gemma-2-2b-norobots / trainer_state.json
Zangs3011's picture
Upload 8 files
05e840d verified
{
"best_metric": 1.6337618827819824,
"best_model_checkpoint": "outputs/checkpoint-298",
"epoch": 0.9987368421052631,
"eval_steps": 149,
"global_step": 593,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0016842105263157896,
"grad_norm": 0.6960500478744507,
"learning_rate": 0.001,
"loss": 2.2378,
"step": 1
},
{
"epoch": 0.003368421052631579,
"grad_norm": 1.7757582664489746,
"learning_rate": 0.001,
"loss": 2.3598,
"step": 2
},
{
"epoch": 0.0050526315789473685,
"grad_norm": 4.837254047393799,
"learning_rate": 0.001,
"loss": 3.0649,
"step": 3
},
{
"epoch": 0.006736842105263158,
"grad_norm": 1.8388794660568237,
"learning_rate": 0.001,
"loss": 2.4077,
"step": 4
},
{
"epoch": 0.008421052631578947,
"grad_norm": 2.6212971210479736,
"learning_rate": 0.001,
"loss": 1.8794,
"step": 5
},
{
"epoch": 0.010105263157894737,
"grad_norm": 3.2032198905944824,
"learning_rate": 0.001,
"loss": 2.2291,
"step": 6
},
{
"epoch": 0.011789473684210527,
"grad_norm": 0.9379774332046509,
"learning_rate": 0.001,
"loss": 1.9836,
"step": 7
},
{
"epoch": 0.013473684210526317,
"grad_norm": 0.8930391073226929,
"learning_rate": 0.001,
"loss": 1.9855,
"step": 8
},
{
"epoch": 0.015157894736842105,
"grad_norm": 1.121151089668274,
"learning_rate": 0.001,
"loss": 2.142,
"step": 9
},
{
"epoch": 0.016842105263157894,
"grad_norm": 1.3604674339294434,
"learning_rate": 0.001,
"loss": 2.0745,
"step": 10
},
{
"epoch": 0.018526315789473686,
"grad_norm": 0.9475807547569275,
"learning_rate": 0.001,
"loss": 2.2516,
"step": 11
},
{
"epoch": 0.020210526315789474,
"grad_norm": 1.56779146194458,
"learning_rate": 0.001,
"loss": 1.9924,
"step": 12
},
{
"epoch": 0.021894736842105262,
"grad_norm": 1.14510178565979,
"learning_rate": 0.001,
"loss": 1.8669,
"step": 13
},
{
"epoch": 0.023578947368421053,
"grad_norm": 0.9147089719772339,
"learning_rate": 0.001,
"loss": 2.1365,
"step": 14
},
{
"epoch": 0.02526315789473684,
"grad_norm": 0.7278650403022766,
"learning_rate": 0.001,
"loss": 2.2927,
"step": 15
},
{
"epoch": 0.026947368421052633,
"grad_norm": 0.6441658735275269,
"learning_rate": 0.001,
"loss": 2.1152,
"step": 16
},
{
"epoch": 0.02863157894736842,
"grad_norm": 0.6069326996803284,
"learning_rate": 0.001,
"loss": 1.8998,
"step": 17
},
{
"epoch": 0.03031578947368421,
"grad_norm": 0.7715803384780884,
"learning_rate": 0.001,
"loss": 2.3267,
"step": 18
},
{
"epoch": 0.032,
"grad_norm": 1.274883508682251,
"learning_rate": 0.001,
"loss": 1.9622,
"step": 19
},
{
"epoch": 0.03368421052631579,
"grad_norm": 1.315987467765808,
"learning_rate": 0.001,
"loss": 2.0188,
"step": 20
},
{
"epoch": 0.03536842105263158,
"grad_norm": 0.7619612216949463,
"learning_rate": 0.001,
"loss": 2.1692,
"step": 21
},
{
"epoch": 0.03705263157894737,
"grad_norm": 0.6206510066986084,
"learning_rate": 0.001,
"loss": 1.9139,
"step": 22
},
{
"epoch": 0.03873684210526316,
"grad_norm": 0.7554602026939392,
"learning_rate": 0.001,
"loss": 2.0588,
"step": 23
},
{
"epoch": 0.04042105263157895,
"grad_norm": 0.6345531344413757,
"learning_rate": 0.001,
"loss": 2.1671,
"step": 24
},
{
"epoch": 0.042105263157894736,
"grad_norm": 0.6695383191108704,
"learning_rate": 0.001,
"loss": 2.02,
"step": 25
},
{
"epoch": 0.043789473684210524,
"grad_norm": 0.4833696186542511,
"learning_rate": 0.001,
"loss": 1.75,
"step": 26
},
{
"epoch": 0.04547368421052632,
"grad_norm": 0.7931104302406311,
"learning_rate": 0.001,
"loss": 2.1626,
"step": 27
},
{
"epoch": 0.04715789473684211,
"grad_norm": 1.5443921089172363,
"learning_rate": 0.001,
"loss": 2.0443,
"step": 28
},
{
"epoch": 0.048842105263157895,
"grad_norm": 0.6693266034126282,
"learning_rate": 0.001,
"loss": 2.2165,
"step": 29
},
{
"epoch": 0.05052631578947368,
"grad_norm": 0.6431847810745239,
"learning_rate": 0.001,
"loss": 2.1791,
"step": 30
},
{
"epoch": 0.05221052631578947,
"grad_norm": 0.5706735253334045,
"learning_rate": 0.001,
"loss": 1.9472,
"step": 31
},
{
"epoch": 0.053894736842105266,
"grad_norm": 0.7617158889770508,
"learning_rate": 0.001,
"loss": 2.0268,
"step": 32
},
{
"epoch": 0.055578947368421054,
"grad_norm": 0.5798472762107849,
"learning_rate": 0.001,
"loss": 1.9278,
"step": 33
},
{
"epoch": 0.05726315789473684,
"grad_norm": 0.5660713315010071,
"learning_rate": 0.001,
"loss": 1.7519,
"step": 34
},
{
"epoch": 0.05894736842105263,
"grad_norm": 0.5779318809509277,
"learning_rate": 0.001,
"loss": 1.9023,
"step": 35
},
{
"epoch": 0.06063157894736842,
"grad_norm": 0.6591325998306274,
"learning_rate": 0.001,
"loss": 1.959,
"step": 36
},
{
"epoch": 0.06231578947368421,
"grad_norm": 0.6363794803619385,
"learning_rate": 0.001,
"loss": 2.1155,
"step": 37
},
{
"epoch": 0.064,
"grad_norm": 0.6779230833053589,
"learning_rate": 0.001,
"loss": 1.9465,
"step": 38
},
{
"epoch": 0.06568421052631579,
"grad_norm": 0.6995664238929749,
"learning_rate": 0.001,
"loss": 1.8616,
"step": 39
},
{
"epoch": 0.06736842105263158,
"grad_norm": 0.7718273997306824,
"learning_rate": 0.001,
"loss": 2.1503,
"step": 40
},
{
"epoch": 0.06905263157894737,
"grad_norm": 0.5334057807922363,
"learning_rate": 0.001,
"loss": 1.7283,
"step": 41
},
{
"epoch": 0.07073684210526315,
"grad_norm": 0.5298858880996704,
"learning_rate": 0.001,
"loss": 1.6779,
"step": 42
},
{
"epoch": 0.07242105263157894,
"grad_norm": 0.5175891518592834,
"learning_rate": 0.001,
"loss": 1.9119,
"step": 43
},
{
"epoch": 0.07410526315789474,
"grad_norm": 0.5781148076057434,
"learning_rate": 0.001,
"loss": 1.7144,
"step": 44
},
{
"epoch": 0.07578947368421053,
"grad_norm": 0.5868591666221619,
"learning_rate": 0.001,
"loss": 1.8802,
"step": 45
},
{
"epoch": 0.07747368421052632,
"grad_norm": 0.5802803635597229,
"learning_rate": 0.001,
"loss": 1.7823,
"step": 46
},
{
"epoch": 0.07915789473684211,
"grad_norm": 0.6214857697486877,
"learning_rate": 0.001,
"loss": 1.6589,
"step": 47
},
{
"epoch": 0.0808421052631579,
"grad_norm": 0.6045804619789124,
"learning_rate": 0.001,
"loss": 1.9772,
"step": 48
},
{
"epoch": 0.08252631578947368,
"grad_norm": 0.6322258114814758,
"learning_rate": 0.001,
"loss": 1.7932,
"step": 49
},
{
"epoch": 0.08421052631578947,
"grad_norm": 0.6137242317199707,
"learning_rate": 0.001,
"loss": 1.8022,
"step": 50
},
{
"epoch": 0.08589473684210526,
"grad_norm": 0.5677167773246765,
"learning_rate": 0.001,
"loss": 1.5019,
"step": 51
},
{
"epoch": 0.08757894736842105,
"grad_norm": 0.6881672143936157,
"learning_rate": 0.001,
"loss": 1.9834,
"step": 52
},
{
"epoch": 0.08926315789473684,
"grad_norm": 0.6887582540512085,
"learning_rate": 0.001,
"loss": 2.0563,
"step": 53
},
{
"epoch": 0.09094736842105264,
"grad_norm": 0.6267439723014832,
"learning_rate": 0.001,
"loss": 1.9473,
"step": 54
},
{
"epoch": 0.09263157894736843,
"grad_norm": 0.7325497269630432,
"learning_rate": 0.001,
"loss": 1.7903,
"step": 55
},
{
"epoch": 0.09431578947368421,
"grad_norm": 0.6531684994697571,
"learning_rate": 0.001,
"loss": 1.8948,
"step": 56
},
{
"epoch": 0.096,
"grad_norm": 0.6358041763305664,
"learning_rate": 0.001,
"loss": 1.7967,
"step": 57
},
{
"epoch": 0.09768421052631579,
"grad_norm": 0.6489672660827637,
"learning_rate": 0.001,
"loss": 1.9836,
"step": 58
},
{
"epoch": 0.09936842105263158,
"grad_norm": 0.6798167824745178,
"learning_rate": 0.001,
"loss": 1.4925,
"step": 59
},
{
"epoch": 0.10105263157894737,
"grad_norm": 0.71540367603302,
"learning_rate": 0.001,
"loss": 1.9803,
"step": 60
},
{
"epoch": 0.10273684210526315,
"grad_norm": 0.7388565540313721,
"learning_rate": 0.001,
"loss": 1.994,
"step": 61
},
{
"epoch": 0.10442105263157894,
"grad_norm": 0.5921775698661804,
"learning_rate": 0.001,
"loss": 1.7347,
"step": 62
},
{
"epoch": 0.10610526315789473,
"grad_norm": 0.6923938393592834,
"learning_rate": 0.001,
"loss": 1.8954,
"step": 63
},
{
"epoch": 0.10778947368421053,
"grad_norm": 0.6679465770721436,
"learning_rate": 0.001,
"loss": 1.6889,
"step": 64
},
{
"epoch": 0.10947368421052632,
"grad_norm": 0.6221023797988892,
"learning_rate": 0.001,
"loss": 1.8324,
"step": 65
},
{
"epoch": 0.11115789473684211,
"grad_norm": 0.6746177673339844,
"learning_rate": 0.001,
"loss": 1.822,
"step": 66
},
{
"epoch": 0.1128421052631579,
"grad_norm": 0.6581069231033325,
"learning_rate": 0.001,
"loss": 2.2108,
"step": 67
},
{
"epoch": 0.11452631578947368,
"grad_norm": 0.6342150568962097,
"learning_rate": 0.001,
"loss": 1.7536,
"step": 68
},
{
"epoch": 0.11621052631578947,
"grad_norm": 0.6652107834815979,
"learning_rate": 0.001,
"loss": 2.0814,
"step": 69
},
{
"epoch": 0.11789473684210526,
"grad_norm": 0.5661808848381042,
"learning_rate": 0.001,
"loss": 1.9419,
"step": 70
},
{
"epoch": 0.11957894736842105,
"grad_norm": 0.8789241313934326,
"learning_rate": 0.001,
"loss": 1.8391,
"step": 71
},
{
"epoch": 0.12126315789473684,
"grad_norm": 0.665008008480072,
"learning_rate": 0.001,
"loss": 1.9936,
"step": 72
},
{
"epoch": 0.12294736842105262,
"grad_norm": 0.647729218006134,
"learning_rate": 0.001,
"loss": 1.8883,
"step": 73
},
