"epoch": 6.311111111111111,
"grad_norm": 20.047704696655273,
"learning_rate": 7.608024691358026e-06,
"loss": 0.2244,
"step": 1136
},
{
"epoch": 6.316666666666666,
"grad_norm": 8.81223201751709,
"learning_rate": 7.604938271604939e-06,
"loss": 0.2556,
"step": 1137
},
{
"epoch": 6.322222222222222,
"grad_norm": 15.155988693237305,
"learning_rate": 7.6018518518518525e-06,
"loss": 0.2423,
"step": 1138
},
{
"epoch": 6.3277777777777775,
"grad_norm": 16.28636932373047,
"learning_rate": 7.598765432098766e-06,
"loss": 0.2343,
"step": 1139
},
{
"epoch": 6.333333333333333,
"grad_norm": 41.228965759277344,
"learning_rate": 7.595679012345679e-06,
"loss": 0.3486,
"step": 1140
},
{
"epoch": 6.338888888888889,
"grad_norm": 10.061383247375488,
"learning_rate": 7.592592592592594e-06,
"loss": 0.2685,
"step": 1141
},
{
"epoch": 6.344444444444444,
"grad_norm": 20.76047706604004,
"learning_rate": 7.589506172839507e-06,
"loss": 0.4075,
"step": 1142
},
{
"epoch": 6.35,
"grad_norm": 12.74234676361084,
"learning_rate": 7.58641975308642e-06,
"loss": 0.1437,
"step": 1143
},
{
"epoch": 6.355555555555555,
"grad_norm": 25.69351577758789,
"learning_rate": 7.583333333333333e-06,
"loss": 0.3646,
"step": 1144
},
{
"epoch": 6.361111111111111,
"grad_norm": 11.426958084106445,
"learning_rate": 7.580246913580247e-06,
"loss": 0.35,
"step": 1145
},
{
"epoch": 6.366666666666666,
"grad_norm": 16.748708724975586,
"learning_rate": 7.577160493827161e-06,
"loss": 0.7173,
"step": 1146
},
{
"epoch": 6.372222222222222,
"grad_norm": 10.737534523010254,
"learning_rate": 7.5740740740740745e-06,
"loss": 0.4106,
"step": 1147
},
{
"epoch": 6.377777777777778,
"grad_norm": 13.504171371459961,
"learning_rate": 7.5709876543209886e-06,
"loss": 0.291,
"step": 1148
},
{
"epoch": 6.383333333333334,
"grad_norm": 7.725314617156982,
"learning_rate": 7.567901234567902e-06,
"loss": 0.2402,
"step": 1149
},
{
"epoch": 6.388888888888889,
"grad_norm": 17.03736114501953,
"learning_rate": 7.564814814814816e-06,
"loss": 0.4704,
"step": 1150
},
{
"epoch": 6.394444444444445,
"grad_norm": 24.675554275512695,
"learning_rate": 7.561728395061729e-06,
"loss": 0.4878,
"step": 1151
},
{
"epoch": 6.4,
"grad_norm": 22.863554000854492,
"learning_rate": 7.558641975308643e-06,
"loss": 0.4213,
"step": 1152
},
{
"epoch": 6.405555555555556,
"grad_norm": 21.61480140686035,
"learning_rate": 7.555555555555556e-06,
"loss": 0.3626,
"step": 1153
},
{
"epoch": 6.411111111111111,
"grad_norm": 18.626476287841797,
"learning_rate": 7.552469135802469e-06,
"loss": 0.2131,
"step": 1154
},
{
"epoch": 6.416666666666667,
"grad_norm": 24.123188018798828,
"learning_rate": 7.549382716049383e-06,
"loss": 0.2927,
"step": 1155
},
{
"epoch": 6.4222222222222225,
"grad_norm": 21.176836013793945,
"learning_rate": 7.546296296296297e-06,
"loss": 0.5958,
"step": 1156
},
{
"epoch": 6.427777777777778,
"grad_norm": 14.827836036682129,
"learning_rate": 7.5432098765432106e-06,
"loss": 0.2821,
"step": 1157
},
{
"epoch": 6.433333333333334,
"grad_norm": 13.61574649810791,
"learning_rate": 7.540123456790124e-06,
"loss": 0.3057,
"step": 1158
},
{
"epoch": 6.438888888888889,
"grad_norm": 25.483530044555664,
"learning_rate": 7.537037037037037e-06,
"loss": 0.5334,
"step": 1159
},
{
"epoch": 6.444444444444445,
"grad_norm": 19.080617904663086,
"learning_rate": 7.533950617283952e-06,
"loss": 0.3182,
"step": 1160
},
{
"epoch": 6.45,
"grad_norm": 28.6224308013916,
"learning_rate": 7.530864197530865e-06,
"loss": 0.3381,
"step": 1161
},
{
"epoch": 6.455555555555556,
"grad_norm": 10.836545944213867,
"learning_rate": 7.527777777777778e-06,
"loss": 0.2882,
"step": 1162
},
{
"epoch": 6.461111111111111,
"grad_norm": 19.422618865966797,
"learning_rate": 7.524691358024691e-06,
"loss": 0.4107,
"step": 1163
},
{
"epoch": 6.466666666666667,
"grad_norm": 15.405062675476074,
"learning_rate": 7.521604938271606e-06,
"loss": 0.3457,
"step": 1164
},
{
"epoch": 6.472222222222222,
"grad_norm": 33.85843276977539,
"learning_rate": 7.518518518518519e-06,
"loss": 0.2324,
"step": 1165
},
{
"epoch": 6.477777777777778,
"grad_norm": 31.806001663208008,
"learning_rate": 7.515432098765433e-06,
"loss": 0.2527,
"step": 1166
},
{
"epoch": 6.483333333333333,
"grad_norm": 19.037675857543945,
"learning_rate": 7.512345679012346e-06,
"loss": 0.4212,
"step": 1167
},
{
"epoch": 6.488888888888889,
"grad_norm": 15.173768997192383,
"learning_rate": 7.50925925925926e-06,
"loss": 0.3012,
"step": 1168
},
{
"epoch": 6.4944444444444445,
"grad_norm": 10.098128318786621,
"learning_rate": 7.506172839506174e-06,
"loss": 0.2385,
"step": 1169
},
{
"epoch": 6.5,
"grad_norm": 12.426032066345215,
"learning_rate": 7.503086419753087e-06,
"loss": 0.2672,
"step": 1170
},
{
"epoch": 6.5055555555555555,
"grad_norm": 28.502685546875,
"learning_rate": 7.500000000000001e-06,
"loss": 0.5188,
"step": 1171
},
{
"epoch": 6.511111111111111,
"grad_norm": 15.446496963500977,
"learning_rate": 7.496913580246914e-06,
"loss": 0.4083,
"step": 1172
},
{
"epoch": 6.516666666666667,
"grad_norm": 12.55864429473877,
"learning_rate": 7.493827160493827e-06,
"loss": 0.1858,
"step": 1173
},
{
"epoch": 6.522222222222222,
"grad_norm": 21.36954689025879,
"learning_rate": 7.4907407407407414e-06,
"loss": 0.4709,
