RAG-Truth-Model / trainer_state.json
3v324v23's picture
upload
854f379
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 80.0,
"global_step": 220,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004545454545454545,
"grad_norm": 31.375,
"learning_rate": 9.090909090909091e-07,
"loss": 0.9322,
"step": 1
},
{
"epoch": 0.00909090909090909,
"grad_norm": 26.75,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.8842,
"step": 2
},
{
"epoch": 0.013636363636363636,
"grad_norm": 23.75,
"learning_rate": 2.7272727272727272e-06,
"loss": 0.8735,
"step": 3
},
{
"epoch": 0.01818181818181818,
"grad_norm": 26.75,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.9293,
"step": 4
},
{
"epoch": 0.022727272727272728,
"grad_norm": 15.375,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.7274,
"step": 5
},
{
"epoch": 0.02727272727272727,
"grad_norm": 12.5625,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.7129,
"step": 6
},
{
"epoch": 0.031818181818181815,
"grad_norm": 14.1875,
"learning_rate": 6.363636363636364e-06,
"loss": 0.5507,
"step": 7
},
{
"epoch": 0.03636363636363636,
"grad_norm": 10.875,
"learning_rate": 7.272727272727273e-06,
"loss": 0.4211,
"step": 8
},
{
"epoch": 0.04090909090909091,
"grad_norm": 7.5625,
"learning_rate": 8.181818181818183e-06,
"loss": 0.3369,
"step": 9
},
{
"epoch": 0.045454545454545456,
"grad_norm": 4.59375,
"learning_rate": 9.090909090909091e-06,
"loss": 0.2542,
"step": 10
},
{
"epoch": 0.05,
"grad_norm": 5.34375,
"learning_rate": 1e-05,
"loss": 0.2182,
"step": 11
},
{
"epoch": 0.05454545454545454,
"grad_norm": 3.21875,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.2255,
"step": 12
},
{
"epoch": 0.05909090909090909,
"grad_norm": 3.234375,
"learning_rate": 1.181818181818182e-05,
"loss": 0.2874,
"step": 13
},
{
"epoch": 0.06363636363636363,
"grad_norm": 3.734375,
"learning_rate": 1.2727272727272728e-05,
"loss": 0.3364,
"step": 14
},
{
"epoch": 0.06818181818181818,
"grad_norm": 3.921875,
"learning_rate": 1.3636363636363637e-05,
"loss": 0.2621,
"step": 15
},
{
"epoch": 0.07272727272727272,
"grad_norm": 3.71875,
"learning_rate": 1.4545454545454546e-05,
"loss": 0.2664,
"step": 16
},
{
"epoch": 0.07727272727272727,
"grad_norm": 3.34375,
"learning_rate": 1.5454545454545454e-05,
"loss": 0.2475,
"step": 17
},
{
"epoch": 0.08181818181818182,
"grad_norm": 3.875,
"learning_rate": 1.6363636363636366e-05,
"loss": 0.2199,
"step": 18
},
{
"epoch": 0.08636363636363636,
"grad_norm": 2.828125,
"learning_rate": 1.7272727272727274e-05,
"loss": 0.2165,
"step": 19
},
{
"epoch": 0.09090909090909091,
"grad_norm": 2.703125,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.2101,
"step": 20
},
{
"epoch": 0.09545454545454546,
"grad_norm": 3.078125,
"learning_rate": 1.9090909090909094e-05,
"loss": 0.2712,
"step": 21
},
{
"epoch": 0.1,
"grad_norm": 3.671875,
"learning_rate": 2e-05,
"loss": 0.218,
"step": 22
},
{
"epoch": 0.10454545454545454,
"grad_norm": 2.71875,
"learning_rate": 1.9998741276738753e-05,
"loss": 0.2207,
"step": 23
},
{
"epoch": 0.10909090909090909,
"grad_norm": 2.359375,
"learning_rate": 1.9994965423831853e-05,
