model_ab12804a / checkpoint-216 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
bd68ce4 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 216,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013888888888888888,
"grad_norm": 95.33702850341797,
"learning_rate": 5.0000000000000004e-08,
"loss": 5.3695,
"step": 1
},
{
"epoch": 0.027777777777777776,
"grad_norm": 96.05199432373047,
"learning_rate": 1.0000000000000001e-07,
"loss": 5.4178,
"step": 2
},
{
"epoch": 0.041666666666666664,
"grad_norm": 92.71851348876953,
"learning_rate": 1.5000000000000002e-07,
"loss": 5.4472,
"step": 3
},
{
"epoch": 0.05555555555555555,
"grad_norm": 95.78789520263672,
"learning_rate": 2.0000000000000002e-07,
"loss": 5.4114,
"step": 4
},
{
"epoch": 0.06944444444444445,
"grad_norm": 95.62769317626953,
"learning_rate": 2.5000000000000004e-07,
"loss": 5.3612,
"step": 5
},
{
"epoch": 0.08333333333333333,
"grad_norm": 94.85267639160156,
"learning_rate": 3.0000000000000004e-07,
"loss": 5.4065,
"step": 6
},
{
"epoch": 0.09722222222222222,
"grad_norm": 93.81153869628906,
"learning_rate": 3.5000000000000004e-07,
"loss": 5.364,
"step": 7
},
{
"epoch": 0.1111111111111111,
"grad_norm": 95.33504486083984,
"learning_rate": 4.0000000000000003e-07,
"loss": 5.4484,
"step": 8
},
{
"epoch": 0.125,
"grad_norm": 94.11618041992188,
"learning_rate": 4.5000000000000003e-07,
"loss": 5.3494,
"step": 9
},
{
"epoch": 0.1388888888888889,
"grad_norm": 93.71621704101562,
"learning_rate": 5.000000000000001e-07,
"loss": 5.2325,
"step": 10
},
{
"epoch": 0.1527777777777778,
"grad_norm": 92.6498031616211,
"learning_rate": 5.5e-07,
"loss": 5.1224,
"step": 11
},
{
"epoch": 0.16666666666666666,
"grad_norm": 89.05821228027344,
"learning_rate": 6.000000000000001e-07,
"loss": 5.0484,
"step": 12
},
{
"epoch": 0.18055555555555555,
"grad_norm": 87.52056884765625,
"learning_rate": 6.5e-07,
"loss": 4.8831,
"step": 13
},
{
"epoch": 0.19444444444444445,
"grad_norm": 87.93170928955078,
"learning_rate": 7.000000000000001e-07,
"loss": 4.7723,
"step": 14
},
{
"epoch": 0.20833333333333334,
"grad_norm": 84.07933044433594,
"learning_rate": 7.5e-07,
"loss": 4.5843,
"step": 15
},
{
"epoch": 0.2222222222222222,
"grad_norm": 82.16165161132812,
"learning_rate": 8.000000000000001e-07,
"loss": 4.4273,
"step": 16
},
{
"epoch": 0.2361111111111111,
"grad_norm": 78.94780731201172,
"learning_rate": 8.500000000000001e-07,
"loss": 4.155,
"step": 17
},
{
"epoch": 0.25,
"grad_norm": 75.85335540771484,
"learning_rate": 9.000000000000001e-07,
"loss": 3.9005,
"step": 18
},
{
"epoch": 0.2638888888888889,
"grad_norm": 71.74459075927734,
"learning_rate": 9.500000000000001e-07,
"loss": 3.5885,
"step": 19
},
{
"epoch": 0.2777777777777778,
"grad_norm": 67.66385650634766,
"learning_rate": 1.0000000000000002e-06,
"loss": 3.308,
"step": 20
},
{
"epoch": 0.2916666666666667,
"grad_norm": 64.22036743164062,
"learning_rate": 1.0500000000000001e-06,
"loss": 3.057,
"step": 21
},
{
"epoch": 0.3055555555555556,
"grad_norm": 60.24971008300781,
"learning_rate": 1.1e-06,
"loss": 2.7939,
"step": 22
},
{
"epoch": 0.3194444444444444,
"grad_norm": 57.68950271606445,
"learning_rate": 1.1500000000000002e-06,
"loss": 2.5539,
"step": 23
},
{
"epoch": 0.3333333333333333,
"grad_norm": 56.10525894165039,
"learning_rate": 1.2000000000000002e-06,
"loss": 2.2688,
"step": 24
},
{
"epoch": 0.3472222222222222,
"grad_norm": 54.84128189086914,
"learning_rate": 1.25e-06,
"loss": 2.009,
"step": 25
},
{
"epoch": 0.3611111111111111,
"grad_norm": 53.96566390991211,
"learning_rate": 1.3e-06,
"loss": 1.6682,
"step": 26
},
{
"epoch": 0.375,