"step": 1174
},
{
"epoch": 6.527777777777778,
"grad_norm": 19.13591194152832,
"learning_rate": 7.4876543209876555e-06,
"loss": 0.2608,
"step": 1175
},
{
"epoch": 6.533333333333333,
"grad_norm": 13.270662307739258,
"learning_rate": 7.484567901234569e-06,
"loss": 0.2284,
"step": 1176
},
{
"epoch": 6.538888888888889,
"grad_norm": 9.584362030029297,
"learning_rate": 7.481481481481482e-06,
"loss": 0.4469,
"step": 1177
},
{
"epoch": 6.544444444444444,
"grad_norm": 9.17410659790039,
"learning_rate": 7.478395061728395e-06,
"loss": 0.3136,
"step": 1178
},
{
"epoch": 6.55,
"grad_norm": 8.4486665725708,
"learning_rate": 7.47530864197531e-06,
"loss": 0.3273,
"step": 1179
},
{
"epoch": 6.555555555555555,
"grad_norm": 17.69330406188965,
"learning_rate": 7.472222222222223e-06,
"loss": 0.4854,
"step": 1180
},
{
"epoch": 6.561111111111111,
"grad_norm": 17.643442153930664,
"learning_rate": 7.469135802469136e-06,
"loss": 0.1226,
"step": 1181
},
{
"epoch": 6.566666666666666,
"grad_norm": 25.434194564819336,
"learning_rate": 7.466049382716049e-06,
"loss": 0.5053,
"step": 1182
},
{
"epoch": 6.572222222222222,
"grad_norm": 7.71209716796875,
"learning_rate": 7.462962962962964e-06,
"loss": 0.1499,
"step": 1183
},
{
"epoch": 6.5777777777777775,
"grad_norm": 8.181035995483398,
"learning_rate": 7.4598765432098775e-06,
"loss": 0.2129,
"step": 1184
},
{
"epoch": 6.583333333333333,
"grad_norm": 14.891180992126465,
"learning_rate": 7.456790123456791e-06,
"loss": 0.2007,
"step": 1185
},
{
"epoch": 6.588888888888889,
"grad_norm": 9.857843399047852,
"learning_rate": 7.453703703703704e-06,
"loss": 0.1918,
"step": 1186
},
{
"epoch": 6.594444444444444,
"grad_norm": 13.922945022583008,
"learning_rate": 7.450617283950618e-06,
"loss": 0.193,
"step": 1187
},
{
"epoch": 6.6,
"grad_norm": 14.242829322814941,
"learning_rate": 7.447530864197532e-06,
"loss": 0.3186,
"step": 1188
},
{
"epoch": 6.605555555555555,
"grad_norm": 15.736903190612793,
"learning_rate": 7.444444444444445e-06,
"loss": 0.4109,
"step": 1189
},
{
"epoch": 6.611111111111111,
"grad_norm": 6.363912582397461,
"learning_rate": 7.441358024691358e-06,
"loss": 0.2338,
"step": 1190
},
{
"epoch": 6.616666666666667,
"grad_norm": 15.198022842407227,
"learning_rate": 7.438271604938272e-06,
"loss": 0.3913,
"step": 1191
},
{
"epoch": 6.622222222222222,
"grad_norm": 21.56873893737793,
"learning_rate": 7.4351851851851855e-06,
"loss": 0.4209,
"step": 1192
},
{
"epoch": 6.627777777777778,
"grad_norm": 8.667607307434082,
"learning_rate": 7.4320987654320995e-06,
"loss": 0.186,
"step": 1193
},
{
"epoch": 6.633333333333333,
"grad_norm": 15.833045959472656,
"learning_rate": 7.429012345679013e-06,
"loss": 0.1981,
"step": 1194
},
{
"epoch": 6.638888888888889,
"grad_norm": 16.712255477905273,
"learning_rate": 7.425925925925927e-06,
"loss": 0.3114,
"step": 1195
},
{
"epoch": 6.644444444444445,
"grad_norm": 15.241368293762207,
"learning_rate": 7.42283950617284e-06,
"loss": 0.3139,
"step": 1196
},
{
"epoch": 6.65,
"grad_norm": 10.725454330444336,
"learning_rate": 7.419753086419754e-06,
"loss": 0.2896,
"step": 1197
},
{
"epoch": 6.655555555555556,
"grad_norm": 12.204390525817871,
"learning_rate": 7.416666666666668e-06,
"loss": 0.4346,
"step": 1198
},
{
"epoch": 6.661111111111111,
"grad_norm": 8.063220977783203,
"learning_rate": 7.413580246913581e-06,
"loss": 0.1589,
"step": 1199
},
{
"epoch": 6.666666666666667,
"grad_norm": 9.417234420776367,
"learning_rate": 7.410493827160494e-06,
"loss": 0.4086,
"step": 1200
},
{
"epoch": 6.6722222222222225,
"grad_norm": 24.660341262817383,
"learning_rate": 7.4074074074074075e-06,
"loss": 0.3768,
"step": 1201
},
{
"epoch": 6.677777777777778,
"grad_norm": 18.092670440673828,
"learning_rate": 7.404320987654322e-06,
"loss": 0.3075,
"step": 1202
},
{
"epoch": 6.683333333333334,
"grad_norm": 11.250205039978027,
"learning_rate": 7.4012345679012355e-06,
"loss": 0.3385,
"step": 1203
},
{
"epoch": 6.688888888888889,
"grad_norm": 9.731067657470703,
"learning_rate": 7.398148148148149e-06,
"loss": 0.2148,
"step": 1204
},
{
"epoch": 6.694444444444445,
"grad_norm": 27.197017669677734,
"learning_rate": 7.395061728395062e-06,
"loss": 0.5218,
"step": 1205
},
{
"epoch": 6.7,
"grad_norm": 11.937191009521484,
"learning_rate": 7.391975308641975e-06,
"loss": 0.2371,
"step": 1206
},
{
"epoch": 6.705555555555556,
"grad_norm": 14.219923973083496,
"learning_rate": 7.38888888888889e-06,
"loss": 0.124,
"step": 1207
},
{
"epoch": 6.711111111111111,
"grad_norm": 10.052413940429688,
"learning_rate": 7.385802469135803e-06,
"loss": 0.1064,
"step": 1208
},
{
"epoch": 6.716666666666667,
"grad_norm": 12.113165855407715,
"learning_rate": 7.382716049382716e-06,
"loss": 0.2939,
"step": 1209
},
{
"epoch": 6.722222222222222,
"grad_norm": 7.318973541259766,
"learning_rate": 7.3796296296296295e-06,
"loss": 0.2391,
"step": 1210
},
{
"epoch": 6.727777777777778,
"grad_norm": 16.581295013427734,
"learning_rate": 7.3765432098765435e-06,
"loss": 0.4235,
"step": 1211
},
{
"epoch": 6.733333333333333,
"grad_norm": 17.404794692993164,
"learning_rate": 7.3734567901234576e-06,
"loss": 0.3292,
"step": 1212
},
{
"epoch": 6.738888888888889,
"grad_norm": 10.266692161560059,
"learning_rate": 7.370370370370371e-06,