"loss": 0.1958,
"step": 24
},
{
"epoch": 0.11363636363636363,
"grad_norm": 3.15625,
"learning_rate": 1.9988673391830082e-05,
"loss": 0.241,
"step": 25
},
{
"epoch": 0.11818181818181818,
"grad_norm": 2.875,
"learning_rate": 1.9979866764718846e-05,
"loss": 0.2201,
"step": 26
},
{
"epoch": 0.12272727272727273,
"grad_norm": 1.75,
"learning_rate": 1.9968547759519426e-05,
"loss": 0.1972,
"step": 27
},
{
"epoch": 0.12727272727272726,
"grad_norm": 3.78125,
"learning_rate": 1.9954719225730847e-05,
"loss": 0.2084,
"step": 28
},
{
"epoch": 0.1318181818181818,
"grad_norm": 2.265625,
"learning_rate": 1.9938384644612542e-05,
"loss": 0.2344,
"step": 29
},
{
"epoch": 0.13636363636363635,
"grad_norm": 1.9375,
"learning_rate": 1.9919548128307954e-05,
"loss": 0.277,
"step": 30
},
{
"epoch": 0.1409090909090909,
"grad_norm": 1.7109375,
"learning_rate": 1.989821441880933e-05,
"loss": 0.1843,
"step": 31
},
{
"epoch": 0.14545454545454545,
"grad_norm": 2.03125,
"learning_rate": 1.9874388886763944e-05,
"loss": 0.2291,
"step": 32
},
{
"epoch": 0.15,
"grad_norm": 1.4765625,
"learning_rate": 1.9848077530122083e-05,
"loss": 0.1496,
"step": 33
},
{
"epoch": 0.15454545454545454,
"grad_norm": 1.765625,
"learning_rate": 1.9819286972627066e-05,
"loss": 0.1891,
"step": 34
},
{
"epoch": 0.1590909090909091,
"grad_norm": 2.328125,
"learning_rate": 1.978802446214779e-05,
"loss": 0.2427,
"step": 35
},
{
"epoch": 0.16363636363636364,
"grad_norm": 2.265625,
"learning_rate": 1.9754297868854075e-05,
"loss": 0.2141,
"step": 36
},
{
"epoch": 0.16818181818181818,
"grad_norm": 2.0625,
"learning_rate": 1.9718115683235418e-05,
"loss": 0.1359,
"step": 37
},
{
"epoch": 0.17272727272727273,
"grad_norm": 1.9140625,
"learning_rate": 1.9679487013963566e-05,
"loss": 0.1665,
"step": 38
},
{
"epoch": 0.17727272727272728,
"grad_norm": 1.8984375,
"learning_rate": 1.9638421585599422e-05,
"loss": 0.2017,
"step": 39
},
{
"epoch": 0.18181818181818182,
"grad_norm": 2.296875,
"learning_rate": 1.9594929736144978e-05,
"loss": 0.2324,
"step": 40
},
{
"epoch": 0.18636363636363637,
"grad_norm": 2.109375,
"learning_rate": 1.9549022414440738e-05,
"loss": 0.186,
"step": 41
},
{
"epoch": 0.19090909090909092,
"grad_norm": 2.59375,
"learning_rate": 1.9500711177409456e-05,
"loss": 0.1927,
"step": 42
},
{
"epoch": 0.19545454545454546,
"grad_norm": 3.25,
"learning_rate": 1.9450008187146685e-05,
"loss": 0.2604,
"step": 43
},
{
"epoch": 0.2,
"grad_norm": 1.875,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.1711,
"step": 44
},
{
"epoch": 0.20454545454545456,
"grad_norm": 2.0,
"learning_rate": 1.9341478602651068e-05,
"loss": 0.1797,
"step": 45
},
{
"epoch": 0.20909090909090908,
"grad_norm": 1.6875,
"learning_rate": 1.9283679330160726e-05,
"loss": 0.1052,
"step": 46
},
{
"epoch": 0.21363636363636362,
"grad_norm": 1.96875,
"learning_rate": 1.9223542941045817e-05,
"loss": 0.1806,
"step": 47
},
{
"epoch": 0.21818181818181817,
"grad_norm": 1.765625,
"learning_rate": 1.9161084574320696e-05,
"loss": 0.1695,
"step": 48
},
{
"epoch": 0.22272727272727272,
"grad_norm": 2.328125,
"learning_rate": 1.9096319953545186e-05,
"loss": 0.2306,