"grad_norm": 53.859439849853516,
"learning_rate": 1.3500000000000002e-06,
"loss": 1.3807,
"step": 27
},
{
"epoch": 0.3888888888888889,
"grad_norm": 53.22216796875,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.1229,
"step": 28
},
{
"epoch": 0.4027777777777778,
"grad_norm": 50.3905143737793,
"learning_rate": 1.45e-06,
"loss": 0.8454,
"step": 29
},
{
"epoch": 0.4166666666666667,
"grad_norm": 40.14346694946289,
"learning_rate": 1.5e-06,
"loss": 0.5817,
"step": 30
},
{
"epoch": 0.4305555555555556,
"grad_norm": 34.043235778808594,
"learning_rate": 1.5500000000000002e-06,
"loss": 0.4234,
"step": 31
},
{
"epoch": 0.4444444444444444,
"grad_norm": 28.703292846679688,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.3074,
"step": 32
},
{
"epoch": 0.4583333333333333,
"grad_norm": 22.456626892089844,
"learning_rate": 1.6500000000000003e-06,
"loss": 0.2146,
"step": 33
},
{
"epoch": 0.4722222222222222,
"grad_norm": 15.350156784057617,
"learning_rate": 1.7000000000000002e-06,
"loss": 0.1103,
"step": 34
},
{
"epoch": 0.4861111111111111,
"grad_norm": 6.5175580978393555,
"learning_rate": 1.75e-06,
"loss": 0.0574,
"step": 35
},
{
"epoch": 0.5,
"grad_norm": 6.813859939575195,
"learning_rate": 1.8000000000000001e-06,
"loss": 0.0497,
"step": 36
},
{
"epoch": 0.5138888888888888,
"grad_norm": 3.5350818634033203,
"learning_rate": 1.85e-06,
"loss": 0.0199,
"step": 37
},
{
"epoch": 0.5277777777777778,
"grad_norm": 4.9657135009765625,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.0245,
"step": 38
},
{
"epoch": 0.5416666666666666,
"grad_norm": 1.2266570329666138,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.0087,
"step": 39
},
{
"epoch": 0.5555555555555556,
"grad_norm": 4.982794761657715,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.048,
"step": 40
},
{
"epoch": 0.5694444444444444,
"grad_norm": 7.6967387199401855,
"learning_rate": 2.05e-06,
"loss": 0.0449,
"step": 41
},
{
"epoch": 0.5833333333333334,
"grad_norm": 2.9466323852539062,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.0098,
"step": 42
},
{
"epoch": 0.5972222222222222,
"grad_norm": 2.191035747528076,
"learning_rate": 2.15e-06,
"loss": 0.0087,
"step": 43
},
{
"epoch": 0.6111111111111112,
"grad_norm": 7.3228840827941895,
"learning_rate": 2.2e-06,
"loss": 0.0339,
"step": 44
},
{
"epoch": 0.625,
"grad_norm": 4.737412929534912,
"learning_rate": 2.25e-06,
"loss": 0.0149,
"step": 45
},
{
"epoch": 0.6388888888888888,
"grad_norm": 1.7612887620925903,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.0071,
"step": 46
},
{
"epoch": 0.6527777777777778,
"grad_norm": 3.344369649887085,
"learning_rate": 2.35e-06,
"loss": 0.0196,
"step": 47
},
{
"epoch": 0.6666666666666666,
"grad_norm": 2.2957704067230225,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.0216,
"step": 48
},
{
"epoch": 0.6805555555555556,
"grad_norm": 1.83970308303833,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.0221,
"step": 49
},
{
"epoch": 0.6944444444444444,
"grad_norm": 1.547287106513977,
"learning_rate": 2.5e-06,
"loss": 0.0061,
"step": 50
},
{
"epoch": 0.7083333333333334,
"grad_norm": 1.6580262184143066,
"learning_rate": 2.55e-06,
"loss": 0.0127,
"step": 51
},
{
"epoch": 0.7222222222222222,
"grad_norm": 1.8863849639892578,
"learning_rate": 2.6e-06,
"loss": 0.0124,
"step": 52
},
{
"epoch": 0.7361111111111112,
"grad_norm": 1.2086963653564453,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0085,
"step": 53
},
{
"epoch": 0.75,
"grad_norm": 2.4265427589416504,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0255,
"step": 54
},
{
"epoch": 0.7638888888888888,