{
"epoch": 0.12463157894736843,
"grad_norm": 0.5845763087272644,
"learning_rate": 0.001,
"loss": 1.8779,
"step": 74
},
{
"epoch": 0.12631578947368421,
"grad_norm": 0.6005629897117615,
"learning_rate": 0.001,
"loss": 2.1395,
"step": 75
},
{
"epoch": 0.128,
"grad_norm": 0.570796012878418,
"learning_rate": 0.001,
"loss": 1.7652,
"step": 76
},
{
"epoch": 0.1296842105263158,
"grad_norm": 0.652999222278595,
"learning_rate": 0.001,
"loss": 1.9479,
"step": 77
},
{
"epoch": 0.13136842105263158,
"grad_norm": 0.7086900472640991,
"learning_rate": 0.001,
"loss": 1.924,
"step": 78
},
{
"epoch": 0.13305263157894737,
"grad_norm": 0.8962117433547974,
"learning_rate": 0.001,
"loss": 1.7471,
"step": 79
},
{
"epoch": 0.13473684210526315,
"grad_norm": 0.9083784222602844,
"learning_rate": 0.001,
"loss": 1.4415,
"step": 80
},
{
"epoch": 0.13642105263157894,
"grad_norm": 0.6662907600402832,
"learning_rate": 0.001,
"loss": 1.5885,
"step": 81
},
{
"epoch": 0.13810526315789473,
"grad_norm": 0.748068630695343,
"learning_rate": 0.001,
"loss": 1.9043,
"step": 82
},
{
"epoch": 0.13978947368421052,
"grad_norm": 0.653835117816925,
"learning_rate": 0.001,
"loss": 1.9271,
"step": 83
},
{
"epoch": 0.1414736842105263,
"grad_norm": 0.5937058925628662,
"learning_rate": 0.001,
"loss": 1.6577,
"step": 84
},
{
"epoch": 0.1431578947368421,
"grad_norm": 0.5573813319206238,
"learning_rate": 0.001,
"loss": 1.7685,
"step": 85
},
{
"epoch": 0.14484210526315788,
"grad_norm": 0.7234801054000854,
"learning_rate": 0.001,
"loss": 2.1049,
"step": 86
},
{
"epoch": 0.14652631578947367,
"grad_norm": 0.7858671545982361,
"learning_rate": 0.001,
"loss": 1.8385,
"step": 87
},
{
"epoch": 0.1482105263157895,
"grad_norm": 0.5881790518760681,
"learning_rate": 0.001,
"loss": 1.6881,
"step": 88
},
{
"epoch": 0.14989473684210528,
"grad_norm": 0.6036899089813232,
"learning_rate": 0.001,
"loss": 2.0763,
"step": 89
},
{
"epoch": 0.15157894736842106,
"grad_norm": 0.6678960919380188,
"learning_rate": 0.001,
"loss": 1.7332,
"step": 90
},
{
"epoch": 0.15326315789473685,
"grad_norm": 0.6993541717529297,
"learning_rate": 0.001,
"loss": 2.0437,
"step": 91
},
{
"epoch": 0.15494736842105264,
"grad_norm": 1.0041996240615845,
"learning_rate": 0.001,
"loss": 2.0819,
"step": 92
},
{
"epoch": 0.15663157894736843,
"grad_norm": 1.3755688667297363,
"learning_rate": 0.001,
"loss": 1.8761,
"step": 93
},
{
"epoch": 0.15831578947368422,
"grad_norm": 0.9399350881576538,
"learning_rate": 0.001,
"loss": 1.7925,
"step": 94
},
{
"epoch": 0.16,
"grad_norm": 0.6488239169120789,
"learning_rate": 0.001,
"loss": 2.009,
"step": 95
},
{
"epoch": 0.1616842105263158,
"grad_norm": 0.9083341360092163,
"learning_rate": 0.001,
"loss": 2.2331,
"step": 96
},
{
"epoch": 0.16336842105263158,
"grad_norm": 0.6239296197891235,
"learning_rate": 0.001,
"loss": 1.8789,
"step": 97
},
{
"epoch": 0.16505263157894737,
"grad_norm": 0.7653887867927551,
"learning_rate": 0.001,
"loss": 2.1016,
"step": 98
},
{
"epoch": 0.16673684210526316,
"grad_norm": 0.6791508793830872,
"learning_rate": 0.001,
"loss": 2.0147,
"step": 99
},
{
"epoch": 0.16842105263157894,
"grad_norm": 0.6757349967956543,
"learning_rate": 0.001,
"loss": 1.909,
"step": 100
},
{
"epoch": 0.17010526315789473,
"grad_norm": 0.5010210275650024,
"learning_rate": 0.001,
"loss": 2.0148,
"step": 101
},
{
"epoch": 0.17178947368421052,
"grad_norm": 0.6564686894416809,
"learning_rate": 0.001,
"loss": 1.707,
"step": 102
},
{
"epoch": 0.1734736842105263,
"grad_norm": 0.6926625370979309,
"learning_rate": 0.001,
"loss": 2.1313,
"step": 103
},
{
"epoch": 0.1751578947368421,
"grad_norm": 0.8134363293647766,
"learning_rate": 0.001,
"loss": 1.8948,
"step": 104
},
{
"epoch": 0.17684210526315788,
"grad_norm": 0.8722719550132751,
"learning_rate": 0.001,
"loss": 1.9564,
"step": 105
},
{
"epoch": 0.17852631578947367,
"grad_norm": 1.5459606647491455,
"learning_rate": 0.001,
"loss": 1.4568,
"step": 106
},
{
"epoch": 0.18021052631578946,
"grad_norm": 0.672356367111206,
"learning_rate": 0.001,
"loss": 2.2486,
"step": 107
},
{
"epoch": 0.18189473684210528,
"grad_norm": 0.6597303152084351,
"learning_rate": 0.001,
"loss": 2.1888,
"step": 108
},
{
"epoch": 0.18357894736842106,
"grad_norm": 0.6516699194908142,
"learning_rate": 0.001,
"loss": 1.7791,
"step": 109
},
{
"epoch": 0.18526315789473685,
"grad_norm": 0.6535261273384094,
"learning_rate": 0.001,
"loss": 1.5753,
"step": 110
},
{
"epoch": 0.18694736842105264,
"grad_norm": 0.5394155979156494,
"learning_rate": 0.001,
"loss": 1.7874,
"step": 111
},
{
"epoch": 0.18863157894736843,
"grad_norm": 0.6403316855430603,
"learning_rate": 0.001,
"loss": 1.8044,
"step": 112
},
{
"epoch": 0.19031578947368422,
"grad_norm": 0.6894748210906982,
"learning_rate": 0.001,
"loss": 1.7434,
"step": 113
},
{
"epoch": 0.192,
"grad_norm": 0.5362414717674255,
"learning_rate": 0.001,
"loss": 1.6198,
"step": 114
},
{
"epoch": 0.1936842105263158,
"grad_norm": 0.5218887329101562,
"learning_rate": 0.001,
"loss": 1.7941,
"step": 115
},
{
"epoch": 0.19536842105263158,
"grad_norm": 0.5951269865036011,
"learning_rate": 0.001,
"loss": 2.115,
"step": 116
},
{
"epoch": 0.19705263157894737,
"grad_norm": 1.0313245058059692,
"learning_rate": 0.001,
"loss": 1.9144,
"step": 117
},
{
"epoch": 0.19873684210526316,
"grad_norm": 0.6776890754699707,
"learning_rate": 0.001,
"loss": 1.6852,
"step": 118
},
{
"epoch": 0.20042105263157894,
"grad_norm": 0.5906718373298645,
"learning_rate": 0.001,
"loss": 1.7103,
"step": 119
},
{
"epoch": 0.20210526315789473,
"grad_norm": 0.6788285970687866,
"learning_rate": 0.001,
"loss": 2.1048,
"step": 120
},
{
"epoch": 0.20378947368421052,
"grad_norm": 0.7527502179145813,
"learning_rate": 0.001,
"loss": 1.8199,
"step": 121
},
{
"epoch": 0.2054736842105263,
"grad_norm": 0.5279136896133423,
"learning_rate": 0.001,
"loss": 1.5327,
"step": 122
},
{
"epoch": 0.2071578947368421,
"grad_norm": 0.7087485194206238,
"learning_rate": 0.001,
"loss": 1.8483,
"step": 123
},
{
"epoch": 0.20884210526315788,
"grad_norm": 0.7274911999702454,
"learning_rate": 0.001,
"loss": 2.4062,
"step": 124
},
{
"epoch": 0.21052631578947367,
"grad_norm": 0.5436732769012451,
"learning_rate": 0.001,
"loss": 1.7369,
"step": 125
},
{
"epoch": 0.21221052631578946,
"grad_norm": 0.5522803664207458,
"learning_rate": 0.001,
"loss": 1.8024,
"step": 126
},
{
"epoch": 0.21389473684210528,
"grad_norm": 0.7198563814163208,
"learning_rate": 0.001,
"loss": 2.2969,
"step": 127
},
{
"epoch": 0.21557894736842106,
"grad_norm": 0.6230013370513916,
"learning_rate": 0.001,
"loss": 1.8566,
"step": 128
},
{
"epoch": 0.21726315789473685,
"grad_norm": 0.5977436304092407,
"learning_rate": 0.001,
"loss": 1.339,
"step": 129
},
{
"epoch": 0.21894736842105264,
"grad_norm": 0.5400142669677734,
"learning_rate": 0.001,
"loss": 1.6346,
"step": 130
},
{
"epoch": 0.22063157894736843,
"grad_norm": 0.6537740230560303,
"learning_rate": 0.001,
"loss": 1.981,
"step": 131
},
{
"epoch": 0.22231578947368422,
"grad_norm": 0.6012418866157532,
"learning_rate": 0.001,
"loss": 1.9957,
"step": 132
},
{
"epoch": 0.224,
"grad_norm": 0.6363667845726013,
"learning_rate": 0.001,
"loss": 2.0906,
"step": 133
},
{
"epoch": 0.2256842105263158,
"grad_norm": 0.7009410262107849,
"learning_rate": 0.001,
"loss": 2.0259,
"step": 134
},
{
"epoch": 0.22736842105263158,
"grad_norm": 0.6076754331588745,
"learning_rate": 0.001,
"loss": 2.0623,
"step": 135
},
{
"epoch": 0.22905263157894737,
"grad_norm": 0.6430286169052124,
"learning_rate": 0.001,
"loss": 1.9965,
"step": 136
},
{
"epoch": 0.23073684210526316,
"grad_norm": 0.7743528485298157,
"learning_rate": 0.001,
"loss": 1.6476,
"step": 137
},
{
"epoch": 0.23242105263157894,
"grad_norm": 0.7490441203117371,
"learning_rate": 0.001,
"loss": 2.1016,
"step": 138
},
{
"epoch": 0.23410526315789473,
"grad_norm": 0.6852337121963501,
"learning_rate": 0.001,
"loss": 1.7251,
"step": 139
},
{
"epoch": 0.23578947368421052,
"grad_norm": 0.6012661457061768,
"learning_rate": 0.001,
"loss": 1.985,
"step": 140
},
{
"epoch": 0.2374736842105263,
"grad_norm": 0.48385104537010193,
"learning_rate": 0.001,
"loss": 1.7926,
"step": 141
},
{
"epoch": 0.2391578947368421,
"grad_norm": 0.5751200914382935,
"learning_rate": 0.001,
"loss": 1.8795,
"step": 142
},
{
"epoch": 0.24084210526315789,
"grad_norm": 0.571426510810852,
"learning_rate": 0.001,
"loss": 1.6457,
"step": 143
},
{
"epoch": 0.24252631578947367,
"grad_norm": 0.6982892751693726,
"learning_rate": 0.001,
"loss": 2.0313,
"step": 144
},
{
"epoch": 0.24421052631578946,
"grad_norm": 0.7380142211914062,
"learning_rate": 0.001,
"loss": 2.1306,
"step": 145
},
{
"epoch": 0.24589473684210525,
"grad_norm": 0.97590571641922,
"learning_rate": 0.001,
"loss": 1.9926,
"step": 146
},
{
"epoch": 0.24757894736842107,
"grad_norm": 0.8416200876235962,
"learning_rate": 0.001,
"loss": 1.733,
"step": 147
},
{
"epoch": 0.24926315789473685,
"grad_norm": 0.6639004945755005,
"learning_rate": 0.001,
"loss": 1.9836,
"step": 148
},
{
"epoch": 0.25094736842105264,