"step": 49
},
{
"epoch": 0.22727272727272727,
"grad_norm": 1.609375,
"learning_rate": 1.9029265382866216e-05,
"loss": 0.1642,
"step": 50
},
{
"epoch": 0.2318181818181818,
"grad_norm": 2.109375,
"learning_rate": 1.895993774291336e-05,
"loss": 0.196,
"step": 51
},
{
"epoch": 0.23636363636363636,
"grad_norm": 2.375,
"learning_rate": 1.8888354486549238e-05,
"loss": 0.2231,
"step": 52
},
{
"epoch": 0.2409090909090909,
"grad_norm": 2.03125,
"learning_rate": 1.881453363447582e-05,
"loss": 0.2116,
"step": 53
},
{
"epoch": 0.24545454545454545,
"grad_norm": 2.0625,
"learning_rate": 1.873849377069785e-05,
"loss": 0.2181,
"step": 54
},
{
"epoch": 0.25,
"grad_norm": 1.546875,
"learning_rate": 1.866025403784439e-05,
"loss": 0.1623,
"step": 55
},
{
"epoch": 0.2545454545454545,
"grad_norm": 1.84375,
"learning_rate": 1.8579834132349773e-05,
"loss": 0.224,
"step": 56
},
{
"epoch": 0.2590909090909091,
"grad_norm": 1.796875,
"learning_rate": 1.8497254299495147e-05,
"loss": 0.1804,
"step": 57
},
{
"epoch": 0.2636363636363636,
"grad_norm": 1.671875,
"learning_rate": 1.8412535328311813e-05,
"loss": 0.1598,
"step": 58
},
{
"epoch": 0.2681818181818182,
"grad_norm": 1.828125,
"learning_rate": 1.8325698546347714e-05,
"loss": 0.1745,
"step": 59
},
{
"epoch": 0.2727272727272727,
"grad_norm": 1.859375,
"learning_rate": 1.8236765814298328e-05,
"loss": 0.1944,
"step": 60
},
{
"epoch": 0.2772727272727273,
"grad_norm": 1.6171875,
"learning_rate": 1.814575952050336e-05,
"loss": 0.1868,
"step": 61
},
{
"epoch": 0.2818181818181818,
"grad_norm": 1.734375,
"learning_rate": 1.8052702575310588e-05,
"loss": 0.1597,
"step": 62
},
{
"epoch": 0.2863636363636364,
"grad_norm": 1.4140625,
"learning_rate": 1.7957618405308323e-05,
"loss": 0.1248,
"step": 63
},
{
"epoch": 0.2909090909090909,
"grad_norm": 1.6328125,
"learning_rate": 1.7860530947427878e-05,
"loss": 0.1501,
"step": 64
},
{
"epoch": 0.29545454545454547,
"grad_norm": 1.375,
"learning_rate": 1.776146464291757e-05,
"loss": 0.1483,
"step": 65
},
{
"epoch": 0.3,
"grad_norm": 1.921875,
"learning_rate": 1.766044443118978e-05,
"loss": 0.209,
"step": 66
},
{
"epoch": 0.30454545454545456,
"grad_norm": 2.046875,
"learning_rate": 1.7557495743542586e-05,
"loss": 0.1744,
"step": 67
},
{
"epoch": 0.3090909090909091,
"grad_norm": 1.6953125,
"learning_rate": 1.745264449675755e-05,
"loss": 0.1715,
"step": 68
},
{
"epoch": 0.31363636363636366,
"grad_norm": 1.6640625,
"learning_rate": 1.734591708657533e-05,
"loss": 0.1978,
"step": 69
},
{
"epoch": 0.3181818181818182,
"grad_norm": 1.5859375,
"learning_rate": 1.72373403810507e-05,
"loss": 0.1521,
"step": 70
},
{
"epoch": 0.32272727272727275,
"grad_norm": 1.578125,
"learning_rate": 1.7126941713788633e-05,
"loss": 0.1337,
"step": 71
},
{
"epoch": 0.32727272727272727,
"grad_norm": 1.8359375,
"learning_rate": 1.7014748877063212e-05,
"loss": 0.1868,
"step": 72
},
{
"epoch": 0.33181818181818185,
"grad_norm": 2.171875,
"learning_rate": 1.6900790114821122e-05,
"loss": 0.1739,
"step": 73
},
{
"epoch": 0.33636363636363636,
"grad_norm": 1.71875,
"learning_rate": 1.6785094115571323e-05,
"loss": 0.1434,
"step": 74
