xp162 / checkpoint-228 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
3e99523 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 228,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013157894736842105,
"grad_norm": 34.99433898925781,
"learning_rate": 5.0000000000000004e-08,
"loss": 2.595,
"step": 1
},
{
"epoch": 0.02631578947368421,
"grad_norm": 35.6848258972168,
"learning_rate": 1.0000000000000001e-07,
"loss": 2.6447,
"step": 2
},
{
"epoch": 0.039473684210526314,
"grad_norm": 35.07997512817383,
"learning_rate": 1.5000000000000002e-07,
"loss": 2.5819,
"step": 3
},
{
"epoch": 0.05263157894736842,
"grad_norm": 34.3863525390625,
"learning_rate": 2.0000000000000002e-07,
"loss": 2.5739,
"step": 4
},
{
"epoch": 0.06578947368421052,
"grad_norm": 35.443077087402344,
"learning_rate": 2.5000000000000004e-07,
"loss": 2.6071,
"step": 5
},
{
"epoch": 0.07894736842105263,
"grad_norm": 34.70173263549805,
"learning_rate": 3.0000000000000004e-07,
"loss": 2.5487,
"step": 6
},
{
"epoch": 0.09210526315789473,
"grad_norm": 34.421295166015625,
"learning_rate": 3.5000000000000004e-07,
"loss": 2.5494,
"step": 7
},
{
"epoch": 0.10526315789473684,
"grad_norm": 35.152748107910156,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.5936,
"step": 8
},
{
"epoch": 0.11842105263157894,
"grad_norm": 34.947021484375,
"learning_rate": 4.5000000000000003e-07,
"loss": 2.5574,
"step": 9
},
{
"epoch": 0.13157894736842105,
"grad_norm": 34.67315673828125,
"learning_rate": 5.000000000000001e-07,
"loss": 2.4894,
"step": 10
},
{
"epoch": 0.14473684210526316,
"grad_norm": 34.679954528808594,
"learning_rate": 5.5e-07,
"loss": 2.4985,
"step": 11
},
{
"epoch": 0.15789473684210525,
"grad_norm": 33.57002258300781,
"learning_rate": 6.000000000000001e-07,
"loss": 2.4339,
"step": 12
},
{
"epoch": 0.17105263157894737,
"grad_norm": 33.517276763916016,
"learning_rate": 6.5e-07,
"loss": 2.4055,
"step": 13
},
{
"epoch": 0.18421052631578946,
"grad_norm": 33.5312385559082,
"learning_rate": 7.000000000000001e-07,
"loss": 2.3806,
"step": 14
},
{
"epoch": 0.19736842105263158,
"grad_norm": 32.01276779174805,
"learning_rate": 7.5e-07,
"loss": 2.2505,
"step": 15
},
{
"epoch": 0.21052631578947367,
"grad_norm": 31.827980041503906,
"learning_rate": 8.000000000000001e-07,
"loss": 2.1359,
"step": 16
},
{
"epoch": 0.2236842105263158,
"grad_norm": 31.437101364135742,
"learning_rate": 8.500000000000001e-07,
"loss": 2.1117,
"step": 17
},
{
"epoch": 0.23684210526315788,
"grad_norm": 30.315187454223633,
"learning_rate": 9.000000000000001e-07,
"loss": 1.9795,
"step": 18
},
{
"epoch": 0.25,
"grad_norm": 29.622655868530273,
"learning_rate": 9.500000000000001e-07,
"loss": 1.8472,
"step": 19
},
{
"epoch": 0.2631578947368421,
"grad_norm": 28.628408432006836,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.7283,
"step": 20
},
{
"epoch": 0.27631578947368424,
"grad_norm": 27.83180046081543,
"learning_rate": 1.0500000000000001e-06,
"loss": 1.5942,
"step": 21
},
{
"epoch": 0.2894736842105263,
"grad_norm": 26.911596298217773,
"learning_rate": 1.1e-06,
"loss": 1.4467,
"step": 22
},
{
"epoch": 0.3026315789473684,
"grad_norm": 25.88102149963379,
"learning_rate": 1.1500000000000002e-06,
"loss": 1.3007,
"step": 23
},
{
"epoch": 0.3157894736842105,
"grad_norm": 25.146381378173828,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.1319,
"step": 24
},
{
"epoch": 0.32894736842105265,
"grad_norm": 24.800382614135742,
"learning_rate": 1.25e-06,
"loss": 0.9359,
"step": 25
},
{
"epoch": 0.34210526315789475,
"grad_norm": 24.648332595825195,
"learning_rate": 1.3e-06,
"loss": 0.7054,
"step": 26
},
{
"epoch": 0.35526315789473684,
"grad_norm": 22.947620391845703,
"learning_rate": 1.3500000000000002e-06,
"loss": 0.5209,
"step": 27
},
{
"epoch": 0.3684210526315789,
"grad_norm": 17.80010414123535,
"learning_rate": 1.4000000000000001e-06,