"grad_norm": 2.0333855152130127,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0145,
"step": 55
},
{
"epoch": 0.7777777777777778,
"grad_norm": 2.9129791259765625,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0228,
"step": 56
},
{
"epoch": 0.7916666666666666,
"grad_norm": 0.8359552621841431,
"learning_rate": 2.85e-06,
"loss": 0.0109,
"step": 57
},
{
"epoch": 0.8055555555555556,
"grad_norm": 1.677287220954895,
"learning_rate": 2.9e-06,
"loss": 0.0246,
"step": 58
},
{
"epoch": 0.8194444444444444,
"grad_norm": 1.0761189460754395,
"learning_rate": 2.95e-06,
"loss": 0.0058,
"step": 59
},
{
"epoch": 0.8333333333333334,
"grad_norm": 1.1098495721817017,
"learning_rate": 3e-06,
"loss": 0.0167,
"step": 60
},
{
"epoch": 0.8472222222222222,
"grad_norm": 1.0377463102340698,
"learning_rate": 3.05e-06,
"loss": 0.007,
"step": 61
},
{
"epoch": 0.8611111111111112,
"grad_norm": 0.6554276347160339,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0039,
"step": 62
},
{
"epoch": 0.875,
"grad_norm": 1.279077410697937,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0199,
"step": 63
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.7709833979606628,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0043,
"step": 64
},
{
"epoch": 0.9027777777777778,
"grad_norm": 1.3619827032089233,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0067,
"step": 65
},
{
"epoch": 0.9166666666666666,
"grad_norm": 1.3849765062332153,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0091,
"step": 66
},
{
"epoch": 0.9305555555555556,
"grad_norm": 1.1380351781845093,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0143,
"step": 67
},
{
"epoch": 0.9444444444444444,
"grad_norm": 1.9759573936462402,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0231,
"step": 68
},
{
"epoch": 0.9583333333333334,
"grad_norm": 0.5920725464820862,
"learning_rate": 3.45e-06,
"loss": 0.0063,
"step": 69
},
{
"epoch": 0.9722222222222222,
"grad_norm": 1.2489631175994873,
"learning_rate": 3.5e-06,
"loss": 0.0149,
"step": 70
},
{
"epoch": 0.9861111111111112,
"grad_norm": 1.5553513765335083,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0085,
"step": 71
},
{
"epoch": 1.0,
"grad_norm": 1.0278698205947876,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0061,
"step": 72
},
{
"epoch": 1.0138888888888888,
"grad_norm": 1.9279776811599731,
"learning_rate": 3.65e-06,
"loss": 0.0118,
"step": 73
},
{
"epoch": 1.0277777777777777,
"grad_norm": 2.592510223388672,
"learning_rate": 3.7e-06,
"loss": 0.0309,
"step": 74
},
{
"epoch": 1.0416666666666667,
"grad_norm": 1.6530096530914307,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0099,
"step": 75
},
{
"epoch": 1.0555555555555556,
"grad_norm": 0.4624968469142914,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0053,
"step": 76
},
{
"epoch": 1.0694444444444444,
"grad_norm": 0.629607617855072,
"learning_rate": 3.85e-06,
"loss": 0.0087,
"step": 77
},
{
"epoch": 1.0833333333333333,
"grad_norm": 0.14678587019443512,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0007,
"step": 78
},
{
"epoch": 1.0972222222222223,
"grad_norm": 1.0052955150604248,
"learning_rate": 3.95e-06,
"loss": 0.0089,
"step": 79
},
{
"epoch": 1.1111111111111112,
"grad_norm": 0.9059052467346191,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0049,
"step": 80
},
{
"epoch": 1.125,
"grad_norm": 0.871515691280365,
"learning_rate": 4.05e-06,
"loss": 0.0092,
"step": 81
},
{
"epoch": 1.1388888888888888,
"grad_norm": 0.07520482689142227,
"learning_rate": 4.1e-06,
"loss": 0.0004,
"step": 82
},
{
"epoch": 1.1527777777777777,
"grad_norm": 0.8039830923080444,