},
{
"epoch": 0.3409090909090909,
"grad_norm": 2.34375,
"learning_rate": 1.666769000516292e-05,
"loss": 0.175,
"step": 75
},
{
"epoch": 0.34545454545454546,
"grad_norm": 1.78125,
"learning_rate": 1.6548607339452853e-05,
"loss": 0.1766,
"step": 76
},
{
"epoch": 0.35,
"grad_norm": 1.59375,
"learning_rate": 1.6427876096865394e-05,
"loss": 0.1828,
"step": 77
},
{
"epoch": 0.35454545454545455,
"grad_norm": 1.8046875,
"learning_rate": 1.6305526670845225e-05,
"loss": 0.151,
"step": 78
},
{
"epoch": 0.35909090909090907,
"grad_norm": 2.265625,
"learning_rate": 1.6181589862206053e-05,
"loss": 0.1852,
"step": 79
},
{
"epoch": 0.36363636363636365,
"grad_norm": 2.140625,
"learning_rate": 1.6056096871376667e-05,
"loss": 0.2097,
"step": 80
},
{
"epoch": 0.36818181818181817,
"grad_norm": 2.359375,
"learning_rate": 1.5929079290546408e-05,
"loss": 0.1958,
"step": 81
},
{
"epoch": 0.37272727272727274,
"grad_norm": 1.59375,
"learning_rate": 1.5800569095711983e-05,
"loss": 0.1381,
"step": 82
},
{
"epoch": 0.37727272727272726,
"grad_norm": 1.9453125,
"learning_rate": 1.5670598638627707e-05,
"loss": 0.1858,
"step": 83
},
{
"epoch": 0.38181818181818183,
"grad_norm": 1.7578125,
"learning_rate": 1.5539200638661106e-05,
"loss": 0.1944,
"step": 84
},
{
"epoch": 0.38636363636363635,
"grad_norm": 1.5078125,
"learning_rate": 1.5406408174555978e-05,
"loss": 0.1372,
"step": 85
},
{
"epoch": 0.39090909090909093,
"grad_norm": 2.046875,
"learning_rate": 1.5272254676105026e-05,
"loss": 0.1858,
"step": 86
},
{
"epoch": 0.39545454545454545,
"grad_norm": 1.703125,
"learning_rate": 1.5136773915734067e-05,
"loss": 0.1626,
"step": 87
},
{
"epoch": 0.4,
"grad_norm": 2.03125,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.1917,
"step": 88
},
{
"epoch": 0.40454545454545454,
"grad_norm": 1.6328125,
"learning_rate": 1.4861967361004687e-05,
"loss": 0.1582,
"step": 89
},
{
"epoch": 0.4090909090909091,
"grad_norm": 1.8359375,
"learning_rate": 1.472271074772683e-05,
"loss": 0.1471,
"step": 90
},
{
"epoch": 0.41363636363636364,
"grad_norm": 1.5703125,
"learning_rate": 1.4582265217274105e-05,
"loss": 0.1801,
"step": 91
},
{
"epoch": 0.41818181818181815,
"grad_norm": 1.640625,
"learning_rate": 1.4440666126057743e-05,
"loss": 0.1992,
"step": 92
},
{
"epoch": 0.42272727272727273,
"grad_norm": 1.765625,
"learning_rate": 1.4297949120891718e-05,
"loss": 0.1886,
"step": 93
},
{
"epoch": 0.42727272727272725,
"grad_norm": 2.09375,
"learning_rate": 1.4154150130018867e-05,
"loss": 0.2106,
"step": 94
},
{
"epoch": 0.4318181818181818,
"grad_norm": 1.8359375,
"learning_rate": 1.4009305354066138e-05,
"loss": 0.1364,
"step": 95
},
{
"epoch": 0.43636363636363634,
"grad_norm": 1.5859375,
"learning_rate": 1.3863451256931286e-05,
"loss": 0.1016,
"step": 96
},
{
"epoch": 0.4409090909090909,
"grad_norm": 2.21875,
"learning_rate": 1.3716624556603275e-05,
"loss": 0.1395,
"step": 97
},
{
"epoch": 0.44545454545454544,
"grad_norm": 1.9140625,
"learning_rate": 1.356886221591872e-05,
"loss": 0.1831,
"step": 98
},
{
"epoch": 0.45,
"grad_norm": 1.796875,
"learning_rate": 1.342020143325669e-05,
"loss": 0.1341,
"step": 99