"loss": 0.2677,
"step": 1213
},
{
"epoch": 6.7444444444444445,
"grad_norm": 10.248065948486328,
"learning_rate": 7.367283950617285e-06,
"loss": 0.2806,
"step": 1214
},
{
"epoch": 6.75,
"grad_norm": 22.972517013549805,
"learning_rate": 7.364197530864198e-06,
"loss": 0.2107,
"step": 1215
},
{
"epoch": 6.7555555555555555,
"grad_norm": 14.26351261138916,
"learning_rate": 7.361111111111112e-06,
"loss": 0.376,
"step": 1216
},
{
"epoch": 6.761111111111111,
"grad_norm": 13.105759620666504,
"learning_rate": 7.358024691358025e-06,
"loss": 0.4211,
"step": 1217
},
{
"epoch": 6.766666666666667,
"grad_norm": 10.634425163269043,
"learning_rate": 7.354938271604939e-06,
"loss": 0.1268,
"step": 1218
},
{
"epoch": 6.772222222222222,
"grad_norm": 19.953847885131836,
"learning_rate": 7.351851851851852e-06,
"loss": 0.2226,
"step": 1219
},
{
"epoch": 6.777777777777778,
"grad_norm": 20.739599227905273,
"learning_rate": 7.3487654320987655e-06,
"loss": 0.2541,
"step": 1220
},
{
"epoch": 6.783333333333333,
"grad_norm": 16.603111267089844,
"learning_rate": 7.34567901234568e-06,
"loss": 0.4866,
"step": 1221
},
{
"epoch": 6.788888888888889,
"grad_norm": 15.047995567321777,
"learning_rate": 7.342592592592594e-06,
"loss": 0.2908,
"step": 1222
},
{
"epoch": 6.794444444444444,
"grad_norm": 17.44907569885254,
"learning_rate": 7.339506172839507e-06,
"loss": 0.2355,
"step": 1223
},
{
"epoch": 6.8,
"grad_norm": 14.371499061584473,
"learning_rate": 7.33641975308642e-06,
"loss": 0.2393,
"step": 1224
},
{
"epoch": 6.805555555555555,
"grad_norm": 15.874516487121582,
"learning_rate": 7.333333333333333e-06,
"loss": 0.1926,
"step": 1225
},
{
"epoch": 6.811111111111111,
"grad_norm": 19.565767288208008,
"learning_rate": 7.330246913580248e-06,
"loss": 0.4036,
"step": 1226
},
{
"epoch": 6.816666666666666,
"grad_norm": 12.748473167419434,
"learning_rate": 7.327160493827161e-06,
"loss": 0.2762,
"step": 1227
},
{
"epoch": 6.822222222222222,
"grad_norm": 11.8579683303833,
"learning_rate": 7.324074074074074e-06,
"loss": 0.2672,
"step": 1228
},
{
"epoch": 6.8277777777777775,
"grad_norm": 23.994869232177734,
"learning_rate": 7.3209876543209876e-06,
"loss": 0.1187,
"step": 1229
},
{
"epoch": 6.833333333333333,
"grad_norm": 11.875256538391113,
"learning_rate": 7.3179012345679024e-06,
"loss": 0.2448,
"step": 1230
},
{
"epoch": 6.838888888888889,
"grad_norm": 22.50078582763672,
"learning_rate": 7.314814814814816e-06,
"loss": 0.2986,
"step": 1231
},
{
"epoch": 6.844444444444444,
"grad_norm": 22.613327026367188,
"learning_rate": 7.311728395061729e-06,
"loss": 0.575,
"step": 1232
},
{
"epoch": 6.85,
"grad_norm": 10.178118705749512,
"learning_rate": 7.308641975308642e-06,
"loss": 0.2792,
"step": 1233
},
{
"epoch": 6.855555555555555,
"grad_norm": 14.739607810974121,
"learning_rate": 7.305555555555556e-06,
"loss": 0.3145,
"step": 1234
},
{
"epoch": 6.861111111111111,
"grad_norm": 22.22174644470215,
"learning_rate": 7.30246913580247e-06,
"loss": 0.2971,
"step": 1235
},
{
"epoch": 6.866666666666667,
"grad_norm": 33.66244125366211,
"learning_rate": 7.299382716049383e-06,
"loss": 0.5963,
"step": 1236
},
{
"epoch": 6.872222222222222,
"grad_norm": 12.975081443786621,
"learning_rate": 7.296296296296297e-06,
"loss": 0.2972,
"step": 1237
},
{
"epoch": 6.877777777777778,
"grad_norm": 14.1677827835083,
"learning_rate": 7.2932098765432104e-06,
"loss": 0.296,
"step": 1238
},
{
"epoch": 6.883333333333333,
"grad_norm": 9.242941856384277,
"learning_rate": 7.290123456790124e-06,
"loss": 0.3788,
"step": 1239
},
{
"epoch": 6.888888888888889,
"grad_norm": 24.517702102661133,
"learning_rate": 7.287037037037038e-06,
"loss": 0.4397,
"step": 1240
},
{
"epoch": 6.894444444444445,
"grad_norm": 10.919740676879883,
"learning_rate": 7.283950617283952e-06,
"loss": 0.2438,
"step": 1241
},
{
"epoch": 6.9,
"grad_norm": 76.37354278564453,
"learning_rate": 7.280864197530865e-06,
"loss": 0.5498,
"step": 1242
},
{
"epoch": 6.905555555555556,
"grad_norm": 11.475580215454102,
"learning_rate": 7.277777777777778e-06,
"loss": 0.3068,
"step": 1243
},
{
"epoch": 6.911111111111111,
"grad_norm": 28.001440048217773,
"learning_rate": 7.274691358024693e-06,
"loss": 0.3547,
"step": 1244
},
{
"epoch": 6.916666666666667,
"grad_norm": 11.421968460083008,
"learning_rate": 7.271604938271606e-06,
"loss": 0.3314,
"step": 1245
},
{
"epoch": 6.9222222222222225,
"grad_norm": 8.133947372436523,
"learning_rate": 7.268518518518519e-06,
"loss": 0.2076,
"step": 1246
},
{
"epoch": 6.927777777777778,
"grad_norm": 12.401556968688965,
"learning_rate": 7.2654320987654324e-06,
"loss": 0.4173,
"step": 1247
},
{
"epoch": 6.933333333333334,
"grad_norm": 34.094947814941406,
"learning_rate": 7.262345679012346e-06,
"loss": 0.2294,
"step": 1248
},
{
"epoch": 6.938888888888889,
"grad_norm": 34.65299606323242,
"learning_rate": 7.2592592592592605e-06,
"loss": 0.4419,
"step": 1249
},
{
"epoch": 6.944444444444445,
"grad_norm": 16.576160430908203,
"learning_rate": 7.256172839506174e-06,
"loss": 0.25,
"step": 1250
},
{
"epoch": 6.95,
"grad_norm": 8.103412628173828,
"learning_rate": 7.253086419753087e-06,
"loss": 0.2475,
"step": 1251
},
{
"epoch": 6.955555555555556,
"grad_norm": 15.717777252197266,
"learning_rate": 7.25e-06,