"learning_rate": 4.15e-06,
"loss": 0.0031,
"step": 83
},
{
"epoch": 1.1666666666666667,
"grad_norm": 0.05209676921367645,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0003,
"step": 84
},
{
"epoch": 1.1805555555555556,
"grad_norm": 0.04410432651638985,
"learning_rate": 4.25e-06,
"loss": 0.0002,
"step": 85
},
{
"epoch": 1.1944444444444444,
"grad_norm": 0.06021099537611008,
"learning_rate": 4.3e-06,
"loss": 0.0002,
"step": 86
},
{
"epoch": 1.2083333333333333,
"grad_norm": 0.283663272857666,
"learning_rate": 4.350000000000001e-06,
"loss": 0.001,
"step": 87
},
{
"epoch": 1.2222222222222223,
"grad_norm": 0.6798669695854187,
"learning_rate": 4.4e-06,
"loss": 0.0033,
"step": 88
},
{
"epoch": 1.2361111111111112,
"grad_norm": 0.06857122480869293,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0002,
"step": 89
},
{
"epoch": 1.25,
"grad_norm": 1.9897412061691284,
"learning_rate": 4.5e-06,
"loss": 0.0126,
"step": 90
},
{
"epoch": 1.2638888888888888,
"grad_norm": 1.2174546718597412,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.0023,
"step": 91
},
{
"epoch": 1.2777777777777777,
"grad_norm": 2.2762115001678467,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0095,
"step": 92
},
{
"epoch": 1.2916666666666667,
"grad_norm": 3.728581428527832,
"learning_rate": 4.65e-06,
"loss": 0.0046,
"step": 93
},
{
"epoch": 1.3055555555555556,
"grad_norm": 2.942180871963501,
"learning_rate": 4.7e-06,
"loss": 0.0261,
"step": 94
},
{
"epoch": 1.3194444444444444,
"grad_norm": 0.3911007344722748,
"learning_rate": 4.75e-06,
"loss": 0.0005,
"step": 95
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.03832005336880684,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0001,
"step": 96
},
{
"epoch": 1.3472222222222223,
"grad_norm": 0.7516991496086121,
"learning_rate": 4.85e-06,
"loss": 0.0017,
"step": 97
},
{
"epoch": 1.3611111111111112,
"grad_norm": 0.4136435091495514,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0014,
"step": 98
},
{
"epoch": 1.375,
"grad_norm": 0.044784627854824066,
"learning_rate": 4.95e-06,
"loss": 0.0001,
"step": 99
},
{
"epoch": 1.3888888888888888,
"grad_norm": 0.7667476534843445,
"learning_rate": 5e-06,
"loss": 0.0022,
"step": 100
},
{
"epoch": 1.4027777777777777,
"grad_norm": 0.9187825322151184,
"learning_rate": 4.999888074163108e-06,
"loss": 0.0035,
"step": 101
},
{
"epoch": 1.4166666666666667,
"grad_norm": 1.2859818935394287,
"learning_rate": 4.999552306674345e-06,
"loss": 0.0046,
"step": 102
},
{
"epoch": 1.4305555555555556,
"grad_norm": 0.5899283289909363,
"learning_rate": 4.998992727598557e-06,
"loss": 0.0027,
"step": 103
},
{
"epoch": 1.4444444444444444,
"grad_norm": 0.027552006766200066,
"learning_rate": 4.998209387040829e-06,
"loss": 0.0001,
"step": 104
},
{
"epoch": 1.4583333333333333,
"grad_norm": 0.14271241426467896,
"learning_rate": 4.9972023551419995e-06,
"loss": 0.0002,
"step": 105
},
{
"epoch": 1.4722222222222223,
"grad_norm": 0.36476054787635803,
"learning_rate": 4.995971722072379e-06,
"loss": 0.001,
"step": 106
},
{
"epoch": 1.4861111111111112,
"grad_norm": 1.7742875814437866,
"learning_rate": 4.9945175980236745e-06,
"loss": 0.0025,
"step": 107
},
{
"epoch": 1.5,
"grad_norm": 0.5356531739234924,
"learning_rate": 4.992840113199131e-06,
"loss": 0.0011,
"step": 108
},
{
"epoch": 1.5138888888888888,
"grad_norm": 0.9400438070297241,
"learning_rate": 4.990939417801859e-06,
"loss": 0.0021,
"step": 109
},
{
"epoch": 1.5277777777777777,
"grad_norm": 0.028793074190616608,
"learning_rate": 4.988815682021398e-06,
"loss": 0.0001,
"step": 110
},
{
"epoch": 1.5416666666666665,
"grad_norm": 0.016167419031262398,