},
{
"epoch": 0.45454545454545453,
"grad_norm": 2.21875,
"learning_rate": 1.3270679633174219e-05,
"loss": 0.1446,
"step": 100
},
{
"epoch": 0.4590909090909091,
"grad_norm": 1.828125,
"learning_rate": 1.3120334456984871e-05,
"loss": 0.1757,
"step": 101
},
{
"epoch": 0.4636363636363636,
"grad_norm": 1.9375,
"learning_rate": 1.296920375328275e-05,
"loss": 0.1582,
"step": 102
},
{
"epoch": 0.4681818181818182,
"grad_norm": 1.984375,
"learning_rate": 1.2817325568414299e-05,
"loss": 0.1489,
"step": 103
},
{
"epoch": 0.4727272727272727,
"grad_norm": 2.203125,
"learning_rate": 1.266473813690035e-05,
"loss": 0.1289,
"step": 104
},
{
"epoch": 0.4772727272727273,
"grad_norm": 1.9609375,
"learning_rate": 1.2511479871810792e-05,
"loss": 0.1579,
"step": 105
},
{
"epoch": 0.4818181818181818,
"grad_norm": 2.3125,
"learning_rate": 1.2357589355094275e-05,
"loss": 0.0772,
"step": 106
},
{
"epoch": 0.4863636363636364,
"grad_norm": 2.0625,
"learning_rate": 1.2203105327865407e-05,
"loss": 0.1084,
"step": 107
},
{
"epoch": 0.4909090909090909,
"grad_norm": 1.9921875,
"learning_rate": 1.2048066680651908e-05,
"loss": 0.1092,
"step": 108
},
{
"epoch": 0.4954545454545455,
"grad_norm": 2.859375,
"learning_rate": 1.1892512443604103e-05,
"loss": 0.1431,
"step": 109
},
{
"epoch": 0.5,
"grad_norm": 5.875,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.1567,
"step": 110
},
{
"epoch": 0.5045454545454545,
"grad_norm": 1.8515625,
"learning_rate": 1.15800139597335e-05,
"loss": 0.1425,
"step": 111
},
{
"epoch": 0.509090909090909,
"grad_norm": 2.203125,
"learning_rate": 1.1423148382732854e-05,
"loss": 0.1589,
"step": 112
},
{
"epoch": 0.5136363636363637,
"grad_norm": 1.859375,
"learning_rate": 1.1265924535737494e-05,
"loss": 0.1323,
"step": 113
},
{
"epoch": 0.5181818181818182,
"grad_norm": 1.7109375,
"learning_rate": 1.1108381999010111e-05,
"loss": 0.1463,
"step": 114
},
{
"epoch": 0.5227272727272727,
"grad_norm": 1.6875,
"learning_rate": 1.0950560433041825e-05,
"loss": 0.1386,
"step": 115
},
{
"epoch": 0.5272727272727272,
"grad_norm": 1.796875,
"learning_rate": 1.0792499568567885e-05,
"loss": 0.1718,
"step": 116
},
{
"epoch": 0.5318181818181819,
"grad_norm": 2.15625,
"learning_rate": 1.0634239196565646e-05,
"loss": 0.1839,
"step": 117
},
{
"epoch": 0.5363636363636364,
"grad_norm": 2.328125,
"learning_rate": 1.0475819158237426e-05,
"loss": 0.1226,
"step": 118
},
{
"epoch": 0.5409090909090909,
"grad_norm": 2.203125,
"learning_rate": 1.031727933498068e-05,
"loss": 0.1921,
"step": 119
},
{
"epoch": 0.5454545454545454,
"grad_norm": 1.921875,
"learning_rate": 1.015865963834808e-05,
"loss": 0.1094,
"step": 120
},
{
"epoch": 0.55,
"grad_norm": 1.7578125,
"learning_rate": 1e-05,
"loss": 0.1204,
"step": 121
},
{
"epoch": 0.5545454545454546,
"grad_norm": 2.0625,
"learning_rate": 9.841340361651921e-06,
"loss": 0.1761,
"step": 122
},
{
"epoch": 0.5590909090909091,
"grad_norm": 2.0625,
"learning_rate": 9.682720665019325e-06,
"loss": 0.1458,
"step": 123
},
{
"epoch": 0.5636363636363636,
"grad_norm": 1.9921875,
"learning_rate": 9.524180841762577e-06,
"loss": 0.141,
"step": 124
},
{