"grad_norm": 0.6488214135169983,
"learning_rate": 0.001,
"loss": 1.8941,
"step": 149
},
{
"epoch": 0.25094736842105264,
"eval_loss": 1.7599804401397705,
"eval_runtime": 0.1738,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 5.754,
"step": 149
},
{
"epoch": 0.25263157894736843,
"grad_norm": 0.524825930595398,
"learning_rate": 0.001,
"loss": 1.7767,
"step": 150
},
{
"epoch": 0.2543157894736842,
"grad_norm": 0.49492335319519043,
"learning_rate": 0.001,
"loss": 1.775,
"step": 151
},
{
"epoch": 0.256,
"grad_norm": 0.5911272168159485,
"learning_rate": 0.001,
"loss": 1.8286,
"step": 152
},
{
"epoch": 0.2576842105263158,
"grad_norm": 0.8157614469528198,
"learning_rate": 0.001,
"loss": 1.8913,
"step": 153
},
{
"epoch": 0.2593684210526316,
"grad_norm": 0.7529662847518921,
"learning_rate": 0.001,
"loss": 1.8988,
"step": 154
},
{
"epoch": 0.26105263157894737,
"grad_norm": 0.8185762763023376,
"learning_rate": 0.001,
"loss": 2.1685,
"step": 155
},
{
"epoch": 0.26273684210526316,
"grad_norm": 0.7138445377349854,
"learning_rate": 0.001,
"loss": 1.8507,
"step": 156
},
{
"epoch": 0.26442105263157895,
"grad_norm": 0.5665900707244873,
"learning_rate": 0.001,
"loss": 1.525,
"step": 157
},
{
"epoch": 0.26610526315789473,
"grad_norm": 0.6799633502960205,
"learning_rate": 0.001,
"loss": 1.9605,
"step": 158
},
{
"epoch": 0.2677894736842105,
"grad_norm": 0.6787411570549011,
"learning_rate": 0.001,
"loss": 1.6556,
"step": 159
},
{
"epoch": 0.2694736842105263,
"grad_norm": 0.8427496552467346,
"learning_rate": 0.001,
"loss": 1.8083,
"step": 160
},
{
"epoch": 0.2711578947368421,
"grad_norm": 0.6665315628051758,
"learning_rate": 0.001,
"loss": 1.966,
"step": 161
},
{
"epoch": 0.2728421052631579,
"grad_norm": 0.6209701895713806,
"learning_rate": 0.001,
"loss": 1.79,
"step": 162
},
{
"epoch": 0.2745263157894737,
"grad_norm": 0.5687562823295593,
"learning_rate": 0.001,
"loss": 1.779,
"step": 163
},
{
"epoch": 0.27621052631578946,
"grad_norm": 0.5852699279785156,
"learning_rate": 0.001,
"loss": 1.4817,
"step": 164
},
{
"epoch": 0.27789473684210525,
"grad_norm": 0.6601601839065552,
"learning_rate": 0.001,
"loss": 1.9279,
"step": 165
},
{
"epoch": 0.27957894736842104,
"grad_norm": 0.5629734992980957,
"learning_rate": 0.001,
"loss": 1.821,
"step": 166
},
{
"epoch": 0.2812631578947368,
"grad_norm": 0.7956101894378662,
"learning_rate": 0.001,
"loss": 1.9925,
"step": 167
},
{
"epoch": 0.2829473684210526,
"grad_norm": 0.7143905758857727,
"learning_rate": 0.001,
"loss": 2.0572,
"step": 168
},
{
"epoch": 0.2846315789473684,
"grad_norm": 0.7645180821418762,
"learning_rate": 0.001,
"loss": 1.9208,
"step": 169
},
{
"epoch": 0.2863157894736842,
"grad_norm": 0.7295411825180054,
"learning_rate": 0.001,
"loss": 1.962,
"step": 170
},
{
"epoch": 0.288,
"grad_norm": 0.7587769031524658,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 171
},
{
"epoch": 0.28968421052631577,
"grad_norm": 0.6111007332801819,
"learning_rate": 0.001,
"loss": 1.5688,
"step": 172
},
{
"epoch": 0.29136842105263155,
"grad_norm": 0.7311589121818542,
"learning_rate": 0.001,
"loss": 1.8835,
"step": 173
},
{
"epoch": 0.29305263157894734,
"grad_norm": 0.6812251210212708,
"learning_rate": 0.001,
"loss": 1.8754,
"step": 174
},
{
"epoch": 0.29473684210526313,
"grad_norm": 0.6704198718070984,
"learning_rate": 0.001,
"loss": 1.8445,
"step": 175
},
{
"epoch": 0.296421052631579,
"grad_norm": 0.7953410148620605,
"learning_rate": 0.001,
"loss": 2.0227,
"step": 176
},
{
"epoch": 0.29810526315789476,
"grad_norm": 0.8933955430984497,
"learning_rate": 0.001,
"loss": 1.9599,
"step": 177
},
{
"epoch": 0.29978947368421055,
"grad_norm": 0.7686247825622559,
"learning_rate": 0.001,
"loss": 1.8684,
"step": 178
},
{
"epoch": 0.30147368421052634,
"grad_norm": 0.6903300881385803,
"learning_rate": 0.001,
"loss": 1.9449,
"step": 179
},
{
"epoch": 0.3031578947368421,
"grad_norm": 0.6970056295394897,
"learning_rate": 0.001,
"loss": 1.6342,
"step": 180
},
{
"epoch": 0.3048421052631579,
"grad_norm": 0.5772702693939209,
"learning_rate": 0.001,
"loss": 1.7464,
"step": 181
},
{
"epoch": 0.3065263157894737,
"grad_norm": 0.6376874446868896,
"learning_rate": 0.001,
"loss": 1.82,
"step": 182
},
{
"epoch": 0.3082105263157895,
"grad_norm": 0.761457085609436,
"learning_rate": 0.001,
"loss": 1.7796,
"step": 183
},
{
"epoch": 0.3098947368421053,
"grad_norm": 0.6312285661697388,
"learning_rate": 0.001,
"loss": 2.0363,
"step": 184
},
{
"epoch": 0.31157894736842107,
"grad_norm": 0.8040784001350403,
"learning_rate": 0.001,
"loss": 2.0369,
"step": 185
},
{
"epoch": 0.31326315789473685,
"grad_norm": 0.7520210146903992,
"learning_rate": 0.001,
"loss": 2.1518,
"step": 186
},
{
"epoch": 0.31494736842105264,
"grad_norm": 0.6293883919715881,
"learning_rate": 0.001,
"loss": 1.9187,
"step": 187
},
{
"epoch": 0.31663157894736843,
"grad_norm": 0.7219449877738953,
"learning_rate": 0.001,
"loss": 1.5069,
"step": 188
},
{
"epoch": 0.3183157894736842,
"grad_norm": 0.8080244660377502,
"learning_rate": 0.001,
"loss": 1.6169,
"step": 189
},
{
"epoch": 0.32,
"grad_norm": 0.8044946193695068,
"learning_rate": 0.001,
"loss": 1.8206,
"step": 190
},
{
"epoch": 0.3216842105263158,
"grad_norm": 0.894588828086853,
"learning_rate": 0.001,
"loss": 2.0623,
"step": 191
},
{
"epoch": 0.3233684210526316,
"grad_norm": 0.6865862607955933,
"learning_rate": 0.001,
"loss": 1.7629,
"step": 192
},
{
"epoch": 0.32505263157894737,
"grad_norm": 0.9992401003837585,
"learning_rate": 0.001,
"loss": 2.2471,
"step": 193
},
{
"epoch": 0.32673684210526316,
"grad_norm": 0.8792619705200195,
"learning_rate": 0.001,
"loss": 2.0458,
"step": 194
},
{
"epoch": 0.32842105263157895,
"grad_norm": 0.8508814573287964,
"learning_rate": 0.001,
"loss": 1.8746,
"step": 195
},
{
"epoch": 0.33010526315789473,
"grad_norm": 0.6977102756500244,
"learning_rate": 0.001,
"loss": 2.0411,
"step": 196
},
{
"epoch": 0.3317894736842105,
"grad_norm": 0.8430894017219543,
"learning_rate": 0.001,
"loss": 2.0066,
"step": 197
},
{
"epoch": 0.3334736842105263,
"grad_norm": 0.8048614859580994,
"learning_rate": 0.001,
"loss": 1.9879,
"step": 198
},
{
"epoch": 0.3351578947368421,
"grad_norm": 0.8604184985160828,
"learning_rate": 0.001,
"loss": 2.0952,
"step": 199
},
{
"epoch": 0.3368421052631579,
"grad_norm": 1.0472347736358643,
"learning_rate": 0.001,
"loss": 1.8939,
"step": 200
},
{
"epoch": 0.3385263157894737,
"grad_norm": 0.761587381362915,
"learning_rate": 0.001,
"loss": 1.9897,
"step": 201
},
{
"epoch": 0.34021052631578946,
"grad_norm": 0.7086905837059021,
"learning_rate": 0.001,
"loss": 1.8068,
"step": 202
},
{
"epoch": 0.34189473684210525,
"grad_norm": 0.8213825225830078,
"learning_rate": 0.001,
"loss": 1.682,
"step": 203
},
{
"epoch": 0.34357894736842104,
"grad_norm": 0.8660598397254944,
"learning_rate": 0.001,
"loss": 2.0042,
"step": 204
},
{
"epoch": 0.3452631578947368,
"grad_norm": 0.9913591742515564,
"learning_rate": 0.001,
"loss": 1.9211,
"step": 205
},
{
"epoch": 0.3469473684210526,
"grad_norm": 0.7640036940574646,
"learning_rate": 0.001,
"loss": 2.0904,
"step": 206
},
{
"epoch": 0.3486315789473684,
"grad_norm": 0.7359378337860107,
"learning_rate": 0.001,
"loss": 1.9424,
"step": 207
},
{
"epoch": 0.3503157894736842,
"grad_norm": 0.7246221303939819,
"learning_rate": 0.001,
"loss": 1.9887,
"step": 208
},
{
"epoch": 0.352,
"grad_norm": 0.8169429302215576,
"learning_rate": 0.001,
"loss": 1.8335,
"step": 209
},
{
"epoch": 0.35368421052631577,
"grad_norm": 0.903678834438324,
"learning_rate": 0.001,
"loss": 1.6703,
"step": 210
},
{
"epoch": 0.35536842105263156,
"grad_norm": 0.7328379154205322,
"learning_rate": 0.001,
"loss": 2.1565,
"step": 211
},
{
"epoch": 0.35705263157894734,
"grad_norm": 0.8003093004226685,
"learning_rate": 0.001,
"loss": 1.7172,
"step": 212
},
{
"epoch": 0.35873684210526313,
"grad_norm": 0.7532063722610474,
"learning_rate": 0.001,
"loss": 2.0264,
"step": 213
},
{
"epoch": 0.3604210526315789,
"grad_norm": 0.7619852423667908,
"learning_rate": 0.001,
"loss": 1.7766,
"step": 214
},
{
"epoch": 0.36210526315789476,
"grad_norm": 0.7145585417747498,
"learning_rate": 0.001,
"loss": 1.8829,
"step": 215
},
{
"epoch": 0.36378947368421055,
"grad_norm": 0.739275336265564,
"learning_rate": 0.001,
"loss": 1.6963,
"step": 216
},
{
"epoch": 0.36547368421052634,
"grad_norm": 0.8174360990524292,
"learning_rate": 0.001,
"loss": 2.028,
"step": 217
},
{
"epoch": 0.3671578947368421,
"grad_norm": 0.7873148322105408,
"learning_rate": 0.001,
"loss": 1.9912,
"step": 218
},
{
"epoch": 0.3688421052631579,
"grad_norm": 0.7683485746383667,
"learning_rate": 0.001,
"loss": 2.0106,
"step": 219
},
{
"epoch": 0.3705263157894737,
"grad_norm": 0.841464102268219,
"learning_rate": 0.001,
"loss": 1.3909,
"step": 220
},
{
"epoch": 0.3722105263157895,
"grad_norm": 0.9224113821983337,
"learning_rate": 0.001,
"loss": 2.0642,
"step": 221
},
{
"epoch": 0.3738947368421053,
"grad_norm": 1.3310387134552002,
"learning_rate": 0.001,
"loss": 2.0075,
"step": 222
},
{
"epoch": 0.37557894736842107,