"learning_rate": 4.986469096018472e-06,
"loss": 0.0001,
"step": 111
},
{
"epoch": 1.5555555555555556,
"grad_norm": 0.04863646626472473,
"learning_rate": 4.983899869907963e-06,
"loss": 0.0001,
"step": 112
},
{
"epoch": 1.5694444444444444,
"grad_norm": 0.11991345882415771,
"learning_rate": 4.981108233740096e-06,
"loss": 0.0003,
"step": 113
},
{
"epoch": 1.5833333333333335,
"grad_norm": 1.1984789371490479,
"learning_rate": 4.978094437479843e-06,
"loss": 0.0205,
"step": 114
},
{
"epoch": 1.5972222222222223,
"grad_norm": 0.2907632887363434,
"learning_rate": 4.97485875098454e-06,
"loss": 0.0005,
"step": 115
},
{
"epoch": 1.6111111111111112,
"grad_norm": 2.186234474182129,
"learning_rate": 4.971401463979722e-06,
"loss": 0.0068,
"step": 116
},
{
"epoch": 1.625,
"grad_norm": 0.17205508053302765,
"learning_rate": 4.967722886033181e-06,
"loss": 0.0004,
"step": 117
},
{
"epoch": 1.6388888888888888,
"grad_norm": 1.9445418119430542,
"learning_rate": 4.963823346527249e-06,
"loss": 0.0052,
"step": 118
},
{
"epoch": 1.6527777777777777,
"grad_norm": 0.8023346662521362,
"learning_rate": 4.959703194629304e-06,
"loss": 0.0087,
"step": 119
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.4967271685600281,
"learning_rate": 4.955362799260507e-06,
"loss": 0.0011,
"step": 120
},
{
"epoch": 1.6805555555555556,
"grad_norm": 0.18211083114147186,
"learning_rate": 4.950802549062764e-06,
"loss": 0.0007,
"step": 121
},
{
"epoch": 1.6944444444444444,
"grad_norm": 0.2594281733036041,
"learning_rate": 4.946022852363932e-06,
"loss": 0.0011,
"step": 122
},
{
"epoch": 1.7083333333333335,
"grad_norm": 0.8132149577140808,
"learning_rate": 4.9410241371412525e-06,
"loss": 0.0023,
"step": 123
},
{
"epoch": 1.7222222222222223,
"grad_norm": 0.27094146609306335,
"learning_rate": 4.935806850983034e-06,
"loss": 0.001,
"step": 124
},
{
"epoch": 1.7361111111111112,
"grad_norm": 0.10404836386442184,
"learning_rate": 4.9303714610485705e-06,
"loss": 0.0005,
"step": 125
},
{
"epoch": 1.75,
"grad_norm": 0.9027087688446045,
"learning_rate": 4.924718454026318e-06,
"loss": 0.005,
"step": 126
},
{
"epoch": 1.7638888888888888,
"grad_norm": 0.3427490293979645,
"learning_rate": 4.918848336090309e-06,
"loss": 0.0013,
"step": 127
},
{
"epoch": 1.7777777777777777,
"grad_norm": 0.41760626435279846,
"learning_rate": 4.912761632854834e-06,
"loss": 0.0032,
"step": 128
},
{
"epoch": 1.7916666666666665,
"grad_norm": 0.09792769700288773,
"learning_rate": 4.906458889327375e-06,
"loss": 0.0004,
"step": 129
},
{
"epoch": 1.8055555555555556,
"grad_norm": 0.5523985624313354,
"learning_rate": 4.899940669859807e-06,
"loss": 0.0077,
"step": 130
},
{
"epoch": 1.8194444444444444,
"grad_norm": 0.15261663496494293,
"learning_rate": 4.893207558097867e-06,
"loss": 0.0007,
"step": 131
},
{
"epoch": 1.8333333333333335,
"grad_norm": 0.12152901291847229,
"learning_rate": 4.8862601569288885e-06,
"loss": 0.0005,
"step": 132
},
{
"epoch": 1.8472222222222223,
"grad_norm": 0.1660558432340622,
"learning_rate": 4.879099088427824e-06,
"loss": 0.0007,
"step": 133
},
{
"epoch": 1.8611111111111112,
"grad_norm": 0.45732977986335754,
"learning_rate": 4.871724993801541e-06,
"loss": 0.0008,
"step": 134
},
{
"epoch": 1.875,
"grad_norm": 0.1277359277009964,
"learning_rate": 4.864138533331411e-06,
"loss": 0.0004,
"step": 135
},
{
"epoch": 1.8888888888888888,
"grad_norm": 0.08218172937631607,
"learning_rate": 4.8563403863141825e-06,
"loss": 0.0003,
"step": 136
},
{
"epoch": 1.9027777777777777,
"grad_norm": 0.35776910185813904,
"learning_rate": 4.84833125100116e-06,
"loss": 0.0012,
"step": 137
},
{