"loss": 0.1383,
"step": 1252
},
{
"epoch": 6.961111111111111,
"grad_norm": 12.182490348815918,
"learning_rate": 7.246913580246914e-06,
"loss": 0.3187,
"step": 1253
},
{
"epoch": 6.966666666666667,
"grad_norm": 15.648293495178223,
"learning_rate": 7.243827160493828e-06,
"loss": 0.2676,
"step": 1254
},
{
"epoch": 6.972222222222222,
"grad_norm": 11.755536079406738,
"learning_rate": 7.240740740740741e-06,
"loss": 0.3665,
"step": 1255
},
{
"epoch": 6.977777777777778,
"grad_norm": 16.675216674804688,
"learning_rate": 7.2376543209876545e-06,
"loss": 0.493,
"step": 1256
},
{
"epoch": 6.983333333333333,
"grad_norm": 10.92180061340332,
"learning_rate": 7.2345679012345685e-06,
"loss": 0.3599,
"step": 1257
},
{
"epoch": 6.988888888888889,
"grad_norm": 19.201391220092773,
"learning_rate": 7.231481481481482e-06,
"loss": 0.4017,
"step": 1258
},
{
"epoch": 6.9944444444444445,
"grad_norm": 16.719573974609375,
"learning_rate": 7.228395061728396e-06,
"loss": 0.256,
"step": 1259
},
{
"epoch": 7.0,
"grad_norm": 41.79844284057617,
"learning_rate": 7.22530864197531e-06,
"loss": 0.5042,
"step": 1260
},
{
"epoch": 7.0,
"eval_accuracy": 0.8740777176586325,
"eval_f1": 0.8707868809674022,
"eval_loss": 0.5409727692604065,
"eval_runtime": 3.0155,
"eval_samples_per_second": 674.183,
"eval_steps_per_second": 5.306,
"step": 1260
},
{
"epoch": 7.0055555555555555,
"grad_norm": 13.826057434082031,
"learning_rate": 7.222222222222223e-06,
"loss": 0.2591,
"step": 1261
},
{
"epoch": 7.011111111111111,
"grad_norm": 13.780817985534668,
"learning_rate": 7.219135802469136e-06,
"loss": 0.2465,
"step": 1262
},
{
"epoch": 7.016666666666667,
"grad_norm": 9.526177406311035,
"learning_rate": 7.21604938271605e-06,
"loss": 0.2327,
"step": 1263
},
{
"epoch": 7.022222222222222,
"grad_norm": 5.398763179779053,
"learning_rate": 7.212962962962964e-06,
"loss": 0.2696,
"step": 1264
},
{
"epoch": 7.027777777777778,
"grad_norm": 10.516599655151367,
"learning_rate": 7.209876543209877e-06,
"loss": 0.1981,
"step": 1265
},
{
"epoch": 7.033333333333333,
"grad_norm": 12.324498176574707,
"learning_rate": 7.2067901234567905e-06,
"loss": 0.3686,
"step": 1266
},
{
"epoch": 7.038888888888889,
"grad_norm": 10.545625686645508,
"learning_rate": 7.203703703703704e-06,
"loss": 0.1661,
"step": 1267
},
{
"epoch": 7.044444444444444,
"grad_norm": 18.887014389038086,
"learning_rate": 7.2006172839506186e-06,
"loss": 0.1771,
"step": 1268
},
{
"epoch": 7.05,
"grad_norm": 8.500919342041016,
"learning_rate": 7.197530864197532e-06,
"loss": 0.0868,
"step": 1269
},
{
"epoch": 7.055555555555555,
"grad_norm": 16.957660675048828,
"learning_rate": 7.194444444444445e-06,
"loss": 0.3696,
"step": 1270
},
{
"epoch": 7.061111111111111,
"grad_norm": 10.220479011535645,
"learning_rate": 7.191358024691358e-06,
"loss": 0.2326,
"step": 1271
},
{
"epoch": 7.066666666666666,
"grad_norm": 7.352659702301025,
"learning_rate": 7.188271604938271e-06,
"loss": 0.1538,
"step": 1272
},
{
"epoch": 7.072222222222222,
"grad_norm": 10.836946487426758,
"learning_rate": 7.185185185185186e-06,
"loss": 0.1126,
"step": 1273
},
{
"epoch": 7.0777777777777775,
"grad_norm": 12.536423683166504,
"learning_rate": 7.182098765432099e-06,
"loss": 0.2414,
"step": 1274
},
{
"epoch": 7.083333333333333,
"grad_norm": 20.635005950927734,
"learning_rate": 7.1790123456790125e-06,
"loss": 0.4387,
"step": 1275
},
{
"epoch": 7.088888888888889,
"grad_norm": 15.875886917114258,
"learning_rate": 7.1759259259259266e-06,
"loss": 0.2804,
"step": 1276
},
{
"epoch": 7.094444444444444,
"grad_norm": 13.98859691619873,
"learning_rate": 7.172839506172841e-06,
"loss": 0.3689,
"step": 1277
},
{
"epoch": 7.1,
"grad_norm": 6.027082443237305,
"learning_rate": 7.169753086419754e-06,
"loss": 0.2336,
"step": 1278
},
{
"epoch": 7.105555555555555,
"grad_norm": 14.487667083740234,
"learning_rate": 7.166666666666667e-06,
"loss": 0.4032,
"step": 1279
},
{
"epoch": 7.111111111111111,
"grad_norm": 10.229047775268555,
"learning_rate": 7.163580246913581e-06,
"loss": 0.172,
"step": 1280
},
{
"epoch": 7.116666666666666,
"grad_norm": 15.41446590423584,
"learning_rate": 7.160493827160494e-06,
"loss": 0.1912,
"step": 1281
},
{
"epoch": 7.122222222222222,
"grad_norm": 17.55734634399414,
"learning_rate": 7.157407407407408e-06,
"loss": 0.2943,
"step": 1282
},
{
"epoch": 7.127777777777778,
"grad_norm": 13.335365295410156,
"learning_rate": 7.154320987654322e-06,
"loss": 0.3814,
"step": 1283
},
{
"epoch": 7.133333333333334,
"grad_norm": 9.273575782775879,
"learning_rate": 7.151234567901235e-06,
"loss": 0.386,
"step": 1284
},
{
"epoch": 7.138888888888889,
"grad_norm": 10.39455509185791,
"learning_rate": 7.1481481481481486e-06,
"loss": 0.2126,
"step": 1285
},
{
"epoch": 7.144444444444445,
"grad_norm": 18.37221908569336,
"learning_rate": 7.145061728395062e-06,
"loss": 0.2237,
"step": 1286
},
{
"epoch": 7.15,
"grad_norm": 27.176185607910156,
"learning_rate": 7.141975308641977e-06,
"loss": 0.4543,
"step": 1287
},
{
"epoch": 7.155555555555556,
"grad_norm": 15.367753028869629,
"learning_rate": 7.13888888888889e-06,
"loss": 0.3276,
"step": 1288
},
{
"epoch": 7.161111111111111,
"grad_norm": 13.412341117858887,
"learning_rate": 7.135802469135803e-06,
"loss": 0.1327,
"step": 1289