"loss": 0.3546,
"step": 28
},
{
"epoch": 0.3815789473684211,
"grad_norm": 11.841789245605469,
"learning_rate": 1.45e-06,
"loss": 0.26,
"step": 29
},
{
"epoch": 0.39473684210526316,
"grad_norm": 7.275839805603027,
"learning_rate": 1.5e-06,
"loss": 0.1808,
"step": 30
},
{
"epoch": 0.40789473684210525,
"grad_norm": 4.6324543952941895,
"learning_rate": 1.5500000000000002e-06,
"loss": 0.1464,
"step": 31
},
{
"epoch": 0.42105263157894735,
"grad_norm": 3.1281485557556152,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.1079,
"step": 32
},
{
"epoch": 0.4342105263157895,
"grad_norm": 2.062562942504883,
"learning_rate": 1.6500000000000003e-06,
"loss": 0.0966,
"step": 33
},
{
"epoch": 0.4473684210526316,
"grad_norm": 2.1343328952789307,
"learning_rate": 1.7000000000000002e-06,
"loss": 0.088,
"step": 34
},
{
"epoch": 0.4605263157894737,
"grad_norm": 1.6768524646759033,
"learning_rate": 1.75e-06,
"loss": 0.0783,
"step": 35
},
{
"epoch": 0.47368421052631576,
"grad_norm": 1.0879229307174683,
"learning_rate": 1.8000000000000001e-06,
"loss": 0.0623,
"step": 36
},
{
"epoch": 0.4868421052631579,
"grad_norm": 0.83177649974823,
"learning_rate": 1.85e-06,
"loss": 0.0655,
"step": 37
},
{
"epoch": 0.5,
"grad_norm": 0.5678385496139526,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.0565,
"step": 38
},
{
"epoch": 0.5131578947368421,
"grad_norm": 0.6994458436965942,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.0491,
"step": 39
},
{
"epoch": 0.5263157894736842,
"grad_norm": 0.711387038230896,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0507,
"step": 40
},
{
"epoch": 0.5394736842105263,
"grad_norm": 0.7169735431671143,
"learning_rate": 2.05e-06,
"loss": 0.0478,
"step": 41
},
{
"epoch": 0.5526315789473685,
"grad_norm": 0.603631317615509,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.0507,
"step": 42
},
{
"epoch": 0.5657894736842105,
"grad_norm": 0.617487907409668,
"learning_rate": 2.15e-06,
"loss": 0.043,
"step": 43
},
{
"epoch": 0.5789473684210527,
"grad_norm": 0.4638065993785858,
"learning_rate": 2.2e-06,
"loss": 0.0472,
"step": 44
},
{
"epoch": 0.5921052631578947,
"grad_norm": 0.5996385216712952,
"learning_rate": 2.25e-06,
"loss": 0.0429,
"step": 45
},
{
"epoch": 0.6052631578947368,
"grad_norm": 0.39118286967277527,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.0421,
"step": 46
},
{
"epoch": 0.618421052631579,
"grad_norm": 0.3118075728416443,
"learning_rate": 2.35e-06,
"loss": 0.0383,
"step": 47
},
{
"epoch": 0.631578947368421,
"grad_norm": 0.31731992959976196,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.041,
"step": 48
},
{
"epoch": 0.6447368421052632,
"grad_norm": 0.5413194298744202,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.0397,
"step": 49
},
{
"epoch": 0.6578947368421053,
"grad_norm": 0.32958006858825684,
"learning_rate": 2.5e-06,
"loss": 0.0355,
"step": 50
},
{
"epoch": 0.6710526315789473,
"grad_norm": 0.596309244632721,
"learning_rate": 2.55e-06,
"loss": 0.0413,
"step": 51
},
{
"epoch": 0.6842105263157895,
"grad_norm": 0.4557362496852875,
"learning_rate": 2.6e-06,
"loss": 0.0461,
"step": 52
},
{
"epoch": 0.6973684210526315,
"grad_norm": 0.3345410227775574,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0385,
"step": 53
},
{
"epoch": 0.7105263157894737,
"grad_norm": 0.3047848343849182,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0383,
"step": 54
},
{
"epoch": 0.7236842105263158,
"grad_norm": 0.43763449788093567,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.038,
"step": 55
},
{
"epoch": 0.7368421052631579,
"grad_norm": 0.26870036125183105,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0374,
"step": 56
},
{
"epoch": 0.75,
"grad_norm": 0.38762542605400085,
"learning_rate": 2.85e-06,
"loss": 0.0349,
"step": 57
},
{
"epoch": 0.7631578947368421,
"grad_norm": 0.27517396211624146,