"grad_norm": 0.8936915397644043,
"learning_rate": 0.001,
"loss": 1.8838,
"step": 223
},
{
"epoch": 0.37726315789473686,
"grad_norm": 0.7084046602249146,
"learning_rate": 0.001,
"loss": 2.0105,
"step": 224
},
{
"epoch": 0.37894736842105264,
"grad_norm": 0.802139401435852,
"learning_rate": 0.001,
"loss": 2.1188,
"step": 225
},
{
"epoch": 0.38063157894736843,
"grad_norm": 0.8018360137939453,
"learning_rate": 0.001,
"loss": 1.8581,
"step": 226
},
{
"epoch": 0.3823157894736842,
"grad_norm": 0.8070486187934875,
"learning_rate": 0.001,
"loss": 1.9121,
"step": 227
},
{
"epoch": 0.384,
"grad_norm": 0.7557722330093384,
"learning_rate": 0.001,
"loss": 1.8515,
"step": 228
},
{
"epoch": 0.3856842105263158,
"grad_norm": 0.8111100196838379,
"learning_rate": 0.001,
"loss": 2.0789,
"step": 229
},
{
"epoch": 0.3873684210526316,
"grad_norm": 0.9642356038093567,
"learning_rate": 0.001,
"loss": 2.2856,
"step": 230
},
{
"epoch": 0.38905263157894737,
"grad_norm": 0.9470245242118835,
"learning_rate": 0.001,
"loss": 2.0114,
"step": 231
},
{
"epoch": 0.39073684210526316,
"grad_norm": 0.8576509952545166,
"learning_rate": 0.001,
"loss": 1.8915,
"step": 232
},
{
"epoch": 0.39242105263157895,
"grad_norm": 0.8524518013000488,
"learning_rate": 0.001,
"loss": 1.9937,
"step": 233
},
{
"epoch": 0.39410526315789474,
"grad_norm": 1.523067831993103,
"learning_rate": 0.001,
"loss": 1.641,
"step": 234
},
{
"epoch": 0.3957894736842105,
"grad_norm": 0.9369080066680908,
"learning_rate": 0.001,
"loss": 2.0977,
"step": 235
},
{
"epoch": 0.3974736842105263,
"grad_norm": 0.8704274296760559,
"learning_rate": 0.001,
"loss": 2.0126,
"step": 236
},
{
"epoch": 0.3991578947368421,
"grad_norm": 0.8420674800872803,
"learning_rate": 0.001,
"loss": 1.9577,
"step": 237
},
{
"epoch": 0.4008421052631579,
"grad_norm": 0.7344264388084412,
"learning_rate": 0.001,
"loss": 1.8681,
"step": 238
},
{
"epoch": 0.4025263157894737,
"grad_norm": 0.7144782543182373,
"learning_rate": 0.001,
"loss": 1.9696,
"step": 239
},
{
"epoch": 0.40421052631578946,
"grad_norm": 0.8455988168716431,
"learning_rate": 0.001,
"loss": 1.7568,
"step": 240
},
{
"epoch": 0.40589473684210525,
"grad_norm": 0.807806134223938,
"learning_rate": 0.001,
"loss": 2.1119,
"step": 241
},
{
"epoch": 0.40757894736842104,
"grad_norm": 0.8274264335632324,
"learning_rate": 0.001,
"loss": 1.9695,
"step": 242
},
{
"epoch": 0.40926315789473683,
"grad_norm": 0.9100606441497803,
"learning_rate": 0.001,
"loss": 1.9766,
"step": 243
},
{
"epoch": 0.4109473684210526,
"grad_norm": 1.1465590000152588,
"learning_rate": 0.001,
"loss": 1.8377,
"step": 244
},
{
"epoch": 0.4126315789473684,
"grad_norm": 0.7355701327323914,
"learning_rate": 0.001,
"loss": 1.3323,
"step": 245
},
{
"epoch": 0.4143157894736842,
"grad_norm": 0.8275692462921143,
"learning_rate": 0.001,
"loss": 1.9701,
"step": 246
},
{
"epoch": 0.416,
"grad_norm": 0.848210334777832,
"learning_rate": 0.001,
"loss": 2.0912,
"step": 247
},
{
"epoch": 0.41768421052631577,
"grad_norm": 0.8262030482292175,
"learning_rate": 0.001,
"loss": 2.115,
"step": 248
},
{
"epoch": 0.41936842105263156,
"grad_norm": 0.6998792886734009,
"learning_rate": 0.001,
"loss": 1.8737,
"step": 249
},
{
"epoch": 0.42105263157894735,
"grad_norm": 0.8081846237182617,
"learning_rate": 0.001,
"loss": 2.2837,
"step": 250
},
{
"epoch": 0.42273684210526313,
"grad_norm": 0.8310023546218872,
"learning_rate": 0.001,
"loss": 2.2355,
"step": 251
},
{
"epoch": 0.4244210526315789,
"grad_norm": 1.157334804534912,
"learning_rate": 0.001,
"loss": 2.3762,
"step": 252
},
{
"epoch": 0.4261052631578947,
"grad_norm": 0.7893511056900024,
"learning_rate": 0.001,
"loss": 1.8737,
"step": 253
},
{
"epoch": 0.42778947368421055,
"grad_norm": 0.959355354309082,
"learning_rate": 0.001,
"loss": 2.0047,
"step": 254
},
{
"epoch": 0.42947368421052634,
"grad_norm": 0.8904256224632263,
"learning_rate": 0.001,
"loss": 1.8809,
"step": 255
},
{
"epoch": 0.43115789473684213,
"grad_norm": 0.9054950475692749,
"learning_rate": 0.001,
"loss": 2.3487,
"step": 256
},
{
"epoch": 0.4328421052631579,
"grad_norm": 0.8389487862586975,
"learning_rate": 0.001,
"loss": 2.0993,
"step": 257
},
{
"epoch": 0.4345263157894737,
"grad_norm": 1.0516859292984009,
"learning_rate": 0.001,
"loss": 1.9482,
"step": 258
},
{
"epoch": 0.4362105263157895,
"grad_norm": 1.0936013460159302,
"learning_rate": 0.001,
"loss": 2.2888,
"step": 259
},
{
"epoch": 0.4378947368421053,
"grad_norm": 0.894350528717041,
"learning_rate": 0.001,
"loss": 1.9703,
"step": 260
},
{
"epoch": 0.43957894736842107,
"grad_norm": 0.8147197961807251,
"learning_rate": 0.001,
"loss": 1.8964,
"step": 261
},
{
"epoch": 0.44126315789473686,
"grad_norm": 0.6683039665222168,
"learning_rate": 0.001,
"loss": 1.8701,
"step": 262
},
{
"epoch": 0.44294736842105265,
"grad_norm": 0.83613121509552,
"learning_rate": 0.001,
"loss": 2.3627,
"step": 263
},
{
"epoch": 0.44463157894736843,
"grad_norm": 0.724908173084259,
"learning_rate": 0.001,
"loss": 1.8411,
"step": 264
},
{
"epoch": 0.4463157894736842,
"grad_norm": 0.7576204538345337,
"learning_rate": 0.001,
"loss": 2.1275,
"step": 265
},
{
"epoch": 0.448,
"grad_norm": 0.7902230620384216,
"learning_rate": 0.001,
"loss": 1.663,
"step": 266
},
{
"epoch": 0.4496842105263158,
"grad_norm": 1.5043684244155884,
"learning_rate": 0.001,
"loss": 2.1615,
"step": 267
},
{
"epoch": 0.4513684210526316,
"grad_norm": 0.8250028491020203,
"learning_rate": 0.001,
"loss": 1.8787,
"step": 268
},
{
"epoch": 0.4530526315789474,
"grad_norm": 0.7849893569946289,
"learning_rate": 0.001,
"loss": 2.0168,
"step": 269
},
{
"epoch": 0.45473684210526316,
"grad_norm": 0.8021153807640076,
"learning_rate": 0.001,
"loss": 2.2486,
"step": 270
},
{
"epoch": 0.45642105263157895,
"grad_norm": 0.7869856953620911,
"learning_rate": 0.001,
"loss": 1.5522,
"step": 271
},
{
"epoch": 0.45810526315789474,
"grad_norm": 0.813165009021759,
"learning_rate": 0.001,
"loss": 2.0801,
"step": 272
},
{
"epoch": 0.4597894736842105,
"grad_norm": 0.8223312497138977,
"learning_rate": 0.001,
"loss": 1.9111,
"step": 273
},
{
"epoch": 0.4614736842105263,
"grad_norm": 0.8650989532470703,
"learning_rate": 0.001,
"loss": 1.716,
"step": 274
},
{
"epoch": 0.4631578947368421,
"grad_norm": 0.7596947550773621,
"learning_rate": 0.001,
"loss": 1.9046,
"step": 275
},
{
"epoch": 0.4648421052631579,
"grad_norm": 0.7211440801620483,
"learning_rate": 0.001,
"loss": 1.7714,
"step": 276
},
{
"epoch": 0.4665263157894737,
"grad_norm": 1.0673142671585083,
"learning_rate": 0.001,
"loss": 2.1321,
"step": 277
},
{
"epoch": 0.46821052631578947,
"grad_norm": 0.7947107553482056,
"learning_rate": 0.001,
"loss": 1.9446,
"step": 278
},
{
"epoch": 0.46989473684210525,
"grad_norm": 0.8121020197868347,
"learning_rate": 0.001,
"loss": 2.217,
"step": 279
},
{
"epoch": 0.47157894736842104,
"grad_norm": 0.7495191097259521,
"learning_rate": 0.001,
"loss": 1.891,
"step": 280
},
{
"epoch": 0.47326315789473683,
"grad_norm": 0.7859931588172913,
"learning_rate": 0.001,
"loss": 1.5517,
"step": 281
},
{
"epoch": 0.4749473684210526,
"grad_norm": 0.8961056470870972,
"learning_rate": 0.001,
"loss": 2.0886,
"step": 282
},
{
"epoch": 0.4766315789473684,
"grad_norm": 0.7971674799919128,
"learning_rate": 0.001,
"loss": 1.8596,
"step": 283
},
{
"epoch": 0.4783157894736842,
"grad_norm": 0.881367564201355,
"learning_rate": 0.001,
"loss": 1.9999,
"step": 284
},
{
"epoch": 0.48,
"grad_norm": 0.883185863494873,
"learning_rate": 0.001,
"loss": 2.0156,
"step": 285
},
{
"epoch": 0.48168421052631577,
"grad_norm": 0.8560335636138916,
"learning_rate": 0.001,
"loss": 2.0237,
"step": 286
},
{
"epoch": 0.48336842105263156,
"grad_norm": 1.038077712059021,
"learning_rate": 0.001,
"loss": 1.6664,
"step": 287
},
{
"epoch": 0.48505263157894735,
"grad_norm": 0.7434845566749573,
"learning_rate": 0.001,
"loss": 1.9518,
"step": 288
},
{
"epoch": 0.48673684210526313,
"grad_norm": 1.099915862083435,
"learning_rate": 0.001,
"loss": 2.1582,
"step": 289
},
{
"epoch": 0.4884210526315789,
"grad_norm": 0.7814631462097168,
"learning_rate": 0.001,
"loss": 1.7189,
"step": 290
},
{
"epoch": 0.4901052631578947,
"grad_norm": 0.9618262052536011,
"learning_rate": 0.001,
"loss": 2.1185,
"step": 291
},
{
"epoch": 0.4917894736842105,
"grad_norm": 0.7547399401664734,
"learning_rate": 0.001,
"loss": 1.8551,
"step": 292
},
{
"epoch": 0.49347368421052634,
"grad_norm": 0.891696035861969,
"learning_rate": 0.001,
"loss": 2.1148,
"step": 293
},
{
"epoch": 0.49515789473684213,
"grad_norm": 0.9156106114387512,
"learning_rate": 0.001,
"loss": 1.829,
"step": 294
},
{
"epoch": 0.4968421052631579,
"grad_norm": 0.8770383596420288,
"learning_rate": 0.001,
"loss": 1.9336,
"step": 295
},
{
"epoch": 0.4985263157894737,
"grad_norm": 0.7889037132263184,
"learning_rate": 0.001,
"loss": 1.7122,
"step": 296
},
{
"epoch": 0.5002105263157894,
"grad_norm": 1.0132378339767456,
"learning_rate": 0.001,
"loss": 2.0484,
"step": 297
},
{
"epoch": 0.5018947368421053,
"grad_norm": 0.852583110332489,