},
{
"epoch": 7.166666666666667,
"grad_norm": 41.95625305175781,
"learning_rate": 7.132716049382716e-06,
"loss": 0.3125,
"step": 1290
},
{
"epoch": 7.1722222222222225,
"grad_norm": 8.081766128540039,
"learning_rate": 7.129629629629629e-06,
"loss": 0.4108,
"step": 1291
},
{
"epoch": 7.177777777777778,
"grad_norm": 11.274505615234375,
"learning_rate": 7.126543209876544e-06,
"loss": 0.1424,
"step": 1292
},
{
"epoch": 7.183333333333334,
"grad_norm": 8.985296249389648,
"learning_rate": 7.123456790123457e-06,
"loss": 0.2612,
"step": 1293
},
{
"epoch": 7.188888888888889,
"grad_norm": 11.669445991516113,
"learning_rate": 7.120370370370371e-06,
"loss": 0.1983,
"step": 1294
},
{
"epoch": 7.194444444444445,
"grad_norm": 24.809383392333984,
"learning_rate": 7.117283950617284e-06,
"loss": 0.3644,
"step": 1295
},
{
"epoch": 7.2,
"grad_norm": 11.63079833984375,
"learning_rate": 7.114197530864199e-06,
"loss": 0.3403,
"step": 1296
},
{
"epoch": 7.205555555555556,
"grad_norm": 10.298707962036133,
"learning_rate": 7.111111111111112e-06,
"loss": 0.2894,
"step": 1297
},
{
"epoch": 7.211111111111111,
"grad_norm": 11.386879920959473,
"learning_rate": 7.108024691358025e-06,
"loss": 0.2804,
"step": 1298
},
{
"epoch": 7.216666666666667,
"grad_norm": 15.093196868896484,
"learning_rate": 7.104938271604939e-06,
"loss": 0.2622,
"step": 1299
},
{
"epoch": 7.222222222222222,
"grad_norm": 7.409731864929199,
"learning_rate": 7.101851851851852e-06,
"loss": 0.2211,
"step": 1300
},
{
"epoch": 7.227777777777778,
"grad_norm": 8.653724670410156,
"learning_rate": 7.098765432098766e-06,
"loss": 0.1894,
"step": 1301
},
{
"epoch": 7.233333333333333,
"grad_norm": 16.986217498779297,
"learning_rate": 7.0956790123456794e-06,
"loss": 0.198,
"step": 1302
},
{
"epoch": 7.238888888888889,
"grad_norm": 8.574886322021484,
"learning_rate": 7.0925925925925935e-06,
"loss": 0.2944,
"step": 1303
},
{
"epoch": 7.2444444444444445,
"grad_norm": 8.188627243041992,
"learning_rate": 7.089506172839507e-06,
"loss": 0.0933,
"step": 1304
},
{
"epoch": 7.25,
"grad_norm": 12.012358665466309,
"learning_rate": 7.08641975308642e-06,
"loss": 0.3235,
"step": 1305
},
{
"epoch": 7.2555555555555555,
"grad_norm": 10.05668830871582,
"learning_rate": 7.083333333333335e-06,
"loss": 0.1455,
"step": 1306
},
{
"epoch": 7.261111111111111,
"grad_norm": 11.618490219116211,
"learning_rate": 7.080246913580248e-06,
"loss": 0.2839,
"step": 1307
},
{
"epoch": 7.266666666666667,
"grad_norm": 16.38620948791504,
"learning_rate": 7.077160493827161e-06,
"loss": 0.1491,
"step": 1308
},
{
"epoch": 7.272222222222222,
"grad_norm": 13.340188980102539,
"learning_rate": 7.074074074074074e-06,
"loss": 0.2773,
"step": 1309
},
{
"epoch": 7.277777777777778,
"grad_norm": 13.89453125,
"learning_rate": 7.070987654320989e-06,
"loss": 0.2859,
"step": 1310
},
{
"epoch": 7.283333333333333,
"grad_norm": 9.107409477233887,
"learning_rate": 7.067901234567902e-06,
"loss": 0.1789,
"step": 1311
},
{
"epoch": 7.288888888888889,
"grad_norm": 10.990808486938477,
"learning_rate": 7.0648148148148155e-06,
"loss": 0.2778,
"step": 1312
},
{
"epoch": 7.294444444444444,
"grad_norm": 7.967137813568115,
"learning_rate": 7.061728395061729e-06,
"loss": 0.1194,
"step": 1313
},
{
"epoch": 7.3,
"grad_norm": 9.002396583557129,
"learning_rate": 7.058641975308642e-06,
"loss": 0.2429,
"step": 1314
},
{
"epoch": 7.305555555555555,
"grad_norm": 18.097000122070312,
"learning_rate": 7.055555555555557e-06,
"loss": 0.2923,
"step": 1315
},
{
"epoch": 7.311111111111111,
"grad_norm": 21.9827823638916,
"learning_rate": 7.05246913580247e-06,
"loss": 0.4489,
"step": 1316
},
{
"epoch": 7.316666666666666,
"grad_norm": 20.885828018188477,
"learning_rate": 7.049382716049383e-06,
"loss": 0.3413,
"step": 1317
},
{
"epoch": 7.322222222222222,
"grad_norm": 8.660916328430176,
"learning_rate": 7.046296296296296e-06,
"loss": 0.1267,
"step": 1318
},
{
"epoch": 7.3277777777777775,
"grad_norm": 10.875480651855469,
"learning_rate": 7.04320987654321e-06,
"loss": 0.3206,
"step": 1319
},
{
"epoch": 7.333333333333333,
"grad_norm": 15.814702033996582,
"learning_rate": 7.040123456790124e-06,
"loss": 0.1562,
"step": 1320
},
{
"epoch": 7.338888888888889,
"grad_norm": 11.84149169921875,
"learning_rate": 7.0370370370370375e-06,
"loss": 0.15,
"step": 1321
},
{
"epoch": 7.344444444444444,
"grad_norm": 11.520919799804688,
"learning_rate": 7.0339506172839515e-06,
"loss": 0.2435,
"step": 1322
},
{
"epoch": 7.35,
"grad_norm": 16.12481689453125,
"learning_rate": 7.030864197530865e-06,
"loss": 0.1921,
"step": 1323
},
{
"epoch": 7.355555555555555,
"grad_norm": 33.912384033203125,
"learning_rate": 7.027777777777778e-06,
"loss": 0.4175,
"step": 1324
},
{
"epoch": 7.361111111111111,
"grad_norm": 11.369695663452148,
"learning_rate": 7.024691358024692e-06,
"loss": 0.1283,
"step": 1325
},
{
"epoch": 7.366666666666666,
"grad_norm": 9.799283027648926,
"learning_rate": 7.021604938271606e-06,
"loss": 0.2728,
"step": 1326
},
{
"epoch": 7.372222222222222,
"grad_norm": 7.781754970550537,
"learning_rate": 7.018518518518519e-06,
"loss": 0.1974,
"step": 1327
},
{
"epoch": 7.377777777777778,
"grad_norm": 6.323156356811523,
"learning_rate": 7.015432098765432e-06,
"loss": 0.1699,