"learning_rate": 2.9e-06,
"loss": 0.0398,
"step": 58
},
{
"epoch": 0.7763157894736842,
"grad_norm": 0.30815261602401733,
"learning_rate": 2.95e-06,
"loss": 0.0364,
"step": 59
},
{
"epoch": 0.7894736842105263,
"grad_norm": 0.30011361837387085,
"learning_rate": 3e-06,
"loss": 0.0307,
"step": 60
},
{
"epoch": 0.8026315789473685,
"grad_norm": 0.3269154727458954,
"learning_rate": 3.05e-06,
"loss": 0.0344,
"step": 61
},
{
"epoch": 0.8157894736842105,
"grad_norm": 0.3750869333744049,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0339,
"step": 62
},
{
"epoch": 0.8289473684210527,
"grad_norm": 0.29285815358161926,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.034,
"step": 63
},
{
"epoch": 0.8421052631578947,
"grad_norm": 0.4157550632953644,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0348,
"step": 64
},
{
"epoch": 0.8552631578947368,
"grad_norm": 0.2852867543697357,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0319,
"step": 65
},
{
"epoch": 0.868421052631579,
"grad_norm": 0.4384031593799591,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0319,
"step": 66
},
{
"epoch": 0.881578947368421,
"grad_norm": 0.4003254771232605,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0347,
"step": 67
},
{
"epoch": 0.8947368421052632,
"grad_norm": 0.49913832545280457,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0347,
"step": 68
},
{
"epoch": 0.9078947368421053,
"grad_norm": 0.22642269730567932,
"learning_rate": 3.45e-06,
"loss": 0.0306,
"step": 69
},
{
"epoch": 0.9210526315789473,
"grad_norm": 0.34004101157188416,
"learning_rate": 3.5e-06,
"loss": 0.0337,
"step": 70
},
{
"epoch": 0.9342105263157895,
"grad_norm": 0.21503636240959167,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0311,
"step": 71
},
{
"epoch": 0.9473684210526315,
"grad_norm": 0.33802086114883423,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0293,
"step": 72
},
{
"epoch": 0.9605263157894737,
"grad_norm": 0.2488064169883728,
"learning_rate": 3.65e-06,
"loss": 0.0318,
"step": 73
},
{
"epoch": 0.9736842105263158,
"grad_norm": 0.21124528348445892,
"learning_rate": 3.7e-06,
"loss": 0.0293,
"step": 74
},
{
"epoch": 0.9868421052631579,
"grad_norm": 0.3108712136745453,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0288,
"step": 75
},
{
"epoch": 1.0,
"grad_norm": 0.33483418822288513,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.031,
"step": 76
},
{
"epoch": 1.013157894736842,
"grad_norm": 0.3099130690097809,
"learning_rate": 3.85e-06,
"loss": 0.0286,
"step": 77
},
{
"epoch": 1.0263157894736843,
"grad_norm": 0.22946476936340332,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0307,
"step": 78
},
{
"epoch": 1.0394736842105263,
"grad_norm": 0.36924120783805847,
"learning_rate": 3.95e-06,
"loss": 0.0274,
"step": 79
},
{
"epoch": 1.0526315789473684,
"grad_norm": 0.30895617604255676,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0274,
"step": 80
},
{
"epoch": 1.0657894736842106,
"grad_norm": 0.42033568024635315,
"learning_rate": 4.05e-06,
"loss": 0.0298,
"step": 81
},
{
"epoch": 1.0789473684210527,
"grad_norm": 0.35573887825012207,
"learning_rate": 4.1e-06,
"loss": 0.0286,
"step": 82
},
{
"epoch": 1.0921052631578947,
"grad_norm": 0.24631913006305695,
"learning_rate": 4.15e-06,
"loss": 0.0294,
"step": 83
},
{
"epoch": 1.1052631578947367,
"grad_norm": 0.2908592224121094,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0243,
"step": 84
},
{
"epoch": 1.118421052631579,
"grad_norm": 0.3293064832687378,
"learning_rate": 4.25e-06,
"loss": 0.0253,
"step": 85
},
{
"epoch": 1.131578947368421,
"grad_norm": 0.3789626359939575,
"learning_rate": 4.3e-06,
"loss": 0.0253,
"step": 86
},
{
"epoch": 1.1447368421052633,
"grad_norm": 0.3900983929634094,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0248,
"step": 87
},
{
"epoch": 1.1578947368421053,