"learning_rate": 0.001,
"loss": 1.9974,
"step": 298
},
{
"epoch": 0.5018947368421053,
"eval_loss": 1.6337618827819824,
"eval_runtime": 0.0834,
"eval_samples_per_second": 11.984,
"eval_steps_per_second": 11.984,
"step": 298
},
{
"epoch": 0.503578947368421,
"grad_norm": 1.0435866117477417,
"learning_rate": 0.001,
"loss": 2.105,
"step": 299
},
{
"epoch": 0.5052631578947369,
"grad_norm": 0.754615843296051,
"learning_rate": 0.001,
"loss": 2.0089,
"step": 300
},
{
"epoch": 0.5069473684210526,
"grad_norm": 1.012373924255371,
"learning_rate": 0.001,
"loss": 2.3203,
"step": 301
},
{
"epoch": 0.5086315789473684,
"grad_norm": 0.7808589935302734,
"learning_rate": 0.001,
"loss": 2.1087,
"step": 302
},
{
"epoch": 0.5103157894736842,
"grad_norm": 0.8035853505134583,
"learning_rate": 0.001,
"loss": 2.1473,
"step": 303
},
{
"epoch": 0.512,
"grad_norm": 0.7854329943656921,
"learning_rate": 0.001,
"loss": 1.9042,
"step": 304
},
{
"epoch": 0.5136842105263157,
"grad_norm": 0.8837404251098633,
"learning_rate": 0.001,
"loss": 1.6176,
"step": 305
},
{
"epoch": 0.5153684210526316,
"grad_norm": 0.9439155459403992,
"learning_rate": 0.001,
"loss": 2.1619,
"step": 306
},
{
"epoch": 0.5170526315789473,
"grad_norm": 0.836586058139801,
"learning_rate": 0.001,
"loss": 1.9484,
"step": 307
},
{
"epoch": 0.5187368421052632,
"grad_norm": 0.8734055161476135,
"learning_rate": 0.001,
"loss": 2.0695,
"step": 308
},
{
"epoch": 0.5204210526315789,
"grad_norm": 0.8716776967048645,
"learning_rate": 0.001,
"loss": 2.1273,
"step": 309
},
{
"epoch": 0.5221052631578947,
"grad_norm": 0.9540092349052429,
"learning_rate": 0.001,
"loss": 1.8999,
"step": 310
},
{
"epoch": 0.5237894736842105,
"grad_norm": 1.1694831848144531,
"learning_rate": 0.001,
"loss": 1.728,
"step": 311
},
{
"epoch": 0.5254736842105263,
"grad_norm": 0.7269738912582397,
"learning_rate": 0.001,
"loss": 2.0951,
"step": 312
},
{
"epoch": 0.5271578947368422,
"grad_norm": 0.7646914720535278,
"learning_rate": 0.001,
"loss": 1.8231,
"step": 313
},
{
"epoch": 0.5288421052631579,
"grad_norm": 0.8613254427909851,
"learning_rate": 0.001,
"loss": 1.9105,
"step": 314
},
{
"epoch": 0.5305263157894737,
"grad_norm": 1.0191853046417236,
"learning_rate": 0.001,
"loss": 1.7064,
"step": 315
},
{
"epoch": 0.5322105263157895,
"grad_norm": 1.2197155952453613,
"learning_rate": 0.001,
"loss": 1.7123,
"step": 316
},
{
"epoch": 0.5338947368421053,
"grad_norm": 0.818133533000946,
"learning_rate": 0.001,
"loss": 1.7865,
"step": 317
},
{
"epoch": 0.535578947368421,
"grad_norm": 0.8760883808135986,
"learning_rate": 0.001,
"loss": 2.1209,
"step": 318
},
{
"epoch": 0.5372631578947369,
"grad_norm": 1.0778782367706299,
"learning_rate": 0.001,
"loss": 2.0902,
"step": 319
},
{
"epoch": 0.5389473684210526,
"grad_norm": 0.8181326985359192,
"learning_rate": 0.001,
"loss": 1.9372,
"step": 320
},
{
"epoch": 0.5406315789473685,
"grad_norm": 0.9272657036781311,
"learning_rate": 0.001,
"loss": 2.0478,
"step": 321
},
{
"epoch": 0.5423157894736842,
"grad_norm": 0.9218736290931702,
"learning_rate": 0.001,
"loss": 2.108,
"step": 322
},
{
"epoch": 0.544,
"grad_norm": 1.0985972881317139,
"learning_rate": 0.001,
"loss": 2.0267,
"step": 323
},
{
"epoch": 0.5456842105263158,
"grad_norm": 0.8310480713844299,
"learning_rate": 0.001,
"loss": 1.7772,
"step": 324
},
{
"epoch": 0.5473684210526316,
"grad_norm": 0.8774259090423584,
"learning_rate": 0.001,
"loss": 2.0248,
"step": 325
},
{
"epoch": 0.5490526315789473,
"grad_norm": 1.0681616067886353,
"learning_rate": 0.001,
"loss": 2.2355,
"step": 326
},
{
"epoch": 0.5507368421052632,
"grad_norm": 0.9428539872169495,
"learning_rate": 0.001,
"loss": 1.9988,
"step": 327
},
{
"epoch": 0.5524210526315789,
"grad_norm": 1.0054833889007568,
"learning_rate": 0.001,
"loss": 1.9063,
"step": 328
},
{
"epoch": 0.5541052631578948,
"grad_norm": 0.8005337715148926,
"learning_rate": 0.001,
"loss": 2.1752,
"step": 329
},
{
"epoch": 0.5557894736842105,
"grad_norm": 1.109134554862976,
"learning_rate": 0.001,
"loss": 2.3235,
"step": 330
},
{
"epoch": 0.5574736842105263,
"grad_norm": 0.9584336280822754,
"learning_rate": 0.001,
"loss": 1.7009,
"step": 331
},
{
"epoch": 0.5591578947368421,
"grad_norm": 1.2622302770614624,
"learning_rate": 0.001,
"loss": 2.0998,
"step": 332
},
{
"epoch": 0.5608421052631579,
"grad_norm": 0.92564457654953,
"learning_rate": 0.001,
"loss": 1.7039,
"step": 333
},
{
"epoch": 0.5625263157894737,
"grad_norm": 0.7569521069526672,
"learning_rate": 0.001,
"loss": 1.7963,
"step": 334
},
{
"epoch": 0.5642105263157895,
"grad_norm": 0.7915797233581543,
"learning_rate": 0.001,
"loss": 1.645,
"step": 335
},
{
"epoch": 0.5658947368421052,
"grad_norm": 0.7300320863723755,
"learning_rate": 0.001,
"loss": 1.7476,
"step": 336
},
{
"epoch": 0.5675789473684211,
"grad_norm": 1.1384440660476685,
"learning_rate": 0.001,
"loss": 2.1937,
"step": 337
},
{
"epoch": 0.5692631578947368,
"grad_norm": 0.8770859241485596,
"learning_rate": 0.001,
"loss": 1.9664,
"step": 338
},
{
"epoch": 0.5709473684210526,
"grad_norm": 0.9081368446350098,
"learning_rate": 0.001,
"loss": 1.4632,
"step": 339
},
{
"epoch": 0.5726315789473684,
"grad_norm": 0.8865834474563599,
"learning_rate": 0.001,
"loss": 1.7578,
"step": 340
},
{
"epoch": 0.5743157894736842,
"grad_norm": 0.8756502866744995,
"learning_rate": 0.001,
"loss": 1.9929,
"step": 341
},
{
"epoch": 0.576,
"grad_norm": 0.8333286643028259,
"learning_rate": 0.001,
"loss": 2.3068,
"step": 342
},
{
"epoch": 0.5776842105263158,
"grad_norm": 0.8217945098876953,
"learning_rate": 0.001,
"loss": 1.9818,
"step": 343
},
{
"epoch": 0.5793684210526315,
"grad_norm": 0.8414101004600525,
"learning_rate": 0.001,
"loss": 2.0111,
"step": 344
},
{
"epoch": 0.5810526315789474,
"grad_norm": 0.9645239114761353,
"learning_rate": 0.001,
"loss": 2.2026,
"step": 345
},
{
"epoch": 0.5827368421052631,
"grad_norm": 0.9366424083709717,
"learning_rate": 0.001,
"loss": 2.1754,
"step": 346
},
{
"epoch": 0.584421052631579,
"grad_norm": 0.839468240737915,
"learning_rate": 0.001,
"loss": 1.8966,
"step": 347
},
{
"epoch": 0.5861052631578947,
"grad_norm": 0.9215678572654724,
"learning_rate": 0.001,
"loss": 2.1501,
"step": 348
},
{
"epoch": 0.5877894736842105,
"grad_norm": 1.0060967206954956,
"learning_rate": 0.001,
"loss": 1.9594,
"step": 349
},
{
"epoch": 0.5894736842105263,
"grad_norm": 0.9866886734962463,
"learning_rate": 0.001,
"loss": 2.0878,
"step": 350
},
{
"epoch": 0.5911578947368421,
"grad_norm": 1.0554858446121216,
"learning_rate": 0.001,
"loss": 1.7109,
"step": 351
},
{
"epoch": 0.592842105263158,
"grad_norm": 0.9574116468429565,
"learning_rate": 0.001,
"loss": 2.1836,
"step": 352
},
{
"epoch": 0.5945263157894737,
"grad_norm": 0.9625939726829529,
"learning_rate": 0.001,
"loss": 2.0379,
"step": 353
},
{
"epoch": 0.5962105263157895,
"grad_norm": 0.9140836000442505,
"learning_rate": 0.001,
"loss": 2.0564,
"step": 354
},
{
"epoch": 0.5978947368421053,
"grad_norm": 0.9520573616027832,
"learning_rate": 0.001,
"loss": 1.9383,
"step": 355
},
{
"epoch": 0.5995789473684211,
"grad_norm": 0.875503659248352,
"learning_rate": 0.001,
"loss": 1.6936,
"step": 356
},
{
"epoch": 0.6012631578947368,
"grad_norm": 1.461020827293396,
"learning_rate": 0.001,
"loss": 2.2684,
"step": 357
},
{
"epoch": 0.6029473684210527,
"grad_norm": 0.8192405700683594,
"learning_rate": 0.001,
"loss": 1.8995,
"step": 358
},
{
"epoch": 0.6046315789473684,
"grad_norm": 1.4530872106552124,
"learning_rate": 0.001,
"loss": 1.8539,
"step": 359
},
{
"epoch": 0.6063157894736843,
"grad_norm": 0.959186315536499,
"learning_rate": 0.001,
"loss": 2.0851,
"step": 360
},
{
"epoch": 0.608,
"grad_norm": 0.8276315331459045,
"learning_rate": 0.001,
"loss": 1.9521,
"step": 361
},
{
"epoch": 0.6096842105263158,
"grad_norm": 1.2478163242340088,
"learning_rate": 0.001,
"loss": 1.9309,
"step": 362
},
{
"epoch": 0.6113684210526316,
"grad_norm": 1.1320995092391968,
"learning_rate": 0.001,
"loss": 1.9807,
"step": 363
},
{
"epoch": 0.6130526315789474,
"grad_norm": 0.9767136573791504,
"learning_rate": 0.001,
"loss": 1.9802,
"step": 364
},
{
"epoch": 0.6147368421052631,
"grad_norm": 0.8936948776245117,
"learning_rate": 0.001,
"loss": 1.9986,
"step": 365
},
{
"epoch": 0.616421052631579,
"grad_norm": 0.7911234498023987,
"learning_rate": 0.001,
"loss": 2.0896,
"step": 366
},
{
"epoch": 0.6181052631578947,
"grad_norm": 0.7824344635009766,
"learning_rate": 0.001,
"loss": 1.4767,
"step": 367
},
{
"epoch": 0.6197894736842106,
"grad_norm": 0.9858822822570801,
"learning_rate": 0.001,
"loss": 1.9758,
"step": 368
},
{
"epoch": 0.6214736842105263,
"grad_norm": 0.942699670791626,
"learning_rate": 0.001,
"loss": 1.9038,
"step": 369
},
{
"epoch": 0.6231578947368421,
"grad_norm": 1.0846315622329712,
"learning_rate": 0.001,
"loss": 1.8084,
"step": 370
},
{
"epoch": 0.6248421052631579,
"grad_norm": 0.9172139167785645,
"learning_rate": 0.001,
"loss": 1.8795,
"step": 371
},
{
"epoch": 0.6265263157894737,
"grad_norm": 0.8866816163063049,
"learning_rate": 0.001,