"step": 1328
},
{
"epoch": 7.383333333333334,
"grad_norm": 15.258740425109863,
"learning_rate": 7.012345679012347e-06,
"loss": 0.4871,
"step": 1329
},
{
"epoch": 7.388888888888889,
"grad_norm": 8.313468933105469,
"learning_rate": 7.00925925925926e-06,
"loss": 0.2758,
"step": 1330
},
{
"epoch": 7.394444444444445,
"grad_norm": 14.73559856414795,
"learning_rate": 7.0061728395061735e-06,
"loss": 0.2192,
"step": 1331
},
{
"epoch": 7.4,
"grad_norm": 29.818294525146484,
"learning_rate": 7.003086419753087e-06,
"loss": 0.2609,
"step": 1332
},
{
"epoch": 7.405555555555556,
"grad_norm": 7.794206619262695,
"learning_rate": 7e-06,
"loss": 0.1782,
"step": 1333
},
{
"epoch": 7.411111111111111,
"grad_norm": 8.881500244140625,
"learning_rate": 6.996913580246915e-06,
"loss": 0.1303,
"step": 1334
},
{
"epoch": 7.416666666666667,
"grad_norm": 15.665053367614746,
"learning_rate": 6.993827160493828e-06,
"loss": 0.2111,
"step": 1335
},
{
"epoch": 7.4222222222222225,
"grad_norm": 20.86842155456543,
"learning_rate": 6.990740740740741e-06,
"loss": 0.2297,
"step": 1336
},
{
"epoch": 7.427777777777778,
"grad_norm": 11.788874626159668,
"learning_rate": 6.987654320987654e-06,
"loss": 0.5753,
"step": 1337
},
{
"epoch": 7.433333333333334,
"grad_norm": 46.930110931396484,
"learning_rate": 6.984567901234568e-06,
"loss": 0.4521,
"step": 1338
},
{
"epoch": 7.438888888888889,
"grad_norm": 14.837639808654785,
"learning_rate": 6.981481481481482e-06,
"loss": 0.1656,
"step": 1339
},
{
"epoch": 7.444444444444445,
"grad_norm": 14.552356719970703,
"learning_rate": 6.9783950617283956e-06,
"loss": 0.2703,
"step": 1340
},
{
"epoch": 7.45,
"grad_norm": 12.023530006408691,
"learning_rate": 6.975308641975309e-06,
"loss": 0.2383,
"step": 1341
},
{
"epoch": 7.455555555555556,
"grad_norm": 14.145208358764648,
"learning_rate": 6.972222222222223e-06,
"loss": 0.2396,
"step": 1342
},
{
"epoch": 7.461111111111111,
"grad_norm": 9.530647277832031,
"learning_rate": 6.969135802469137e-06,
"loss": 0.2121,
"step": 1343
},
{
"epoch": 7.466666666666667,
"grad_norm": 23.217220306396484,
"learning_rate": 6.96604938271605e-06,
"loss": 0.2313,
"step": 1344
},
{
"epoch": 7.472222222222222,
"grad_norm": 9.800066947937012,
"learning_rate": 6.962962962962964e-06,
"loss": 0.1906,
"step": 1345
},
{
"epoch": 7.477777777777778,
"grad_norm": 19.147180557250977,
"learning_rate": 6.959876543209877e-06,
"loss": 0.3571,
"step": 1346
},
{
"epoch": 7.483333333333333,
"grad_norm": 28.833229064941406,
"learning_rate": 6.95679012345679e-06,
"loss": 0.2347,
"step": 1347
},
{
"epoch": 7.488888888888889,
"grad_norm": 14.149465560913086,
"learning_rate": 6.953703703703704e-06,
"loss": 0.147,
"step": 1348
},
{
"epoch": 7.4944444444444445,
"grad_norm": 11.4259614944458,
"learning_rate": 6.950617283950618e-06,
"loss": 0.2264,
"step": 1349
},
{
"epoch": 7.5,
"grad_norm": 16.456266403198242,
"learning_rate": 6.947530864197532e-06,
"loss": 0.3573,
"step": 1350
},
{
"epoch": 7.5055555555555555,
"grad_norm": 15.715588569641113,
"learning_rate": 6.944444444444445e-06,
"loss": 0.1853,
"step": 1351
},
{
"epoch": 7.511111111111111,
"grad_norm": 13.131957054138184,
"learning_rate": 6.941358024691358e-06,
"loss": 0.2372,
"step": 1352
},
{
"epoch": 7.516666666666667,
"grad_norm": 17.01700210571289,
"learning_rate": 6.938271604938273e-06,
"loss": 0.4442,
"step": 1353
},
{
"epoch": 7.522222222222222,
"grad_norm": 10.023733139038086,
"learning_rate": 6.935185185185186e-06,
"loss": 0.2388,
"step": 1354
},
{
"epoch": 7.527777777777778,
"grad_norm": 9.218841552734375,
"learning_rate": 6.932098765432099e-06,
"loss": 0.4191,
"step": 1355
},
{
"epoch": 7.533333333333333,
"grad_norm": 12.074708938598633,
"learning_rate": 6.929012345679012e-06,
"loss": 0.3102,
"step": 1356
},
{
"epoch": 7.538888888888889,
"grad_norm": 13.559629440307617,
"learning_rate": 6.9259259259259256e-06,
"loss": 0.3507,
"step": 1357
},
{
"epoch": 7.544444444444444,
"grad_norm": 9.859298706054688,
"learning_rate": 6.9228395061728404e-06,
"loss": 0.1731,
"step": 1358
},
{
"epoch": 7.55,
"grad_norm": 6.720864772796631,
"learning_rate": 6.919753086419754e-06,
"loss": 0.0987,
"step": 1359
},
{
"epoch": 7.555555555555555,
"grad_norm": 20.902376174926758,
"learning_rate": 6.916666666666667e-06,
"loss": 0.2286,
"step": 1360
},
{
"epoch": 7.561111111111111,
"grad_norm": 13.183963775634766,
"learning_rate": 6.913580246913581e-06,
"loss": 0.2598,
"step": 1361
},
{
"epoch": 7.566666666666666,
"grad_norm": 8.441410064697266,
"learning_rate": 6.910493827160495e-06,
"loss": 0.1604,
"step": 1362
},
{
"epoch": 7.572222222222222,
"grad_norm": 22.50967788696289,
"learning_rate": 6.907407407407408e-06,
"loss": 0.3556,
"step": 1363
},
{
"epoch": 7.5777777777777775,
"grad_norm": 17.22089958190918,
"learning_rate": 6.904320987654321e-06,
"loss": 0.3868,
"step": 1364
},
{
"epoch": 7.583333333333333,
"grad_norm": 27.446292877197266,
"learning_rate": 6.901234567901235e-06,
"loss": 0.3296,
"step": 1365
},
{
"epoch": 7.588888888888889,
"grad_norm": 26.09615135192871,
"learning_rate": 6.898148148148148e-06,
"loss": 0.3017,
"step": 1366
},
{
"epoch": 7.594444444444444,
"grad_norm": 16.380996704101562,
"learning_rate": 6.8950617283950625e-06,
"loss": 0.2584,