"epoch": 0.5681818181818182,
"grad_norm": 1.734375,
"learning_rate": 9.365760803434356e-06,
"loss": 0.1374,
"step": 125
},
{
"epoch": 0.5727272727272728,
"grad_norm": 2.015625,
"learning_rate": 9.207500431432115e-06,
"loss": 0.1448,
"step": 126
},
{
"epoch": 0.5772727272727273,
"grad_norm": 1.796875,
"learning_rate": 9.049439566958176e-06,
"loss": 0.1682,
"step": 127
},
{
"epoch": 0.5818181818181818,
"grad_norm": 1.3984375,
"learning_rate": 8.89161800098989e-06,
"loss": 0.1063,
"step": 128
},
{
"epoch": 0.5863636363636363,
"grad_norm": 1.7734375,
"learning_rate": 8.734075464262507e-06,
"loss": 0.1312,
"step": 129
},
{
"epoch": 0.5909090909090909,
"grad_norm": 1.6796875,
"learning_rate": 8.576851617267151e-06,
"loss": 0.139,
"step": 130
},
{
"epoch": 0.5954545454545455,
"grad_norm": 1.859375,
"learning_rate": 8.419986040266502e-06,
"loss": 0.1566,
"step": 131
},
{
"epoch": 0.6,
"grad_norm": 1.71875,
"learning_rate": 8.263518223330698e-06,
"loss": 0.1398,
"step": 132
},
{
"epoch": 0.6045454545454545,
"grad_norm": 1.5625,
"learning_rate": 8.107487556395902e-06,
"loss": 0.1031,
"step": 133
},
{
"epoch": 0.6090909090909091,
"grad_norm": 1.4921875,
"learning_rate": 7.951933319348095e-06,
"loss": 0.1274,
"step": 134
},
{
"epoch": 0.6136363636363636,
"grad_norm": 2.0625,
"learning_rate": 7.796894672134594e-06,
"loss": 0.1655,
"step": 135
},
{
"epoch": 0.6181818181818182,
"grad_norm": 2.265625,
"learning_rate": 7.642410644905726e-06,
"loss": 0.1554,
"step": 136
},
{
"epoch": 0.6227272727272727,
"grad_norm": 1.7265625,
"learning_rate": 7.488520128189209e-06,
"loss": 0.133,
"step": 137
},
{
"epoch": 0.6272727272727273,
"grad_norm": 1.75,
"learning_rate": 7.335261863099652e-06,
"loss": 0.1109,
"step": 138
},
{
"epoch": 0.6318181818181818,
"grad_norm": 2.4375,
"learning_rate": 7.182674431585703e-06,
"loss": 0.1165,
"step": 139
},
{
"epoch": 0.6363636363636364,
"grad_norm": 1.59375,
"learning_rate": 7.0307962467172555e-06,
"loss": 0.1328,
"step": 140
},
{
"epoch": 0.6409090909090909,
"grad_norm": 1.7265625,
"learning_rate": 6.87966554301513e-06,
"loss": 0.1078,
"step": 141
},
{
"epoch": 0.6454545454545455,
"grad_norm": 1.7265625,
"learning_rate": 6.729320366825785e-06,
"loss": 0.1412,
"step": 142
},
{
"epoch": 0.65,
"grad_norm": 2.34375,
"learning_rate": 6.579798566743314e-06,
"loss": 0.1246,
"step": 143
},
{
"epoch": 0.6545454545454545,
"grad_norm": 1.6328125,
"learning_rate": 6.431137784081283e-06,
"loss": 0.1262,
"step": 144
},
{
"epoch": 0.6590909090909091,
"grad_norm": 2.375,
"learning_rate": 6.283375443396726e-06,
"loss": 0.1617,
"step": 145
},
{
"epoch": 0.6636363636363637,
"grad_norm": 1.4609375,
"learning_rate": 6.136548743068713e-06,
"loss": 0.1579,
"step": 146
},
{
"epoch": 0.6681818181818182,
"grad_norm": 1.8515625,
"learning_rate": 5.990694645933866e-06,
"loss": 0.1222,
"step": 147
},
{
"epoch": 0.6727272727272727,
"grad_norm": 2.328125,
"learning_rate": 5.845849869981137e-06,
"loss": 0.1382,
"step": 148
},
{
"epoch": 0.6772727272727272,
"grad_norm": 1.8828125,
"learning_rate": 5.702050879108284e-06,
"loss": 0.1856,
"step": 149
},
{
"epoch": 0.6818181818181818,