"loss": 1.8835,
"step": 372
},
{
"epoch": 0.6282105263157894,
"grad_norm": 0.8923367261886597,
"learning_rate": 0.001,
"loss": 2.1602,
"step": 373
},
{
"epoch": 0.6298947368421053,
"grad_norm": 0.9485911130905151,
"learning_rate": 0.001,
"loss": 2.0832,
"step": 374
},
{
"epoch": 0.631578947368421,
"grad_norm": 1.026877999305725,
"learning_rate": 0.001,
"loss": 2.283,
"step": 375
},
{
"epoch": 0.6332631578947369,
"grad_norm": 0.9710808396339417,
"learning_rate": 0.001,
"loss": 1.6655,
"step": 376
},
{
"epoch": 0.6349473684210526,
"grad_norm": 1.1433035135269165,
"learning_rate": 0.001,
"loss": 1.9597,
"step": 377
},
{
"epoch": 0.6366315789473684,
"grad_norm": 0.9025890827178955,
"learning_rate": 0.001,
"loss": 2.0539,
"step": 378
},
{
"epoch": 0.6383157894736842,
"grad_norm": 0.9245177507400513,
"learning_rate": 0.001,
"loss": 1.7705,
"step": 379
},
{
"epoch": 0.64,
"grad_norm": 0.932959258556366,
"learning_rate": 0.001,
"loss": 2.0923,
"step": 380
},
{
"epoch": 0.6416842105263157,
"grad_norm": 0.9858509302139282,
"learning_rate": 0.001,
"loss": 1.9338,
"step": 381
},
{
"epoch": 0.6433684210526316,
"grad_norm": 1.0888968706130981,
"learning_rate": 0.001,
"loss": 1.8463,
"step": 382
},
{
"epoch": 0.6450526315789473,
"grad_norm": 0.9424766302108765,
"learning_rate": 0.001,
"loss": 1.8135,
"step": 383
},
{
"epoch": 0.6467368421052632,
"grad_norm": 0.955096960067749,
"learning_rate": 0.001,
"loss": 1.9355,
"step": 384
},
{
"epoch": 0.6484210526315789,
"grad_norm": 0.9020712375640869,
"learning_rate": 0.001,
"loss": 2.2235,
"step": 385
},
{
"epoch": 0.6501052631578947,
"grad_norm": 1.2948638200759888,
"learning_rate": 0.001,
"loss": 1.8841,
"step": 386
},
{
"epoch": 0.6517894736842105,
"grad_norm": 1.1215901374816895,
"learning_rate": 0.001,
"loss": 2.3204,
"step": 387
},
{
"epoch": 0.6534736842105263,
"grad_norm": 1.000780701637268,
"learning_rate": 0.001,
"loss": 1.9545,
"step": 388
},
{
"epoch": 0.655157894736842,
"grad_norm": 1.0688225030899048,
"learning_rate": 0.001,
"loss": 2.1332,
"step": 389
},
{
"epoch": 0.6568421052631579,
"grad_norm": 0.8454869985580444,
"learning_rate": 0.001,
"loss": 2.2442,
"step": 390
},
{
"epoch": 0.6585263157894737,
"grad_norm": 1.0029394626617432,
"learning_rate": 0.001,
"loss": 1.9708,
"step": 391
},
{
"epoch": 0.6602105263157895,
"grad_norm": 1.2006776332855225,
"learning_rate": 0.001,
"loss": 1.9889,
"step": 392
},
{
"epoch": 0.6618947368421053,
"grad_norm": 0.8848575949668884,
"learning_rate": 0.001,
"loss": 1.8719,
"step": 393
},
{
"epoch": 0.663578947368421,
"grad_norm": 0.9433349370956421,
"learning_rate": 0.001,
"loss": 1.807,
"step": 394
},
{
"epoch": 0.6652631578947369,
"grad_norm": 1.1462281942367554,
"learning_rate": 0.001,
"loss": 1.9315,
"step": 395
},
{
"epoch": 0.6669473684210526,
"grad_norm": 0.9325450658798218,
"learning_rate": 0.001,
"loss": 1.701,
"step": 396
},
{
"epoch": 0.6686315789473685,
"grad_norm": 1.1033800840377808,
"learning_rate": 0.001,
"loss": 2.0728,
"step": 397
},
{
"epoch": 0.6703157894736842,
"grad_norm": 1.0380494594573975,
"learning_rate": 0.001,
"loss": 1.9656,
"step": 398
},
{
"epoch": 0.672,
"grad_norm": 0.8989469408988953,
"learning_rate": 0.001,
"loss": 1.9998,
"step": 399
},
{
"epoch": 0.6736842105263158,
"grad_norm": 1.1360111236572266,
"learning_rate": 0.001,
"loss": 2.1114,
"step": 400
},
{
"epoch": 0.6753684210526316,
"grad_norm": 0.9334345459938049,
"learning_rate": 0.001,
"loss": 1.7843,
"step": 401
},
{
"epoch": 0.6770526315789474,
"grad_norm": 0.8565030097961426,
"learning_rate": 0.001,
"loss": 1.8634,
"step": 402
},
{
"epoch": 0.6787368421052632,
"grad_norm": 0.926354706287384,
"learning_rate": 0.001,
"loss": 2.1583,
"step": 403
},
{
"epoch": 0.6804210526315789,
"grad_norm": 1.041408896446228,
"learning_rate": 0.001,
"loss": 2.0652,
"step": 404
},
{
"epoch": 0.6821052631578948,
"grad_norm": 0.8957986235618591,
"learning_rate": 0.001,
"loss": 1.9705,
"step": 405
},
{
"epoch": 0.6837894736842105,
"grad_norm": 0.866303026676178,
"learning_rate": 0.001,
"loss": 1.9173,
"step": 406
},
{
"epoch": 0.6854736842105263,
"grad_norm": 0.9298515915870667,
"learning_rate": 0.001,
"loss": 1.4851,
"step": 407
},
{
"epoch": 0.6871578947368421,
"grad_norm": 0.8325154781341553,
"learning_rate": 0.001,
"loss": 1.9217,
"step": 408
},
{
"epoch": 0.6888421052631579,
"grad_norm": 1.0331366062164307,
"learning_rate": 0.001,
"loss": 2.2276,
"step": 409
},
{
"epoch": 0.6905263157894737,
"grad_norm": 0.9623380899429321,
"learning_rate": 0.001,
"loss": 1.9401,
"step": 410
},
{
"epoch": 0.6922105263157895,
"grad_norm": 0.9502870440483093,
"learning_rate": 0.001,
"loss": 2.0698,
"step": 411
},
{
"epoch": 0.6938947368421052,
"grad_norm": 0.7351365089416504,
"learning_rate": 0.001,
"loss": 1.8196,
"step": 412
},
{
"epoch": 0.6955789473684211,
"grad_norm": 1.4265284538269043,
"learning_rate": 0.001,
"loss": 2.1069,
"step": 413
},
{
"epoch": 0.6972631578947368,
"grad_norm": 0.9151477813720703,
"learning_rate": 0.001,
"loss": 1.9652,
"step": 414
},
{
"epoch": 0.6989473684210527,
"grad_norm": 1.0058677196502686,
"learning_rate": 0.001,
"loss": 1.9402,
"step": 415
},
{
"epoch": 0.7006315789473684,
"grad_norm": 0.8107333183288574,
"learning_rate": 0.001,
"loss": 1.8946,
"step": 416
},
{
"epoch": 0.7023157894736842,
"grad_norm": 0.9497429132461548,
"learning_rate": 0.001,
"loss": 2.0289,
"step": 417
},
{
"epoch": 0.704,
"grad_norm": 0.9337472319602966,
"learning_rate": 0.001,
"loss": 1.9517,
"step": 418
},
{
"epoch": 0.7056842105263158,
"grad_norm": 0.872475802898407,
"learning_rate": 0.001,
"loss": 2.0209,
"step": 419
},
{
"epoch": 0.7073684210526315,
"grad_norm": 0.9438268542289734,
"learning_rate": 0.001,
"loss": 1.9209,
"step": 420
},
{
"epoch": 0.7090526315789474,
"grad_norm": 1.2881578207015991,
"learning_rate": 0.001,
"loss": 2.1235,
"step": 421
},
{
"epoch": 0.7107368421052631,
"grad_norm": 0.8764305114746094,
"learning_rate": 0.001,
"loss": 1.9836,
"step": 422
},
{
"epoch": 0.712421052631579,
"grad_norm": 1.232689619064331,
"learning_rate": 0.001,
"loss": 2.2588,
"step": 423
},
{
"epoch": 0.7141052631578947,
"grad_norm": 0.9619866013526917,
"learning_rate": 0.001,
"loss": 2.1062,
"step": 424
},
{
"epoch": 0.7157894736842105,
"grad_norm": 0.9023774266242981,
"learning_rate": 0.001,
"loss": 1.9278,
"step": 425
},
{
"epoch": 0.7174736842105263,
"grad_norm": 1.1033554077148438,
"learning_rate": 0.001,
"loss": 1.7297,
"step": 426
},
{
"epoch": 0.7191578947368421,
"grad_norm": 0.7463766932487488,
"learning_rate": 0.001,
"loss": 1.725,
"step": 427
},
{
"epoch": 0.7208421052631578,
"grad_norm": 0.9457252621650696,
"learning_rate": 0.001,
"loss": 1.7739,
"step": 428
},
{
"epoch": 0.7225263157894737,
"grad_norm": 0.934600293636322,
"learning_rate": 0.001,
"loss": 2.1775,
"step": 429
},
{
"epoch": 0.7242105263157895,
"grad_norm": 0.8955628871917725,
"learning_rate": 0.001,
"loss": 2.2009,
"step": 430
},
{
"epoch": 0.7258947368421053,
"grad_norm": 0.94439697265625,
"learning_rate": 0.001,
"loss": 2.244,
"step": 431
},
{
"epoch": 0.7275789473684211,
"grad_norm": 0.8255289793014526,
"learning_rate": 0.001,
"loss": 1.8666,
"step": 432
},
{
"epoch": 0.7292631578947368,
"grad_norm": 0.8670260906219482,
"learning_rate": 0.001,
"loss": 1.7115,
"step": 433
},
{
"epoch": 0.7309473684210527,
"grad_norm": 0.8938360214233398,
"learning_rate": 0.001,
"loss": 1.6273,
"step": 434
},
{
"epoch": 0.7326315789473684,
"grad_norm": 1.236402988433838,
"learning_rate": 0.001,
"loss": 2.0744,
"step": 435
},
{
"epoch": 0.7343157894736843,
"grad_norm": 0.8387994170188904,
"learning_rate": 0.001,
"loss": 1.9027,
"step": 436
},
{
"epoch": 0.736,
"grad_norm": 0.8984929323196411,
"learning_rate": 0.001,
"loss": 2.1411,
"step": 437
},
{
"epoch": 0.7376842105263158,
"grad_norm": 0.9328674077987671,
"learning_rate": 0.001,
"loss": 2.2223,
"step": 438
},
{
"epoch": 0.7393684210526316,
"grad_norm": 0.8986714482307434,
"learning_rate": 0.001,
"loss": 1.9568,
"step": 439
},
{
"epoch": 0.7410526315789474,
"grad_norm": 0.9492053389549255,
"learning_rate": 0.001,
"loss": 2.2018,
"step": 440
},
{
"epoch": 0.7427368421052631,
"grad_norm": 0.8261067867279053,
"learning_rate": 0.001,
"loss": 2.0828,
"step": 441
},
{
"epoch": 0.744421052631579,
"grad_norm": 1.0723634958267212,
"learning_rate": 0.001,
"loss": 2.2274,
"step": 442
},
{
"epoch": 0.7461052631578947,
"grad_norm": 0.933506190776825,
"learning_rate": 0.001,
"loss": 2.0962,
"step": 443
},
{
"epoch": 0.7477894736842106,
"grad_norm": 0.7961298227310181,
"learning_rate": 0.001,
"loss": 2.1599,
"step": 444
},
{
"epoch": 0.7494736842105263,
"grad_norm": 0.9804624319076538,
"learning_rate": 0.001,
"loss": 2.2872,
"step": 445
},
{
"epoch": 0.7511578947368421,
"grad_norm": 0.8495241403579712,
"learning_rate": 0.001,
"loss": 1.9647,
"step": 446
},
{
"epoch": 0.7528421052631579,
"grad_norm": 0.9075875878334045,
"learning_rate": 0.001,
"loss": 2.1734,
"step": 447
},
{
"epoch": 0.7528421052631579,