"epoch": 1.9166666666666665,
"grad_norm": 0.11485318094491959,
"learning_rate": 4.840111844535682e-06,
"loss": 0.0004,
"step": 138
},
{
"epoch": 1.9305555555555556,
"grad_norm": 0.03145573288202286,
"learning_rate": 4.8316829028889076e-06,
"loss": 0.0001,
"step": 139
},
{
"epoch": 1.9444444444444444,
"grad_norm": 0.03419964388012886,
"learning_rate": 4.823045180793914e-06,
"loss": 0.0001,
"step": 140
},
{
"epoch": 1.9583333333333335,
"grad_norm": 0.008005158044397831,
"learning_rate": 4.8141994516781196e-06,
"loss": 0.0,
"step": 141
},
{
"epoch": 1.9722222222222223,
"grad_norm": 0.30687257647514343,
"learning_rate": 4.805146507594034e-06,
"loss": 0.0006,
"step": 142
},
{
"epoch": 1.9861111111111112,
"grad_norm": 0.0030141561292111874,
"learning_rate": 4.7958871591483305e-06,
"loss": 0.0,
"step": 143
},
{
"epoch": 2.0,
"grad_norm": 0.0026682906318455935,
"learning_rate": 4.786422235429269e-06,
"loss": 0.0,
"step": 144
},
{
"epoch": 2.013888888888889,
"grad_norm": 0.008881614543497562,
"learning_rate": 4.776752583932455e-06,
"loss": 0.0,
"step": 145
},
{
"epoch": 2.0277777777777777,
"grad_norm": 0.001991939265280962,
"learning_rate": 4.766879070484957e-06,
"loss": 0.0,
"step": 146
},
{
"epoch": 2.0416666666666665,
"grad_norm": 0.006773048546165228,
"learning_rate": 4.756802579167781e-06,
"loss": 0.0,
"step": 147
},
{
"epoch": 2.0555555555555554,
"grad_norm": 0.00205055414699018,
"learning_rate": 4.746524012236706e-06,
"loss": 0.0,
"step": 148
},
{
"epoch": 2.0694444444444446,
"grad_norm": 0.0041306703351438046,
"learning_rate": 4.736044290041496e-06,
"loss": 0.0,
"step": 149
},
{
"epoch": 2.0833333333333335,
"grad_norm": 0.001996932551264763,
"learning_rate": 4.725364350943492e-06,
"loss": 0.0,
"step": 150
},
{
"epoch": 2.0972222222222223,
"grad_norm": 0.003478364087641239,
"learning_rate": 4.714485151231593e-06,
"loss": 0.0,
"step": 151
},
{
"epoch": 2.111111111111111,
"grad_norm": 0.01027267798781395,
"learning_rate": 4.703407665036622e-06,
"loss": 0.0,
"step": 152
},
{
"epoch": 2.125,
"grad_norm": 0.0020006722770631313,
"learning_rate": 4.692132884244113e-06,
"loss": 0.0,
"step": 153
},
{
"epoch": 2.138888888888889,
"grad_norm": 0.006151544861495495,
"learning_rate": 4.680661818405485e-06,
"loss": 0.0,
"step": 154
},
{
"epoch": 2.1527777777777777,
"grad_norm": 0.0020251101814210415,
"learning_rate": 4.668995494647653e-06,
"loss": 0.0,
"step": 155
},
{
"epoch": 2.1666666666666665,
"grad_norm": 0.0021893251687288284,
"learning_rate": 4.657134957581057e-06,
"loss": 0.0,
"step": 156
},
{
"epoch": 2.1805555555555554,
"grad_norm": 0.0018878229893743992,
"learning_rate": 4.645081269206128e-06,
"loss": 0.0,
"step": 157
},
{
"epoch": 2.1944444444444446,
"grad_norm": 0.759505569934845,
"learning_rate": 4.632835508818192e-06,
"loss": 0.0002,
"step": 158
},
{
"epoch": 2.2083333333333335,
"grad_norm": 0.0018357271328568459,
"learning_rate": 4.620398772910833e-06,
"loss": 0.0,
"step": 159
},
{
"epoch": 2.2222222222222223,
"grad_norm": 0.001739851082675159,
"learning_rate": 4.607772175077712e-06,
"loss": 0.0,
"step": 160
},
{
"epoch": 2.236111111111111,
"grad_norm": 0.0031391726806759834,
"learning_rate": 4.59495684591285e-06,
"loss": 0.0,
"step": 161
},
{
"epoch": 2.25,
"grad_norm": 0.001889107865281403,
"learning_rate": 4.581953932909403e-06,
"loss": 0.0,
"step": 162
},
{
"epoch": 2.263888888888889,
"grad_norm": 0.0014751956332474947,
"learning_rate": 4.5687646003569055e-06,
"loss": 0.0,
"step": 163
},
{
"epoch": 2.2777777777777777,
"grad_norm": 0.0014328192919492722,
"learning_rate": 4.555390029237026e-06,
"loss": 0.0,
"step": 164