"grad_norm": 0.28972727060317993,
"learning_rate": 4.4e-06,
"loss": 0.0256,
"step": 88
},
{
"epoch": 1.1710526315789473,
"grad_norm": 0.4615432620048523,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0259,
"step": 89
},
{
"epoch": 1.1842105263157894,
"grad_norm": 0.3959222137928009,
"learning_rate": 4.5e-06,
"loss": 0.0277,
"step": 90
},
{
"epoch": 1.1973684210526316,
"grad_norm": 0.4927828907966614,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.0251,
"step": 91
},
{
"epoch": 1.2105263157894737,
"grad_norm": 0.23854510486125946,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0214,
"step": 92
},
{
"epoch": 1.2236842105263157,
"grad_norm": 0.2470882534980774,
"learning_rate": 4.65e-06,
"loss": 0.0255,
"step": 93
},
{
"epoch": 1.236842105263158,
"grad_norm": 0.22575952112674713,
"learning_rate": 4.7e-06,
"loss": 0.0208,
"step": 94
},
{
"epoch": 1.25,
"grad_norm": 0.437495619058609,
"learning_rate": 4.75e-06,
"loss": 0.0234,
"step": 95
},
{
"epoch": 1.263157894736842,
"grad_norm": 0.2712303102016449,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0236,
"step": 96
},
{
"epoch": 1.2763157894736843,
"grad_norm": 0.2843461334705353,
"learning_rate": 4.85e-06,
"loss": 0.0195,
"step": 97
},
{
"epoch": 1.2894736842105263,
"grad_norm": 0.21141311526298523,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0223,
"step": 98
},
{
"epoch": 1.3026315789473684,
"grad_norm": 0.25484079122543335,
"learning_rate": 4.95e-06,
"loss": 0.0211,
"step": 99
},
{
"epoch": 1.3157894736842106,
"grad_norm": 0.358674556016922,
"learning_rate": 5e-06,
"loss": 0.027,
"step": 100
},
{
"epoch": 1.3289473684210527,
"grad_norm": 0.20442990958690643,
"learning_rate": 4.999902656502973e-06,
"loss": 0.0234,
"step": 101
},
{
"epoch": 1.3421052631578947,
"grad_norm": 0.2281407117843628,
"learning_rate": 4.9996106335924965e-06,
"loss": 0.0243,
"step": 102
},
{
"epoch": 1.3552631578947367,
"grad_norm": 0.23803724348545074,
"learning_rate": 4.999123954009797e-06,
"loss": 0.0189,
"step": 103
},
{
"epoch": 1.368421052631579,
"grad_norm": 0.21493025124073029,
"learning_rate": 4.998442655654946e-06,
"loss": 0.0207,
"step": 104
},
{
"epoch": 1.381578947368421,
"grad_norm": 0.2565159797668457,
"learning_rate": 4.997566791583916e-06,
"loss": 0.0178,
"step": 105
},
{
"epoch": 1.3947368421052633,
"grad_norm": 0.3488551378250122,
"learning_rate": 4.996496430004446e-06,
"loss": 0.0226,
"step": 106
},
{
"epoch": 1.4078947368421053,
"grad_norm": 0.27695611119270325,
"learning_rate": 4.995231654270726e-06,
"loss": 0.0189,
"step": 107
},
{
"epoch": 1.4210526315789473,
"grad_norm": 0.23477056622505188,
"learning_rate": 4.993772562876909e-06,
"loss": 0.0182,
"step": 108
},
{
"epoch": 1.4342105263157894,
"grad_norm": 0.22611404955387115,
"learning_rate": 4.992119269449445e-06,
"loss": 0.0168,
"step": 109
},
{
"epoch": 1.4473684210526316,
"grad_norm": 0.25616368651390076,
"learning_rate": 4.990271902738223e-06,
"loss": 0.022,
"step": 110
},
{
"epoch": 1.4605263157894737,
"grad_norm": 0.23842717707157135,
"learning_rate": 4.988230606606552e-06,
"loss": 0.0163,
"step": 111
},
{
"epoch": 1.4736842105263157,
"grad_norm": 0.24285905063152313,
"learning_rate": 4.985995540019956e-06,
"loss": 0.0202,
"step": 112
},
{
"epoch": 1.486842105263158,
"grad_norm": 0.24602730572223663,
"learning_rate": 4.983566877033791e-06,
"loss": 0.0173,
"step": 113
},
{
"epoch": 1.5,
"grad_norm": 0.26218464970588684,
"learning_rate": 4.980944806779698e-06,
"loss": 0.0206,
"step": 114
},
{
"epoch": 1.513157894736842,
"grad_norm": 0.2999787926673889,
"learning_rate": 4.9781295334508664e-06,
"loss": 0.0178,
"step": 115
},
{
"epoch": 1.526315789473684,
"grad_norm": 0.20500704646110535,
"learning_rate": 4.975121276286136e-06,
"loss": 0.0181,
"step": 116
},
{
"epoch": 1.5394736842105263,
"grad_norm": 0.25106561183929443,