"grad_norm": 2.046875,
"learning_rate": 5.559333873942259e-06,
"loss": 0.201,
"step": 150
},
{
"epoch": 0.6863636363636364,
"grad_norm": 1.8046875,
"learning_rate": 5.417734782725896e-06,
"loss": 0.1315,
"step": 151
},
{
"epoch": 0.6909090909090909,
"grad_norm": 1.7421875,
"learning_rate": 5.277289252273175e-06,
"loss": 0.1788,
"step": 152
},
{
"epoch": 0.6954545454545454,
"grad_norm": 1.5625,
"learning_rate": 5.138032638995315e-06,
"loss": 0.1264,
"step": 153
},
{
"epoch": 0.7,
"grad_norm": 2.046875,
"learning_rate": 5.000000000000003e-06,
"loss": 0.1586,
"step": 154
},
{
"epoch": 0.7045454545454546,
"grad_norm": 1.6015625,
"learning_rate": 4.863226084265939e-06,
"loss": 0.1565,
"step": 155
},
{
"epoch": 0.7090909090909091,
"grad_norm": 1.9921875,
"learning_rate": 4.727745323894976e-06,
"loss": 0.1435,
"step": 156
},
{
"epoch": 0.7136363636363636,
"grad_norm": 1.6484375,
"learning_rate": 4.593591825444028e-06,
"loss": 0.1468,
"step": 157
},
{
"epoch": 0.7181818181818181,
"grad_norm": 2.078125,
"learning_rate": 4.460799361338898e-06,
"loss": 0.1528,
"step": 158
},
{
"epoch": 0.7227272727272728,
"grad_norm": 1.7109375,
"learning_rate": 4.3294013613722944e-06,
"loss": 0.1714,
"step": 159
},
{
"epoch": 0.7272727272727273,
"grad_norm": 1.734375,
"learning_rate": 4.19943090428802e-06,
"loss": 0.1478,
"step": 160
},
{
"epoch": 0.7318181818181818,
"grad_norm": 1.4765625,
"learning_rate": 4.070920709453597e-06,
"loss": 0.1042,
"step": 161
},
{
"epoch": 0.7363636363636363,
"grad_norm": 2.125,
"learning_rate": 3.943903128623336e-06,
"loss": 0.1378,
"step": 162
},
{
"epoch": 0.740909090909091,
"grad_norm": 1.921875,
"learning_rate": 3.818410137793947e-06,
"loss": 0.1423,
"step": 163
},
{
"epoch": 0.7454545454545455,
"grad_norm": 1.6171875,
"learning_rate": 3.6944733291547784e-06,
"loss": 0.1407,
"step": 164
},
{
"epoch": 0.75,
"grad_norm": 1.4375,
"learning_rate": 3.5721239031346067e-06,
"loss": 0.1169,
"step": 165
},
{
"epoch": 0.7545454545454545,
"grad_norm": 1.6328125,
"learning_rate": 3.4513926605471504e-06,
"loss": 0.1168,
"step": 166
},
{
"epoch": 0.759090909090909,
"grad_norm": 1.6328125,
"learning_rate": 3.3323099948370853e-06,
"loss": 0.1337,
"step": 167
},
{
"epoch": 0.7636363636363637,
"grad_norm": 2.265625,
"learning_rate": 3.2149058844286796e-06,
"loss": 0.1141,
"step": 168
},
{
"epoch": 0.7681818181818182,
"grad_norm": 1.53125,
"learning_rate": 3.099209885178882e-06,
"loss": 0.1203,
"step": 169
},
{
"epoch": 0.7727272727272727,
"grad_norm": 1.78125,
"learning_rate": 2.9852511229367862e-06,
"loss": 0.0953,
"step": 170
},
{
"epoch": 0.7772727272727272,
"grad_norm": 1.8515625,
"learning_rate": 2.8730582862113743e-06,
"loss": 0.1672,
"step": 171
},
{
"epoch": 0.7818181818181819,
"grad_norm": 1.828125,
"learning_rate": 2.7626596189492983e-06,
"loss": 0.1367,
"step": 172
},
{
"epoch": 0.7863636363636364,
"grad_norm": 2.109375,
"learning_rate": 2.6540829134246683e-06,
"loss": 0.1386,
"step": 173
},
{
"epoch": 0.7909090909090909,
"grad_norm": 1.7421875,
"learning_rate": 2.5473555032424534e-06,
"loss": 0.1688,
"step": 174
},
{