"step": 1367
},
{
"epoch": 7.6,
"grad_norm": 20.175870895385742,
"learning_rate": 6.8919753086419765e-06,
"loss": 0.3177,
"step": 1368
},
{
"epoch": 7.605555555555555,
"grad_norm": 21.313526153564453,
"learning_rate": 6.88888888888889e-06,
"loss": 0.2401,
"step": 1369
},
{
"epoch": 7.611111111111111,
"grad_norm": 107.38150024414062,
"learning_rate": 6.885802469135803e-06,
"loss": 0.2342,
"step": 1370
},
{
"epoch": 7.616666666666667,
"grad_norm": 11.370809555053711,
"learning_rate": 6.882716049382716e-06,
"loss": 0.2846,
"step": 1371
},
{
"epoch": 7.622222222222222,
"grad_norm": 12.642956733703613,
"learning_rate": 6.879629629629631e-06,
"loss": 0.3076,
"step": 1372
},
{
"epoch": 7.627777777777778,
"grad_norm": 11.909661293029785,
"learning_rate": 6.876543209876544e-06,
"loss": 0.0953,
"step": 1373
},
{
"epoch": 7.633333333333333,
"grad_norm": 11.996376991271973,
"learning_rate": 6.873456790123457e-06,
"loss": 0.1113,
"step": 1374
},
{
"epoch": 7.638888888888889,
"grad_norm": 19.63287353515625,
"learning_rate": 6.8703703703703704e-06,
"loss": 0.194,
"step": 1375
},
{
"epoch": 7.644444444444445,
"grad_norm": 13.453766822814941,
"learning_rate": 6.867283950617285e-06,
"loss": 0.3797,
"step": 1376
},
{
"epoch": 7.65,
"grad_norm": 9.649170875549316,
"learning_rate": 6.8641975308641985e-06,
"loss": 0.107,
"step": 1377
},
{
"epoch": 7.655555555555556,
"grad_norm": 14.499027252197266,
"learning_rate": 6.861111111111112e-06,
"loss": 0.2663,
"step": 1378
},
{
"epoch": 7.661111111111111,
"grad_norm": 15.947366714477539,
"learning_rate": 6.858024691358025e-06,
"loss": 0.1491,
"step": 1379
},
{
"epoch": 7.666666666666667,
"grad_norm": 12.656583786010742,
"learning_rate": 6.854938271604938e-06,
"loss": 0.28,
"step": 1380
},
{
"epoch": 7.6722222222222225,
"grad_norm": 17.12876319885254,
"learning_rate": 6.851851851851853e-06,
"loss": 0.3796,
"step": 1381
},
{
"epoch": 7.677777777777778,
"grad_norm": 8.734187126159668,
"learning_rate": 6.848765432098766e-06,
"loss": 0.275,
"step": 1382
},
{
"epoch": 7.683333333333334,
"grad_norm": 13.667276382446289,
"learning_rate": 6.845679012345679e-06,
"loss": 0.4552,
"step": 1383
},
{
"epoch": 7.688888888888889,
"grad_norm": 19.07502555847168,
"learning_rate": 6.842592592592593e-06,
"loss": 0.338,
"step": 1384
},
{
"epoch": 7.694444444444445,
"grad_norm": 53.8626823425293,
"learning_rate": 6.8395061728395065e-06,
"loss": 0.2504,
"step": 1385
},
{
"epoch": 7.7,
"grad_norm": 21.283132553100586,
"learning_rate": 6.8364197530864205e-06,
"loss": 0.4616,
"step": 1386
},
{
"epoch": 7.705555555555556,
"grad_norm": 8.399044036865234,
"learning_rate": 6.833333333333334e-06,
"loss": 0.2226,
"step": 1387
},
{
"epoch": 7.711111111111111,
"grad_norm": 18.01186180114746,
"learning_rate": 6.830246913580248e-06,
"loss": 0.3399,
"step": 1388
},
{
"epoch": 7.716666666666667,
"grad_norm": 14.495725631713867,
"learning_rate": 6.827160493827161e-06,
"loss": 0.3699,
"step": 1389
},
{
"epoch": 7.722222222222222,
"grad_norm": 15.599531173706055,
"learning_rate": 6.824074074074075e-06,
"loss": 0.4389,
"step": 1390
},
{
"epoch": 7.727777777777778,
"grad_norm": 19.09662628173828,
"learning_rate": 6.820987654320988e-06,
"loss": 0.2176,
"step": 1391
},
{
"epoch": 7.733333333333333,
"grad_norm": 8.437607765197754,
"learning_rate": 6.817901234567902e-06,
"loss": 0.2009,
"step": 1392
},
{
"epoch": 7.738888888888889,
"grad_norm": 42.0845832824707,
"learning_rate": 6.814814814814815e-06,
"loss": 0.1769,
"step": 1393
},
{
"epoch": 7.7444444444444445,
"grad_norm": 6.10894775390625,
"learning_rate": 6.8117283950617285e-06,
"loss": 0.1142,
"step": 1394
},
{
"epoch": 7.75,
"grad_norm": 10.213293075561523,
"learning_rate": 6.808641975308643e-06,
"loss": 0.1025,
"step": 1395
},
{
"epoch": 7.7555555555555555,
"grad_norm": 19.267887115478516,
"learning_rate": 6.8055555555555566e-06,
"loss": 0.2447,
"step": 1396
},
{
"epoch": 7.761111111111111,
"grad_norm": 11.201254844665527,
"learning_rate": 6.80246913580247e-06,
"loss": 0.2405,
"step": 1397
},
{
"epoch": 7.766666666666667,
"grad_norm": 16.378137588500977,
"learning_rate": 6.799382716049383e-06,
"loss": 0.3355,
"step": 1398
},
{
"epoch": 7.772222222222222,
"grad_norm": 15.386472702026367,
"learning_rate": 6.796296296296296e-06,
"loss": 0.1226,
"step": 1399
},
{
"epoch": 7.777777777777778,
"grad_norm": 13.521950721740723,
"learning_rate": 6.793209876543211e-06,
"loss": 0.3562,
"step": 1400
},
{
"epoch": 7.783333333333333,
"grad_norm": 19.2817440032959,
"learning_rate": 6.790123456790124e-06,
"loss": 0.3211,
"step": 1401
},
{
"epoch": 7.788888888888889,
"grad_norm": 20.35334587097168,
"learning_rate": 6.787037037037037e-06,
"loss": 0.3202,
"step": 1402
},
{
"epoch": 7.794444444444444,
"grad_norm": 5.612096786499023,
"learning_rate": 6.7839506172839505e-06,
"loss": 0.1127,
"step": 1403
},
{
"epoch": 7.8,
"grad_norm": 10.975028991699219,
"learning_rate": 6.7808641975308645e-06,
"loss": 0.2113,
"step": 1404
},
{
"epoch": 7.805555555555555,
"grad_norm": 21.79230308532715,
"learning_rate": 6.777777777777779e-06,
"loss": 0.2604,
"step": 1405
},
{
"epoch": 7.811111111111111,
"grad_norm": 9.014321327209473,
"learning_rate": 6.774691358024692e-06,
"loss": 0.1031,