"learning_rate": 4.9719202695529265e-06,
"loss": 0.0128,
"step": 117
},
{
"epoch": 1.5526315789473686,
"grad_norm": 0.2686936855316162,
"learning_rate": 4.968526762528988e-06,
"loss": 0.0146,
"step": 118
},
{
"epoch": 1.5657894736842106,
"grad_norm": 0.2770400047302246,
"learning_rate": 4.964941019482995e-06,
"loss": 0.0167,
"step": 119
},
{
"epoch": 1.5789473684210527,
"grad_norm": 0.27510589361190796,
"learning_rate": 4.961163319653959e-06,
"loss": 0.0162,
"step": 120
},
{
"epoch": 1.5921052631578947,
"grad_norm": 0.3720133602619171,
"learning_rate": 4.9571939572294914e-06,
"loss": 0.0163,
"step": 121
},
{
"epoch": 1.6052631578947367,
"grad_norm": 0.2288741022348404,
"learning_rate": 4.953033241322887e-06,
"loss": 0.0133,
"step": 122
},
{
"epoch": 1.618421052631579,
"grad_norm": 0.31084850430488586,
"learning_rate": 4.948681495949055e-06,
"loss": 0.0124,
"step": 123
},
{
"epoch": 1.631578947368421,
"grad_norm": 0.19490985572338104,
"learning_rate": 4.944139059999286e-06,
"loss": 0.0114,
"step": 124
},
{
"epoch": 1.6447368421052633,
"grad_norm": 0.3074445426464081,
"learning_rate": 4.939406287214861e-06,
"loss": 0.0153,
"step": 125
},
{
"epoch": 1.6578947368421053,
"grad_norm": 0.29279908537864685,
"learning_rate": 4.9344835461595016e-06,
"loss": 0.0117,
"step": 126
},
{
"epoch": 1.6710526315789473,
"grad_norm": 0.3299407362937927,
"learning_rate": 4.929371220190671e-06,
"loss": 0.0128,
"step": 127
},
{
"epoch": 1.6842105263157894,
"grad_norm": 0.24818794429302216,
"learning_rate": 4.9240697074297205e-06,
"loss": 0.0146,
"step": 128
},
{
"epoch": 1.6973684210526314,
"grad_norm": 0.35983219742774963,
"learning_rate": 4.918579420730884e-06,
"loss": 0.0138,
"step": 129
},
{
"epoch": 1.7105263157894737,
"grad_norm": 0.2583932876586914,
"learning_rate": 4.912900787649124e-06,
"loss": 0.0136,
"step": 130
},
{
"epoch": 1.723684210526316,
"grad_norm": 0.20754319429397583,
"learning_rate": 4.907034250406846e-06,
"loss": 0.0116,
"step": 131
},
{
"epoch": 1.736842105263158,
"grad_norm": 0.30609601736068726,
"learning_rate": 4.900980265859449e-06,
"loss": 0.0111,
"step": 132
},
{
"epoch": 1.75,
"grad_norm": 0.3754304349422455,
"learning_rate": 4.894739305459754e-06,
"loss": 0.0126,
"step": 133
},
{
"epoch": 1.763157894736842,
"grad_norm": 0.2517055571079254,
"learning_rate": 4.88831185522129e-06,
"loss": 0.0118,
"step": 134
},
{
"epoch": 1.776315789473684,
"grad_norm": 0.198478102684021,
"learning_rate": 4.881698415680442e-06,
"loss": 0.0087,
"step": 135
},
{
"epoch": 1.7894736842105263,
"grad_norm": 0.2307695895433426,
"learning_rate": 4.874899501857477e-06,
"loss": 0.0094,
"step": 136
},
{
"epoch": 1.8026315789473686,
"grad_norm": 0.17823486030101776,
"learning_rate": 4.867915643216434e-06,
"loss": 0.0098,
"step": 137
},
{
"epoch": 1.8157894736842106,
"grad_norm": 0.2157433032989502,
"learning_rate": 4.860747383623889e-06,
"loss": 0.0114,
"step": 138
},
{
"epoch": 1.8289473684210527,
"grad_norm": 0.21051311492919922,
"learning_rate": 4.85339528130661e-06,
"loss": 0.011,
"step": 139
},
{
"epoch": 1.8421052631578947,
"grad_norm": 0.32886555790901184,
"learning_rate": 4.845859908808074e-06,
"loss": 0.011,
"step": 140
},
{
"epoch": 1.8552631578947367,
"grad_norm": 0.22413378953933716,
"learning_rate": 4.838141852943891e-06,
"loss": 0.0087,
"step": 141
},
{
"epoch": 1.868421052631579,
"grad_norm": 0.2896019518375397,
"learning_rate": 4.830241714756099e-06,
"loss": 0.011,
"step": 142
},
{
"epoch": 1.881578947368421,
"grad_norm": 0.26163023710250854,
"learning_rate": 4.822160109466361e-06,
"loss": 0.0084,
"step": 143
},
{
"epoch": 1.8947368421052633,
"grad_norm": 0.23998413980007172,
"learning_rate": 4.813897666428054e-06,
"loss": 0.0094,
"step": 144
},
{
"epoch": 1.9078947368421053,
"grad_norm": 0.2334728091955185,
"learning_rate": 4.805455029077255e-06,