},
{
"epoch": 2.2916666666666665,
"grad_norm": 0.0014799810014665127,
"learning_rate": 4.541831417117815e-06,
"loss": 0.0,
"step": 165
},
{
"epoch": 2.3055555555555554,
"grad_norm": 0.0013504689559340477,
"learning_rate": 4.528089978046481e-06,
"loss": 0.0,
"step": 166
},
{
"epoch": 2.3194444444444446,
"grad_norm": 0.001344231073744595,
"learning_rate": 4.514166942440679e-06,
"loss": 0.0,
"step": 167
},
{
"epoch": 2.3333333333333335,
"grad_norm": 0.001366922864690423,
"learning_rate": 4.5000635569783365e-06,
"loss": 0.0,
"step": 168
},
{
"epoch": 2.3472222222222223,
"grad_norm": 0.0013009505346417427,
"learning_rate": 4.4857810844860325e-06,
"loss": 0.0,
"step": 169
},
{
"epoch": 2.361111111111111,
"grad_norm": 0.001247942098416388,
"learning_rate": 4.471320803825915e-06,
"loss": 0.0,
"step": 170
},
{
"epoch": 2.375,
"grad_norm": 0.0011512853670865297,
"learning_rate": 4.4566840097811956e-06,
"loss": 0.0,
"step": 171
},
{
"epoch": 2.388888888888889,
"grad_norm": 0.001167183741927147,
"learning_rate": 4.4418720129402145e-06,
"loss": 0.0,
"step": 172
},
{
"epoch": 2.4027777777777777,
"grad_norm": 0.0011255062418058515,
"learning_rate": 4.426886139579083e-06,
"loss": 0.0,
"step": 173
},
{
"epoch": 2.4166666666666665,
"grad_norm": 0.0010559650836512446,
"learning_rate": 4.411727731542937e-06,
"loss": 0.0,
"step": 174
},
{
"epoch": 2.4305555555555554,
"grad_norm": 0.0010468937689438462,
"learning_rate": 4.39639814612578e-06,
"loss": 0.0,
"step": 175
},
{
"epoch": 2.4444444444444446,
"grad_norm": 0.0009965520584955812,
"learning_rate": 4.3808987559489536e-06,
"loss": 0.0,
"step": 176
},
{
"epoch": 2.4583333333333335,
"grad_norm": 0.000950520858168602,
"learning_rate": 4.365230948838232e-06,
"loss": 0.0,
"step": 177
},
{
"epoch": 2.4722222222222223,
"grad_norm": 0.0009662396623753011,
"learning_rate": 4.349396127699552e-06,
"loss": 0.0,
"step": 178
},
{
"epoch": 2.486111111111111,
"grad_norm": 0.0009316857904195786,
"learning_rate": 4.3333957103934025e-06,
"loss": 0.0,
"step": 179
},
{
"epoch": 2.5,
"grad_norm": 0.0009209261042997241,
"learning_rate": 4.317231129607859e-06,
"loss": 0.0,
"step": 180
},
{
"epoch": 2.513888888888889,
"grad_norm": 0.0008661423926241696,
"learning_rate": 4.30090383273031e-06,
"loss": 0.0,
"step": 181
},
{
"epoch": 2.5277777777777777,
"grad_norm": 0.0008176359115168452,
"learning_rate": 4.2844152817178476e-06,
"loss": 0.0,
"step": 182
},
{
"epoch": 2.5416666666666665,
"grad_norm": 0.0008025923161767423,
"learning_rate": 4.267766952966369e-06,
"loss": 0.0,
"step": 183
},
{
"epoch": 2.5555555555555554,
"grad_norm": 0.0008243928314186633,
"learning_rate": 4.2509603371783776e-06,
"loss": 0.0,
"step": 184
},
{
"epoch": 2.5694444444444446,
"grad_norm": 0.0013688765466213226,
"learning_rate": 4.233996939229502e-06,
"loss": 0.0,
"step": 185
},
{
"epoch": 2.5833333333333335,
"grad_norm": 0.0007681425777263939,
"learning_rate": 4.216878278033753e-06,
"loss": 0.0,
"step": 186
},
{
"epoch": 2.5972222222222223,
"grad_norm": 0.0007665084558539093,
"learning_rate": 4.199605886407515e-06,
"loss": 0.0,
"step": 187
},
{
"epoch": 2.611111111111111,
"grad_norm": 0.000745179713703692,
"learning_rate": 4.1821813109322975e-06,
"loss": 0.0,
"step": 188
},
{
"epoch": 2.625,
"grad_norm": 0.0007080566138029099,
"learning_rate": 4.164606111816256e-06,
"loss": 0.0,
"step": 189
},
{
"epoch": 2.638888888888889,
"grad_norm": 0.0007035013986751437,
"learning_rate": 4.146881862754485e-06,
"loss": 0.0,
"step": 190
},
{
"epoch": 2.6527777777777777,
"grad_norm": 0.001035734312608838,
"learning_rate": 4.129010150788112e-06,
"loss": 0.0,