"eval_loss": 1.7126047611236572,
"eval_runtime": 0.0791,
"eval_samples_per_second": 12.634,
"eval_steps_per_second": 12.634,
"step": 447
},
{
"epoch": 0.7545263157894737,
"grad_norm": 0.8501783013343811,
"learning_rate": 0.001,
"loss": 1.7057,
"step": 448
},
{
"epoch": 0.7562105263157894,
"grad_norm": 0.9169737100601196,
"learning_rate": 0.001,
"loss": 2.0444,
"step": 449
},
{
"epoch": 0.7578947368421053,
"grad_norm": 0.8813796043395996,
"learning_rate": 0.001,
"loss": 1.4839,
"step": 450
},
{
"epoch": 0.759578947368421,
"grad_norm": 0.9467214345932007,
"learning_rate": 0.001,
"loss": 1.8931,
"step": 451
},
{
"epoch": 0.7612631578947369,
"grad_norm": 0.8730418086051941,
"learning_rate": 0.001,
"loss": 1.7104,
"step": 452
},
{
"epoch": 0.7629473684210526,
"grad_norm": 0.8568257093429565,
"learning_rate": 0.001,
"loss": 1.998,
"step": 453
},
{
"epoch": 0.7646315789473684,
"grad_norm": 0.8972058892250061,
"learning_rate": 0.001,
"loss": 1.8552,
"step": 454
},
{
"epoch": 0.7663157894736842,
"grad_norm": 0.9764978289604187,
"learning_rate": 0.001,
"loss": 2.0078,
"step": 455
},
{
"epoch": 0.768,
"grad_norm": 0.9850934147834778,
"learning_rate": 0.001,
"loss": 1.9529,
"step": 456
},
{
"epoch": 0.7696842105263157,
"grad_norm": 0.8368688225746155,
"learning_rate": 0.001,
"loss": 2.1118,
"step": 457
},
{
"epoch": 0.7713684210526316,
"grad_norm": 0.9366937875747681,
"learning_rate": 0.001,
"loss": 1.7256,
"step": 458
},
{
"epoch": 0.7730526315789473,
"grad_norm": 0.9020842909812927,
"learning_rate": 0.001,
"loss": 1.697,
"step": 459
},
{
"epoch": 0.7747368421052632,
"grad_norm": 0.9683967232704163,
"learning_rate": 0.001,
"loss": 1.8288,
"step": 460
},
{
"epoch": 0.7764210526315789,
"grad_norm": 0.926777720451355,
"learning_rate": 0.001,
"loss": 1.7249,
"step": 461
},
{
"epoch": 0.7781052631578947,
"grad_norm": 1.0532008409500122,
"learning_rate": 0.001,
"loss": 2.3132,
"step": 462
},
{
"epoch": 0.7797894736842105,
"grad_norm": 0.8814186453819275,
"learning_rate": 0.001,
"loss": 1.9781,
"step": 463
},
{
"epoch": 0.7814736842105263,
"grad_norm": 0.78118896484375,
"learning_rate": 0.001,
"loss": 1.7407,
"step": 464
},
{
"epoch": 0.783157894736842,
"grad_norm": 0.9273678064346313,
"learning_rate": 0.001,
"loss": 2.2367,
"step": 465
},
{
"epoch": 0.7848421052631579,
"grad_norm": 0.9391574263572693,
"learning_rate": 0.001,
"loss": 1.9642,
"step": 466
},
{
"epoch": 0.7865263157894736,
"grad_norm": 1.0936115980148315,
"learning_rate": 0.001,
"loss": 2.2852,
"step": 467
},
{
"epoch": 0.7882105263157895,
"grad_norm": 1.0484883785247803,
"learning_rate": 0.001,
"loss": 1.8051,
"step": 468
},
{
"epoch": 0.7898947368421053,
"grad_norm": 1.0337159633636475,
"learning_rate": 0.001,
"loss": 2.0115,
"step": 469
},
{
"epoch": 0.791578947368421,
"grad_norm": 0.8993913531303406,
"learning_rate": 0.001,
"loss": 1.7269,
"step": 470
},
{
"epoch": 0.7932631578947369,
"grad_norm": 0.8433123826980591,
"learning_rate": 0.001,
"loss": 2.0798,
"step": 471
},
{
"epoch": 0.7949473684210526,
"grad_norm": 0.9056971669197083,
"learning_rate": 0.001,
"loss": 2.3624,
"step": 472
},
{
"epoch": 0.7966315789473685,
"grad_norm": 0.8916146159172058,
"learning_rate": 0.001,
"loss": 1.6266,
"step": 473
},
{
"epoch": 0.7983157894736842,
"grad_norm": 0.8712090253829956,
"learning_rate": 0.001,
"loss": 2.2228,
"step": 474
},
{
"epoch": 0.8,
"grad_norm": 0.8916635513305664,
"learning_rate": 0.001,
"loss": 1.9197,
"step": 475
},
{
"epoch": 0.8016842105263158,
"grad_norm": 0.9295555949211121,
"learning_rate": 0.001,
"loss": 1.7184,
"step": 476
},
{
"epoch": 0.8033684210526316,
"grad_norm": 0.8718081116676331,
"learning_rate": 0.001,
"loss": 1.9394,
"step": 477
},
{
"epoch": 0.8050526315789474,
"grad_norm": 1.0214195251464844,
"learning_rate": 0.001,
"loss": 1.8555,
"step": 478
},
{
"epoch": 0.8067368421052632,
"grad_norm": 0.9039567708969116,
"learning_rate": 0.001,
"loss": 2.0961,
"step": 479
},
{
"epoch": 0.8084210526315789,
"grad_norm": 1.088826298713684,
"learning_rate": 0.001,
"loss": 2.1166,
"step": 480
},
{
"epoch": 0.8101052631578948,
"grad_norm": 0.9610921144485474,
"learning_rate": 0.001,
"loss": 2.1177,
"step": 481
},
{
"epoch": 0.8117894736842105,
"grad_norm": 0.8916026949882507,
"learning_rate": 0.001,
"loss": 1.9126,
"step": 482
},
{
"epoch": 0.8134736842105263,
"grad_norm": 0.9478291273117065,
"learning_rate": 0.001,
"loss": 2.0522,
"step": 483
},
{
"epoch": 0.8151578947368421,
"grad_norm": 1.1988763809204102,
"learning_rate": 0.001,
"loss": 2.1891,
"step": 484
},
{
"epoch": 0.8168421052631579,
"grad_norm": 1.06550133228302,
"learning_rate": 0.001,
"loss": 2.0575,
"step": 485
},
{
"epoch": 0.8185263157894737,
"grad_norm": 1.0411326885223389,
"learning_rate": 0.001,
"loss": 2.2342,
"step": 486
},
{
"epoch": 0.8202105263157895,
"grad_norm": 0.996446967124939,
"learning_rate": 0.001,
"loss": 2.3195,
"step": 487
},
{
"epoch": 0.8218947368421052,
"grad_norm": 0.9175570011138916,
"learning_rate": 0.001,
"loss": 1.9672,
"step": 488
},
{
"epoch": 0.8235789473684211,
"grad_norm": 0.9615358710289001,
"learning_rate": 0.001,
"loss": 1.7088,
"step": 489
},
{
"epoch": 0.8252631578947368,
"grad_norm": 1.0030488967895508,
"learning_rate": 0.001,
"loss": 1.9093,
"step": 490
},
{
"epoch": 0.8269473684210527,
"grad_norm": 0.8371875882148743,
"learning_rate": 0.001,
"loss": 2.0981,
"step": 491
},
{
"epoch": 0.8286315789473684,
"grad_norm": 1.0094941854476929,
"learning_rate": 0.001,
"loss": 1.9831,
"step": 492
},
{
"epoch": 0.8303157894736842,
"grad_norm": 0.6985566020011902,
"learning_rate": 0.001,
"loss": 1.481,
"step": 493
},
{
"epoch": 0.832,
"grad_norm": 0.8714520335197449,
"learning_rate": 0.001,
"loss": 1.8478,
"step": 494
},
{
"epoch": 0.8336842105263158,
"grad_norm": 0.9632995128631592,
"learning_rate": 0.001,
"loss": 1.9434,
"step": 495
},
{
"epoch": 0.8353684210526315,
"grad_norm": 0.989193320274353,
"learning_rate": 0.001,
"loss": 2.1274,
"step": 496
},
{
"epoch": 0.8370526315789474,
"grad_norm": 0.9159345626831055,
"learning_rate": 0.001,
"loss": 2.0572,
"step": 497
},
{
"epoch": 0.8387368421052631,
"grad_norm": 0.8769975304603577,
"learning_rate": 0.001,
"loss": 1.6761,
"step": 498
},
{
"epoch": 0.840421052631579,
"grad_norm": 1.0717746019363403,
"learning_rate": 0.001,
"loss": 1.964,
"step": 499
},
{
"epoch": 0.8421052631578947,
"grad_norm": 1.0184441804885864,
"learning_rate": 0.001,
"loss": 2.0598,
"step": 500
},
{
"epoch": 0.8437894736842105,
"grad_norm": 1.1409798860549927,
"learning_rate": 0.001,
"loss": 1.57,
"step": 501
},
{
"epoch": 0.8454736842105263,
"grad_norm": 0.917641818523407,
"learning_rate": 0.001,
"loss": 1.7864,
"step": 502
},
{
"epoch": 0.8471578947368421,
"grad_norm": 0.9784872531890869,
"learning_rate": 0.001,
"loss": 2.2752,
"step": 503
},
{
"epoch": 0.8488421052631578,
"grad_norm": 1.012035846710205,
"learning_rate": 0.001,
"loss": 1.9572,
"step": 504
},
{
"epoch": 0.8505263157894737,
"grad_norm": 0.8496696949005127,
"learning_rate": 0.001,
"loss": 1.5138,
"step": 505
},
{
"epoch": 0.8522105263157894,
"grad_norm": 1.0498113632202148,
"learning_rate": 0.001,
"loss": 2.1815,
"step": 506
},
{
"epoch": 0.8538947368421053,
"grad_norm": 0.8694950938224792,
"learning_rate": 0.001,
"loss": 1.9297,
"step": 507
},
{
"epoch": 0.8555789473684211,
"grad_norm": 0.9349990487098694,
"learning_rate": 0.001,
"loss": 1.9476,
"step": 508
},
{
"epoch": 0.8572631578947368,
"grad_norm": 0.9136828184127808,
"learning_rate": 0.001,
"loss": 1.9822,
"step": 509
},
{
"epoch": 0.8589473684210527,
"grad_norm": 0.9763911366462708,
"learning_rate": 0.001,
"loss": 2.0084,
"step": 510
},
{
"epoch": 0.8606315789473684,
"grad_norm": 0.9221206307411194,
"learning_rate": 0.001,
"loss": 1.9916,
"step": 511
},
{
"epoch": 0.8623157894736843,
"grad_norm": 0.9817140698432922,
"learning_rate": 0.001,
"loss": 1.9887,
"step": 512
},
{
"epoch": 0.864,
"grad_norm": 1.166142463684082,
"learning_rate": 0.001,
"loss": 2.0389,
"step": 513
},
{
"epoch": 0.8656842105263158,
"grad_norm": 0.9571674466133118,
"learning_rate": 0.001,
"loss": 1.6596,
"step": 514
},
{
"epoch": 0.8673684210526316,
"grad_norm": 1.113754391670227,
"learning_rate": 0.001,
"loss": 1.7947,
"step": 515
},
{
"epoch": 0.8690526315789474,
"grad_norm": 0.8172054290771484,
"learning_rate": 0.001,
"loss": 2.1411,
"step": 516
},
{
"epoch": 0.8707368421052631,
"grad_norm": 0.7713819742202759,
"learning_rate": 0.001,
"loss": 1.6631,
"step": 517
},
{
"epoch": 0.872421052631579,
"grad_norm": 1.0675171613693237,
"learning_rate": 0.001,
"loss": 2.115,
"step": 518
},
{
"epoch": 0.8741052631578947,
"grad_norm": 0.9892959594726562,
"learning_rate": 0.001,
"loss": 2.0591,
"step": 519
},
{
"epoch": 0.8757894736842106,
"grad_norm": 1.017602562904358,
"learning_rate": 0.001,
"loss": 1.8098,
"step": 520
},
{
"epoch": 0.8774736842105263,
"grad_norm": 1.0160664319992065,
"learning_rate": 0.001,
"loss": 2.0635,
"step": 521
},
{
"epoch": 0.8791578947368421,
"grad_norm": 0.7594957947731018,