"loss": 0.007,
"step": 145
},
{
"epoch": 1.9210526315789473,
"grad_norm": 0.17431940138339996,
"learning_rate": 4.79683285488264e-06,
"loss": 0.0047,
"step": 146
},
{
"epoch": 1.9342105263157894,
"grad_norm": 0.19151932001113892,
"learning_rate": 4.788031815294282e-06,
"loss": 0.0056,
"step": 147
},
{
"epoch": 1.9473684210526314,
"grad_norm": 0.2352588027715683,
"learning_rate": 4.779052595691355e-06,
"loss": 0.0107,
"step": 148
},
{
"epoch": 1.9605263157894737,
"grad_norm": 0.2848915159702301,
"learning_rate": 4.76989589532877e-06,
"loss": 0.0074,
"step": 149
},
{
"epoch": 1.973684210526316,
"grad_norm": 0.218011736869812,
"learning_rate": 4.7605624272827125e-06,
"loss": 0.0075,
"step": 150
},
{
"epoch": 1.986842105263158,
"grad_norm": 0.3043143153190613,
"learning_rate": 4.75105291839512e-06,
"loss": 0.0073,
"step": 151
},
{
"epoch": 2.0,
"grad_norm": 0.16677772998809814,
"learning_rate": 4.741368109217072e-06,
"loss": 0.0065,
"step": 152
},
{
"epoch": 2.013157894736842,
"grad_norm": 0.14940837025642395,
"learning_rate": 4.7315087539511225e-06,
"loss": 0.0034,
"step": 153
},
{
"epoch": 2.026315789473684,
"grad_norm": 0.14960654079914093,
"learning_rate": 4.721475620392567e-06,
"loss": 0.0034,
"step": 154
},
{
"epoch": 2.039473684210526,
"grad_norm": 0.2261868566274643,
"learning_rate": 4.711269489869654e-06,
"loss": 0.0034,
"step": 155
},
{
"epoch": 2.0526315789473686,
"grad_norm": 0.20907555520534515,
"learning_rate": 4.700891157182729e-06,
"loss": 0.0045,
"step": 156
},
{
"epoch": 2.0657894736842106,
"grad_norm": 0.15571005642414093,
"learning_rate": 4.690341430542351e-06,
"loss": 0.0032,
"step": 157
},
{
"epoch": 2.0789473684210527,
"grad_norm": 0.16968725621700287,
"learning_rate": 4.679621131506347e-06,
"loss": 0.0044,
"step": 158
},
{
"epoch": 2.0921052631578947,
"grad_norm": 0.1937742531299591,
"learning_rate": 4.668731094915835e-06,
"loss": 0.0027,
"step": 159
},
{
"epoch": 2.1052631578947367,
"grad_norm": 0.14914007484912872,
"learning_rate": 4.657672168830211e-06,
"loss": 0.0031,
"step": 160
},
{
"epoch": 2.1184210526315788,
"grad_norm": 0.19651293754577637,
"learning_rate": 4.646445214461105e-06,
"loss": 0.0043,
"step": 161
},
{
"epoch": 2.1315789473684212,
"grad_norm": 0.2023143172264099,
"learning_rate": 4.635051106105316e-06,
"loss": 0.0036,
"step": 162
},
{
"epoch": 2.1447368421052633,
"grad_norm": 0.17952999472618103,
"learning_rate": 4.623490731076728e-06,
"loss": 0.0024,
"step": 163
},
{
"epoch": 2.1578947368421053,
"grad_norm": 0.18410134315490723,
"learning_rate": 4.6117649896372055e-06,
"loss": 0.0054,
"step": 164
},
{
"epoch": 2.1710526315789473,
"grad_norm": 0.18808087706565857,
"learning_rate": 4.59987479492649e-06,
"loss": 0.0039,
"step": 165
},
{
"epoch": 2.1842105263157894,
"grad_norm": 0.12346187978982925,
"learning_rate": 4.587821072891089e-06,
"loss": 0.0036,
"step": 166
},
{
"epoch": 2.1973684210526314,
"grad_norm": 0.140532448887825,
"learning_rate": 4.5756047622121665e-06,
"loss": 0.0028,
"step": 167
},
{
"epoch": 2.2105263157894735,
"grad_norm": 0.8201041221618652,
"learning_rate": 4.563226814232444e-06,
"loss": 0.0028,
"step": 168
},
{
"epoch": 2.223684210526316,
"grad_norm": 0.26919177174568176,
"learning_rate": 4.550688192882115e-06,
"loss": 0.0032,
"step": 169
},
{
"epoch": 2.236842105263158,
"grad_norm": 0.1321878731250763,
"learning_rate": 4.53798987460378e-06,
"loss": 0.0023,
"step": 170
},
{
"epoch": 2.25,
"grad_norm": 0.12545251846313477,
"learning_rate": 4.525132848276405e-06,
"loss": 0.0024,
"step": 171
},
{
"epoch": 2.263157894736842,
"grad_norm": 0.1377445012331009,
"learning_rate": 4.512118115138315e-06,
"loss": 0.0033,
"step": 172
},
{
"epoch": 2.276315789473684,
"grad_norm": 0.10942364484071732,
"learning_rate": 4.498946688709216e-06,
"loss": 0.0023,
"step": 173
},
{
"epoch": 2.2894736842105265,