"step": 191
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.000686554005369544,
"learning_rate": 4.110992576162193e-06,
"loss": 0.0,
"step": 192
},
{
"epoch": 2.6805555555555554,
"grad_norm": 0.0006567820673808455,
"learning_rate": 4.092830752182423e-06,
"loss": 0.0,
"step": 193
},
{
"epoch": 2.6944444444444446,
"grad_norm": 0.0006689206347800791,
"learning_rate": 4.074526305070679e-06,
"loss": 0.0,
"step": 194
},
{
"epoch": 2.7083333333333335,
"grad_norm": 0.000665506231598556,
"learning_rate": 4.056080873819412e-06,
"loss": 0.0,
"step": 195
},
{
"epoch": 2.7222222222222223,
"grad_norm": 0.0006280328962020576,
"learning_rate": 4.037496110044885e-06,
"loss": 0.0,
"step": 196
},
{
"epoch": 2.736111111111111,
"grad_norm": 0.0005998269189149141,
"learning_rate": 4.018773677839289e-06,
"loss": 0.0,
"step": 197
},
{
"epoch": 2.75,
"grad_norm": 0.0007591253379359841,
"learning_rate": 3.999915253621739e-06,
"loss": 0.0,
"step": 198
},
{
"epoch": 2.763888888888889,
"grad_norm": 0.0005739334737882018,
"learning_rate": 3.980922525988167e-06,
"loss": 0.0,
"step": 199
},
{
"epoch": 2.7777777777777777,
"grad_norm": 0.0005984510062262416,
"learning_rate": 3.961797195560118e-06,
"loss": 0.0,
"step": 200
},
{
"epoch": 2.7916666666666665,
"grad_norm": 0.0007093317108228803,
"learning_rate": 3.942540974832486e-06,
"loss": 0.0,
"step": 201
},
{
"epoch": 2.8055555555555554,
"grad_norm": 0.0005686501390300691,
"learning_rate": 3.9231555880201655e-06,
"loss": 0.0,
"step": 202
},
{
"epoch": 2.8194444444444446,
"grad_norm": 0.0005396155174821615,
"learning_rate": 3.903642770903671e-06,
"loss": 0.0,
"step": 203
},
{
"epoch": 2.8333333333333335,
"grad_norm": 0.000549685733858496,
"learning_rate": 3.884004270673711e-06,
"loss": 0.0,
"step": 204
},
{
"epoch": 2.8472222222222223,
"grad_norm": 0.0005211409879848361,
"learning_rate": 3.864241845774746e-06,
"loss": 0.0,
"step": 205
},
{
"epoch": 2.861111111111111,
"grad_norm": 0.0005807566340081394,
"learning_rate": 3.844357265747531e-06,
"loss": 0.0,
"step": 206
},
{
"epoch": 2.875,
"grad_norm": 0.0005310736014507711,
"learning_rate": 3.8243523110706736e-06,
"loss": 0.0,
"step": 207
},
{
"epoch": 2.888888888888889,
"grad_norm": 0.001211474766023457,
"learning_rate": 3.8042287730012117e-06,
"loss": 0.0,
"step": 208
},
{
"epoch": 2.9027777777777777,
"grad_norm": 0.0005012262845411897,
"learning_rate": 3.7839884534142157e-06,
"loss": 0.0,
"step": 209
},
{
"epoch": 2.9166666666666665,
"grad_norm": 0.0005107534816488624,
"learning_rate": 3.7636331646414524e-06,
"loss": 0.0,
"step": 210
},
{
"epoch": 2.9305555555555554,
"grad_norm": 0.0005153871607035398,
"learning_rate": 3.7431647293091076e-06,
"loss": 0.0,
"step": 211
},
{
"epoch": 2.9444444444444446,
"grad_norm": 0.0005016613868065178,
"learning_rate": 3.7225849801745835e-06,
"loss": 0.0,
"step": 212
},
{
"epoch": 2.9583333333333335,
"grad_norm": 0.00048161958693526685,
"learning_rate": 3.701895759962397e-06,
"loss": 0.0,
"step": 213
},
{
"epoch": 2.9722222222222223,
"grad_norm": 0.0004826453805435449,
"learning_rate": 3.6810989211991777e-06,
"loss": 0.0,
"step": 214
},
{
"epoch": 2.986111111111111,
"grad_norm": 0.0004991457099094987,
"learning_rate": 3.6601963260477923e-06,
"loss": 0.0,
"step": 215
},
{
"epoch": 3.0,
"grad_norm": 0.0004765830235555768,
"learning_rate": 3.6391898461406045e-06,
"loss": 0.0,
"step": 216
}
],
"logging_steps": 1,
"max_steps": 432,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 72,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.4393990203572224e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}