"step": 1406
},
{
"epoch": 7.816666666666666,
"grad_norm": 21.076736450195312,
"learning_rate": 6.771604938271606e-06,
"loss": 0.4113,
"step": 1407
},
{
"epoch": 7.822222222222222,
"grad_norm": 12.828376770019531,
"learning_rate": 6.768518518518519e-06,
"loss": 0.2429,
"step": 1408
},
{
"epoch": 7.8277777777777775,
"grad_norm": 9.7906494140625,
"learning_rate": 6.765432098765433e-06,
"loss": 0.3828,
"step": 1409
},
{
"epoch": 7.833333333333333,
"grad_norm": 17.81595230102539,
"learning_rate": 6.762345679012346e-06,
"loss": 0.1716,
"step": 1410
},
{
"epoch": 7.838888888888889,
"grad_norm": 22.416086196899414,
"learning_rate": 6.75925925925926e-06,
"loss": 0.4574,
"step": 1411
},
{
"epoch": 7.844444444444444,
"grad_norm": 15.764571189880371,
"learning_rate": 6.756172839506173e-06,
"loss": 0.1928,
"step": 1412
},
{
"epoch": 7.85,
"grad_norm": 8.870821952819824,
"learning_rate": 6.7530864197530866e-06,
"loss": 0.1636,
"step": 1413
},
{
"epoch": 7.855555555555555,
"grad_norm": 12.058917999267578,
"learning_rate": 6.750000000000001e-06,
"loss": 0.2219,
"step": 1414
},
{
"epoch": 7.861111111111111,
"grad_norm": 16.9622745513916,
"learning_rate": 6.746913580246915e-06,
"loss": 0.4879,
"step": 1415
},
{
"epoch": 7.866666666666667,
"grad_norm": 17.025127410888672,
"learning_rate": 6.743827160493828e-06,
"loss": 0.2579,
"step": 1416
},
{
"epoch": 7.872222222222222,
"grad_norm": 12.809483528137207,
"learning_rate": 6.740740740740741e-06,
"loss": 0.1989,
"step": 1417
},
{
"epoch": 7.877777777777778,
"grad_norm": 11.853103637695312,
"learning_rate": 6.737654320987654e-06,
"loss": 0.311,
"step": 1418
},
{
"epoch": 7.883333333333333,
"grad_norm": 12.592460632324219,
"learning_rate": 6.734567901234569e-06,
"loss": 0.1427,
"step": 1419
},
{
"epoch": 7.888888888888889,
"grad_norm": 14.14799690246582,
"learning_rate": 6.731481481481482e-06,
"loss": 0.1439,
"step": 1420
},
{
"epoch": 7.894444444444445,
"grad_norm": 10.478841781616211,
"learning_rate": 6.728395061728395e-06,
"loss": 0.3492,
"step": 1421
},
{
"epoch": 7.9,
"grad_norm": 16.15822982788086,
"learning_rate": 6.725308641975309e-06,
"loss": 0.4083,
"step": 1422
},
{
"epoch": 7.905555555555556,
"grad_norm": 14.974079132080078,
"learning_rate": 6.7222222222222235e-06,
"loss": 0.2988,
"step": 1423
},
{
"epoch": 7.911111111111111,
"grad_norm": 14.63045883178711,
"learning_rate": 6.719135802469137e-06,
"loss": 0.2642,
"step": 1424
},
{
"epoch": 7.916666666666667,
"grad_norm": 8.428140640258789,
"learning_rate": 6.71604938271605e-06,
"loss": 0.1297,
"step": 1425
},
{
"epoch": 7.9222222222222225,
"grad_norm": 15.21141242980957,
"learning_rate": 6.712962962962963e-06,
"loss": 0.2529,
"step": 1426
},
{
"epoch": 7.927777777777778,
"grad_norm": 18.588472366333008,
"learning_rate": 6.709876543209877e-06,
"loss": 0.2259,
"step": 1427
},
{
"epoch": 7.933333333333334,
"grad_norm": 12.635353088378906,
"learning_rate": 6.706790123456791e-06,
"loss": 0.128,
"step": 1428
},
{
"epoch": 7.938888888888889,
"grad_norm": 12.428218841552734,
"learning_rate": 6.703703703703704e-06,
"loss": 0.2188,
"step": 1429
},
{
"epoch": 7.944444444444445,
"grad_norm": 12.290231704711914,
"learning_rate": 6.700617283950617e-06,
"loss": 0.1688,
"step": 1430
},
{
"epoch": 7.95,
"grad_norm": 11.652839660644531,
"learning_rate": 6.6975308641975314e-06,
"loss": 0.3783,
"step": 1431
},
{
"epoch": 7.955555555555556,
"grad_norm": 8.461857795715332,
"learning_rate": 6.694444444444445e-06,
"loss": 0.2072,
"step": 1432
},
{
"epoch": 7.961111111111111,
"grad_norm": 6.847550392150879,
"learning_rate": 6.691358024691359e-06,
"loss": 0.0977,
"step": 1433
},
{
"epoch": 7.966666666666667,
"grad_norm": 29.906368255615234,
"learning_rate": 6.688271604938273e-06,
"loss": 0.3733,
"step": 1434
},
{
"epoch": 7.972222222222222,
"grad_norm": 9.834501266479492,
"learning_rate": 6.685185185185186e-06,
"loss": 0.351,
"step": 1435
},
{
"epoch": 7.977777777777778,
"grad_norm": 23.878517150878906,
"learning_rate": 6.682098765432099e-06,
"loss": 0.3496,
"step": 1436
},
{
"epoch": 7.983333333333333,
"grad_norm": 24.51555824279785,
"learning_rate": 6.679012345679012e-06,
"loss": 0.1848,
"step": 1437
},
{
"epoch": 7.988888888888889,
"grad_norm": 21.32552146911621,
"learning_rate": 6.675925925925927e-06,
"loss": 0.3999,
"step": 1438
},
{
"epoch": 7.9944444444444445,
"grad_norm": 21.4161376953125,
"learning_rate": 6.67283950617284e-06,
"loss": 0.2019,
"step": 1439
},
{
"epoch": 8.0,
"grad_norm": 5.846489906311035,
"learning_rate": 6.6697530864197535e-06,
"loss": 0.0764,
"step": 1440
},
{
"epoch": 8.0,
"eval_accuracy": 0.8760452533202164,
"eval_f1": 0.8750991952959509,
"eval_loss": 0.5522083044052124,
"eval_runtime": 2.8469,
"eval_samples_per_second": 714.101,
"eval_steps_per_second": 5.62,
"step": 1440
},
{
"epoch": 8.0,
"step": 1440,
"total_flos": 2.1464721047568384e+16,
"train_loss": 1.2266346912210186,
"train_runtime": 546.3155,
"train_samples_per_second": 421.515,
"train_steps_per_second": 6.59
}
],
"logging_steps": 1,
"max_steps": 3600,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 3
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.1464721047568384e+16,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}