"grad_norm": 0.17425717413425446,
"learning_rate": 4.485619594711278e-06,
"loss": 0.003,
"step": 174
},
{
"epoch": 2.3026315789473686,
"grad_norm": 0.15876342356204987,
"learning_rate": 4.4721378709892475e-06,
"loss": 0.0034,
"step": 175
},
{
"epoch": 2.3157894736842106,
"grad_norm": 0.1537884920835495,
"learning_rate": 4.4585025674296315e-06,
"loss": 0.002,
"step": 176
},
{
"epoch": 2.3289473684210527,
"grad_norm": 0.13558532297611237,
"learning_rate": 4.444714745878936e-06,
"loss": 0.0021,
"step": 177
},
{
"epoch": 2.3421052631578947,
"grad_norm": 0.14405666291713715,
"learning_rate": 4.430775480060973e-06,
"loss": 0.0028,
"step": 178
},
{
"epoch": 2.3552631578947367,
"grad_norm": 0.19296719133853912,
"learning_rate": 4.416685855493246e-06,
"loss": 0.0034,
"step": 179
},
{
"epoch": 2.3684210526315788,
"grad_norm": 0.2153935730457306,
"learning_rate": 4.4024469694024194e-06,
"loss": 0.0032,
"step": 180
},
{
"epoch": 2.3815789473684212,
"grad_norm": 0.11674188822507858,
"learning_rate": 4.388059930638865e-06,
"loss": 0.0013,
"step": 181
},
{
"epoch": 2.3947368421052633,
"grad_norm": 0.21349935233592987,
"learning_rate": 4.373525859590313e-06,
"loss": 0.002,
"step": 182
},
{
"epoch": 2.4078947368421053,
"grad_norm": 0.16676126420497894,
"learning_rate": 4.358845888094607e-06,
"loss": 0.0015,
"step": 183
},
{
"epoch": 2.4210526315789473,
"grad_norm": 0.20975975692272186,
"learning_rate": 4.3440211593515556e-06,
"loss": 0.0025,
"step": 184
},
{
"epoch": 2.4342105263157894,
"grad_norm": 0.3014683425426483,
"learning_rate": 4.32905282783391e-06,
"loss": 0.0031,
"step": 185
},
{
"epoch": 2.4473684210526314,
"grad_norm": 0.1687438040971756,
"learning_rate": 4.313942059197457e-06,
"loss": 0.0014,
"step": 186
},
{
"epoch": 2.4605263157894735,
"grad_norm": 0.13351179659366608,
"learning_rate": 4.298690030190247e-06,
"loss": 0.0012,
"step": 187
},
{
"epoch": 2.473684210526316,
"grad_norm": 0.4079025387763977,
"learning_rate": 4.283297928560951e-06,
"loss": 0.0026,
"step": 188
},
{
"epoch": 2.486842105263158,
"grad_norm": 0.12639036774635315,
"learning_rate": 4.267766952966369e-06,
"loss": 0.0017,
"step": 189
},
{
"epoch": 2.5,
"grad_norm": 0.1551010012626648,
"learning_rate": 4.252098312878083e-06,
"loss": 0.0022,
"step": 190
},
{
"epoch": 2.513157894736842,
"grad_norm": 0.1431741863489151,
"learning_rate": 4.236293228488267e-06,
"loss": 0.0022,
"step": 191
},
{
"epoch": 2.526315789473684,
"grad_norm": 0.39600786566734314,
"learning_rate": 4.220352930614672e-06,
"loss": 0.0031,
"step": 192
},
{
"epoch": 2.5394736842105265,
"grad_norm": 0.13951376080513,
"learning_rate": 4.204278660604767e-06,
"loss": 0.0016,
"step": 193
},
{
"epoch": 2.5526315789473686,
"grad_norm": 0.10893042385578156,
"learning_rate": 4.1880716702390764e-06,
"loss": 0.0007,
"step": 194
},
{
"epoch": 2.5657894736842106,
"grad_norm": 0.16801239550113678,
"learning_rate": 4.171733221633695e-06,
"loss": 0.002,
"step": 195
},
{
"epoch": 2.5789473684210527,
"grad_norm": 0.11393369734287262,
"learning_rate": 4.155264587142002e-06,
"loss": 0.0017,
"step": 196
},
{
"epoch": 2.5921052631578947,
"grad_norm": 0.23128700256347656,
"learning_rate": 4.138667049255574e-06,
"loss": 0.0018,
"step": 197
},
{
"epoch": 2.6052631578947367,
"grad_norm": 0.06730300188064575,
"learning_rate": 4.121941900504316e-06,
"loss": 0.0006,
"step": 198
},
{
"epoch": 2.6184210526315788,
"grad_norm": 0.11693810671567917,
"learning_rate": 4.105090443355801e-06,
"loss": 0.0012,
"step": 199
},
{
"epoch": 2.6315789473684212,
"grad_norm": 0.1186346486210823,
"learning_rate": 4.088113990113846e-06,
"loss": 0.0012,
"step": 200
},
{
"epoch": 2.6447368421052633,
"grad_norm": 0.2584531605243683,
"learning_rate": 4.071013862816311e-06,
"loss": 0.0025,
"step": 201
},
{
"epoch": 2.6578947368421053,
"grad_norm": 0.09868124127388,