"learning_rate": 0.001,
"loss": 1.9662,
"step": 522
},
{
"epoch": 0.8808421052631579,
"grad_norm": 0.9666638374328613,
"learning_rate": 0.001,
"loss": 2.3076,
"step": 523
},
{
"epoch": 0.8825263157894737,
"grad_norm": 1.0217084884643555,
"learning_rate": 0.001,
"loss": 2.1043,
"step": 524
},
{
"epoch": 0.8842105263157894,
"grad_norm": 0.9620029330253601,
"learning_rate": 0.001,
"loss": 1.9836,
"step": 525
},
{
"epoch": 0.8858947368421053,
"grad_norm": 0.9031502604484558,
"learning_rate": 0.001,
"loss": 1.8648,
"step": 526
},
{
"epoch": 0.887578947368421,
"grad_norm": 1.0853564739227295,
"learning_rate": 0.001,
"loss": 2.2491,
"step": 527
},
{
"epoch": 0.8892631578947369,
"grad_norm": 0.850796639919281,
"learning_rate": 0.001,
"loss": 1.8988,
"step": 528
},
{
"epoch": 0.8909473684210526,
"grad_norm": 0.9813094735145569,
"learning_rate": 0.001,
"loss": 2.0652,
"step": 529
},
{
"epoch": 0.8926315789473684,
"grad_norm": 1.1805915832519531,
"learning_rate": 0.001,
"loss": 1.9761,
"step": 530
},
{
"epoch": 0.8943157894736842,
"grad_norm": 0.91289222240448,
"learning_rate": 0.001,
"loss": 2.2265,
"step": 531
},
{
"epoch": 0.896,
"grad_norm": 0.8116694092750549,
"learning_rate": 0.001,
"loss": 2.0667,
"step": 532
},
{
"epoch": 0.8976842105263158,
"grad_norm": 1.0094329118728638,
"learning_rate": 0.001,
"loss": 2.2099,
"step": 533
},
{
"epoch": 0.8993684210526316,
"grad_norm": 0.9709912538528442,
"learning_rate": 0.001,
"loss": 1.7337,
"step": 534
},
{
"epoch": 0.9010526315789473,
"grad_norm": 1.1453299522399902,
"learning_rate": 0.001,
"loss": 2.0997,
"step": 535
},
{
"epoch": 0.9027368421052632,
"grad_norm": 1.097075343132019,
"learning_rate": 0.001,
"loss": 2.1082,
"step": 536
},
{
"epoch": 0.9044210526315789,
"grad_norm": 0.9422668218612671,
"learning_rate": 0.001,
"loss": 2.2451,
"step": 537
},
{
"epoch": 0.9061052631578947,
"grad_norm": 0.8550103902816772,
"learning_rate": 0.001,
"loss": 1.8164,
"step": 538
},
{
"epoch": 0.9077894736842105,
"grad_norm": 1.0287948846817017,
"learning_rate": 0.001,
"loss": 1.8799,
"step": 539
},
{
"epoch": 0.9094736842105263,
"grad_norm": 1.0734996795654297,
"learning_rate": 0.001,
"loss": 2.1292,
"step": 540
},
{
"epoch": 0.9111578947368421,
"grad_norm": 0.9072704315185547,
"learning_rate": 0.001,
"loss": 1.9709,
"step": 541
},
{
"epoch": 0.9128421052631579,
"grad_norm": 0.9148054718971252,
"learning_rate": 0.001,
"loss": 1.7025,
"step": 542
},
{
"epoch": 0.9145263157894736,
"grad_norm": 1.094970941543579,
"learning_rate": 0.001,
"loss": 2.0636,
"step": 543
},
{
"epoch": 0.9162105263157895,
"grad_norm": 0.8233382701873779,
"learning_rate": 0.001,
"loss": 2.0036,
"step": 544
},
{
"epoch": 0.9178947368421052,
"grad_norm": 0.789847731590271,
"learning_rate": 0.001,
"loss": 1.9641,
"step": 545
},
{
"epoch": 0.919578947368421,
"grad_norm": 1.1164312362670898,
"learning_rate": 0.001,
"loss": 2.0094,
"step": 546
},
{
"epoch": 0.9212631578947369,
"grad_norm": 0.9254114031791687,
"learning_rate": 0.001,
"loss": 2.0071,
"step": 547
},
{
"epoch": 0.9229473684210526,
"grad_norm": 0.772678017616272,
"learning_rate": 0.001,
"loss": 1.6871,
"step": 548
},
{
"epoch": 0.9246315789473685,
"grad_norm": 0.8702642321586609,
"learning_rate": 0.001,
"loss": 1.86,
"step": 549
},
{
"epoch": 0.9263157894736842,
"grad_norm": 0.9259825348854065,
"learning_rate": 0.001,
"loss": 2.2161,
"step": 550
},
{
"epoch": 0.928,
"grad_norm": 1.095923662185669,
"learning_rate": 0.001,
"loss": 2.2506,
"step": 551
},
{
"epoch": 0.9296842105263158,
"grad_norm": 0.8884152770042419,
"learning_rate": 0.001,
"loss": 1.9812,
"step": 552
},
{
"epoch": 0.9313684210526316,
"grad_norm": 1.201453685760498,
"learning_rate": 0.001,
"loss": 2.3967,
"step": 553
},
{
"epoch": 0.9330526315789474,
"grad_norm": 0.8036067485809326,
"learning_rate": 0.001,
"loss": 2.0411,
"step": 554
},
{
"epoch": 0.9347368421052632,
"grad_norm": 1.1204805374145508,
"learning_rate": 0.001,
"loss": 1.9963,
"step": 555
},
{
"epoch": 0.9364210526315789,
"grad_norm": 0.9753801822662354,
"learning_rate": 0.001,
"loss": 2.0774,
"step": 556
},
{
"epoch": 0.9381052631578948,
"grad_norm": 0.9044502973556519,
"learning_rate": 0.001,
"loss": 2.2171,
"step": 557
},
{
"epoch": 0.9397894736842105,
"grad_norm": 0.872684121131897,
"learning_rate": 0.001,
"loss": 2.1116,
"step": 558
},
{
"epoch": 0.9414736842105264,
"grad_norm": 0.9896319508552551,
"learning_rate": 0.001,
"loss": 1.9894,
"step": 559
},
{
"epoch": 0.9431578947368421,
"grad_norm": 0.8896704912185669,
"learning_rate": 0.001,
"loss": 1.83,
"step": 560
},
{
"epoch": 0.9448421052631579,
"grad_norm": 1.1786295175552368,
"learning_rate": 0.001,
"loss": 1.3999,
"step": 561
},
{
"epoch": 0.9465263157894737,
"grad_norm": 1.0260367393493652,
"learning_rate": 0.001,
"loss": 1.7856,
"step": 562
},
{
"epoch": 0.9482105263157895,
"grad_norm": 1.1223475933074951,
"learning_rate": 0.001,
"loss": 1.8988,
"step": 563
},
{
"epoch": 0.9498947368421052,
"grad_norm": 1.2666854858398438,
"learning_rate": 0.001,
"loss": 2.4208,
"step": 564
},
{
"epoch": 0.9515789473684211,
"grad_norm": 0.8746899366378784,
"learning_rate": 0.001,
"loss": 2.0621,
"step": 565
},
{
"epoch": 0.9532631578947368,
"grad_norm": 1.1559736728668213,
"learning_rate": 0.001,
"loss": 1.9889,
"step": 566
},
{
"epoch": 0.9549473684210527,
"grad_norm": 0.8954889178276062,
"learning_rate": 0.001,
"loss": 2.1674,
"step": 567
},
{
"epoch": 0.9566315789473684,
"grad_norm": 0.848497748374939,
"learning_rate": 0.001,
"loss": 2.1309,
"step": 568
},
{
"epoch": 0.9583157894736842,
"grad_norm": 0.9832907319068909,
"learning_rate": 0.001,
"loss": 1.9696,
"step": 569
},
{
"epoch": 0.96,
"grad_norm": 1.004216194152832,
"learning_rate": 0.001,
"loss": 2.1556,
"step": 570
},
{
"epoch": 0.9616842105263158,
"grad_norm": 1.2567979097366333,
"learning_rate": 0.001,
"loss": 1.925,
"step": 571
},
{
"epoch": 0.9633684210526315,
"grad_norm": 1.056889533996582,
"learning_rate": 0.001,
"loss": 1.7742,
"step": 572
},
{
"epoch": 0.9650526315789474,
"grad_norm": 0.7364183664321899,
"learning_rate": 0.001,
"loss": 1.7558,
"step": 573
},
{
"epoch": 0.9667368421052631,
"grad_norm": 1.1390528678894043,
"learning_rate": 0.001,
"loss": 1.8911,
"step": 574
},
{
"epoch": 0.968421052631579,
"grad_norm": 1.0370616912841797,
"learning_rate": 0.001,
"loss": 2.091,
"step": 575
},
{
"epoch": 0.9701052631578947,
"grad_norm": 0.8506829738616943,
"learning_rate": 0.001,
"loss": 2.2052,
"step": 576
},
{
"epoch": 0.9717894736842105,
"grad_norm": 0.8810485601425171,
"learning_rate": 0.001,
"loss": 2.2049,
"step": 577
},
{
"epoch": 0.9734736842105263,
"grad_norm": 1.0657389163970947,
"learning_rate": 0.001,
"loss": 2.1982,
"step": 578
},
{
"epoch": 0.9751578947368421,
"grad_norm": 0.9130502343177795,
"learning_rate": 0.001,
"loss": 1.7093,
"step": 579
},
{
"epoch": 0.9768421052631578,
"grad_norm": 0.9334926605224609,
"learning_rate": 0.001,
"loss": 1.8507,
"step": 580
},
{
"epoch": 0.9785263157894737,
"grad_norm": 0.9801141023635864,
"learning_rate": 0.001,
"loss": 2.0824,
"step": 581
},
{
"epoch": 0.9802105263157894,
"grad_norm": 1.1863903999328613,
"learning_rate": 0.001,
"loss": 2.0316,
"step": 582
},
{
"epoch": 0.9818947368421053,
"grad_norm": 0.9224819540977478,
"learning_rate": 0.001,
"loss": 2.1538,
"step": 583
},
{
"epoch": 0.983578947368421,
"grad_norm": 0.9597621560096741,
"learning_rate": 0.001,
"loss": 2.0054,
"step": 584
},
{
"epoch": 0.9852631578947368,
"grad_norm": 1.1641483306884766,
"learning_rate": 0.001,
"loss": 1.9722,
"step": 585
},
{
"epoch": 0.9869473684210527,
"grad_norm": 0.9333254098892212,
"learning_rate": 0.001,
"loss": 2.0654,
"step": 586
},
{
"epoch": 0.9886315789473684,
"grad_norm": 1.0137170553207397,
"learning_rate": 0.001,
"loss": 2.198,
"step": 587
},
{
"epoch": 0.9903157894736843,
"grad_norm": 0.9962888360023499,
"learning_rate": 0.001,
"loss": 1.9295,
"step": 588
},
{
"epoch": 0.992,
"grad_norm": 1.1276189088821411,
"learning_rate": 0.001,
"loss": 1.9579,
"step": 589
},
{
"epoch": 0.9936842105263158,
"grad_norm": 0.9350583553314209,
"learning_rate": 0.001,
"loss": 1.9998,
"step": 590
},
{
"epoch": 0.9953684210526316,
"grad_norm": 0.97312992811203,
"learning_rate": 0.001,
"loss": 1.7338,
"step": 591
},
{
"epoch": 0.9970526315789474,
"grad_norm": 1.0777076482772827,
"learning_rate": 0.001,
"loss": 1.7413,
"step": 592
},
{
"epoch": 0.9987368421052631,
"grad_norm": 1.031515121459961,
"learning_rate": 0.001,
"loss": 2.3266,
"step": 593
},
{
"epoch": 0.9987368421052631,
"step": 593,
"total_flos": 3.231264518066995e+16,
"train_loss": 1.9546177544038976,
"train_runtime": 1901.8595,
"train_samples_per_second": 4.995,
"train_steps_per_second": 0.312
}
],
"logging_steps": 1,
"max_steps": 593,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 149,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 100,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.231264518066995e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}