"learning_rate": 4.0537913931321495e-06,
"loss": 0.0017,
"step": 202
},
{
"epoch": 2.6710526315789473,
"grad_norm": 0.09907737374305725,
"learning_rate": 4.036447922257699e-06,
"loss": 0.002,
"step": 203
},
{
"epoch": 2.6842105263157894,
"grad_norm": 0.06743597984313965,
"learning_rate": 4.018984800812248e-06,
"loss": 0.0006,
"step": 204
},
{
"epoch": 2.6973684210526314,
"grad_norm": 0.08913715183734894,
"learning_rate": 4.001403388732842e-06,
"loss": 0.0007,
"step": 205
},
{
"epoch": 2.7105263157894735,
"grad_norm": 0.12334564328193665,
"learning_rate": 3.983705055168391e-06,
"loss": 0.0006,
"step": 206
},
{
"epoch": 2.723684210526316,
"grad_norm": 0.10878646373748779,
"learning_rate": 3.965891178373038e-06,
"loss": 0.0016,
"step": 207
},
{
"epoch": 2.736842105263158,
"grad_norm": 0.10623253136873245,
"learning_rate": 3.947963145598833e-06,
"loss": 0.0015,
"step": 208
},
{
"epoch": 2.75,
"grad_norm": 0.15580499172210693,
"learning_rate": 3.929922352987702e-06,
"loss": 0.0011,
"step": 209
},
{
"epoch": 2.763157894736842,
"grad_norm": 0.06405838578939438,
"learning_rate": 3.911770205462717e-06,
"loss": 0.0007,
"step": 210
},
{
"epoch": 2.776315789473684,
"grad_norm": 0.17784689366817474,
"learning_rate": 3.8935081166186935e-06,
"loss": 0.0017,
"step": 211
},
{
"epoch": 2.7894736842105265,
"grad_norm": 0.14516866207122803,
"learning_rate": 3.875137508612104e-06,
"loss": 0.0014,
"step": 212
},
{
"epoch": 2.8026315789473686,
"grad_norm": 0.09510776400566101,
"learning_rate": 3.856659812050328e-06,
"loss": 0.0009,
"step": 213
},
{
"epoch": 2.8157894736842106,
"grad_norm": 0.1000828891992569,
"learning_rate": 3.838076465880248e-06,
"loss": 0.0008,
"step": 214
},
{
"epoch": 2.8289473684210527,
"grad_norm": 0.10773428529500961,
"learning_rate": 3.819388917276186e-06,
"loss": 0.0008,
"step": 215
},
{
"epoch": 2.8421052631578947,
"grad_norm": 0.12319213151931763,
"learning_rate": 3.8005986215272056e-06,
"loss": 0.0007,
"step": 216
},
{
"epoch": 2.8552631578947367,
"grad_norm": 0.07209170609712601,
"learning_rate": 3.7817070419237866e-06,
"loss": 0.0006,
"step": 217
},
{
"epoch": 2.8684210526315788,
"grad_norm": 0.12889248132705688,
"learning_rate": 3.7627156496438686e-06,
"loss": 0.0005,
"step": 218
},
{
"epoch": 2.8815789473684212,
"grad_norm": 0.05019540339708328,
"learning_rate": 3.7436259236382797e-06,
"loss": 0.0003,
"step": 219
},
{
"epoch": 2.8947368421052633,
"grad_norm": 0.10657542198896408,
"learning_rate": 3.7244393505155713e-06,
"loss": 0.0008,
"step": 220
},
{
"epoch": 2.9078947368421053,
"grad_norm": 0.15984083712100983,
"learning_rate": 3.7051574244262412e-06,
"loss": 0.0003,
"step": 221
},
{
"epoch": 2.9210526315789473,
"grad_norm": 0.1567343920469284,
"learning_rate": 3.6857816469463806e-06,
"loss": 0.0005,
"step": 222
},
{
"epoch": 2.9342105263157894,
"grad_norm": 0.07294822484254837,
"learning_rate": 3.6663135269607413e-06,
"loss": 0.0006,
"step": 223
},
{
"epoch": 2.9473684210526314,
"grad_norm": 0.04486699402332306,
"learning_rate": 3.6467545805452266e-06,
"loss": 0.0003,
"step": 224
},
{
"epoch": 2.9605263157894735,
"grad_norm": 0.08188032358884811,
"learning_rate": 3.6271063308488298e-06,
"loss": 0.0004,
"step": 225
},
{
"epoch": 2.973684210526316,
"grad_norm": 0.029995013028383255,
"learning_rate": 3.6073703079750204e-06,
"loss": 0.0002,
"step": 226
},
{
"epoch": 2.986842105263158,
"grad_norm": 0.029155094176530838,
"learning_rate": 3.5875480488625847e-06,
"loss": 0.0002,
"step": 227
},
{
"epoch": 3.0,
"grad_norm": 0.058334361761808395,
"learning_rate": 3.5676410971659404e-06,
"loss": 0.0003,
"step": 228
}
],
"logging_steps": 1,
"max_steps": 456,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 76,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.4667657840936616e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}