"epoch": 0.7954545454545454,
"grad_norm": 1.859375,
"learning_rate": 2.4425042564574186e-06,
"loss": 0.1475,
"step": 175
},
{
"epoch": 0.8,
"grad_norm": 1.6484375,
"learning_rate": 2.339555568810221e-06,
"loss": 0.1601,
"step": 176
},
{
"epoch": 0.8045454545454546,
"grad_norm": 1.4140625,
"learning_rate": 2.2385353570824308e-06,
"loss": 0.1184,
"step": 177
},
{
"epoch": 0.8090909090909091,
"grad_norm": 2.109375,
"learning_rate": 2.1394690525721275e-06,
"loss": 0.1145,
"step": 178
},
{
"epoch": 0.8136363636363636,
"grad_norm": 1.578125,
"learning_rate": 2.0423815946916783e-06,
"loss": 0.1457,
"step": 179
},
{
"epoch": 0.8181818181818182,
"grad_norm": 1.7734375,
"learning_rate": 1.947297424689414e-06,
"loss": 0.117,
"step": 180
},
{
"epoch": 0.8227272727272728,
"grad_norm": 2.03125,
"learning_rate": 1.854240479496643e-06,
"loss": 0.1884,
"step": 181
},
{
"epoch": 0.8272727272727273,
"grad_norm": 1.5546875,
"learning_rate": 1.7632341857016733e-06,
"loss": 0.0915,
"step": 182
},
{
"epoch": 0.8318181818181818,
"grad_norm": 1.7265625,
"learning_rate": 1.6743014536522872e-06,
"loss": 0.1393,
"step": 183
},
{
"epoch": 0.8363636363636363,
"grad_norm": 3.125,
"learning_rate": 1.587464671688187e-06,
"loss": 0.1461,
"step": 184
},
{
"epoch": 0.8409090909090909,
"grad_norm": 1.578125,
"learning_rate": 1.5027457005048573e-06,
"loss": 0.1276,
"step": 185
},
{
"epoch": 0.8454545454545455,
"grad_norm": 2.234375,
"learning_rate": 1.4201658676502294e-06,
"loss": 0.1521,
"step": 186
},
{
"epoch": 0.85,
"grad_norm": 1.5703125,
"learning_rate": 1.339745962155613e-06,
"loss": 0.148,
"step": 187
},
{
"epoch": 0.8545454545454545,
"grad_norm": 1.6875,
"learning_rate": 1.2615062293021508e-06,
"loss": 0.1639,
"step": 188
},
{
"epoch": 0.8590909090909091,
"grad_norm": 1.9375,
"learning_rate": 1.1854663655241804e-06,
"loss": 0.162,
"step": 189
},
{
"epoch": 0.8636363636363636,
"grad_norm": 1.65625,
"learning_rate": 1.1116455134507665e-06,
"loss": 0.146,
"step": 190
},
{
"epoch": 0.8681818181818182,
"grad_norm": 1.765625,
"learning_rate": 1.0400622570866426e-06,
"loss": 0.1364,
"step": 191
},
{
"epoch": 0.8727272727272727,
"grad_norm": 1.8046875,
"learning_rate": 9.707346171337895e-07,
"loss": 0.1333,
"step": 192
},
{
"epoch": 0.8772727272727273,
"grad_norm": 1.3671875,
"learning_rate": 9.036800464548157e-07,
"loss": 0.1336,
"step": 193
},
{
"epoch": 0.8818181818181818,
"grad_norm": 1.703125,
"learning_rate": 8.389154256793042e-07,
"loss": 0.1259,
"step": 194
},
{
"epoch": 0.8863636363636364,
"grad_norm": 1.671875,
"learning_rate": 7.764570589541876e-07,
"loss": 0.1474,
"step": 195
},
{
"epoch": 0.8909090909090909,
"grad_norm": 1.7109375,
"learning_rate": 7.163206698392744e-07,
"loss": 0.1148,
"step": 196
},
{
"epoch": 0.8954545454545455,
"grad_norm": 1.984375,
"learning_rate": 6.585213973489335e-07,
"loss": 0.188,
"step": 197
},
{
"epoch": 0.9,
"grad_norm": 1.4140625,
"learning_rate": 6.030737921409169e-07,
"loss": 0.1234,
"step": 198
},
{
"epoch": 0.9045454545454545,
"grad_norm": 2.28125,
"learning_rate": 5.499918128533155e-07,
"loss": 0.183,
"step": 199
},
{
"epoch": 0.9090909090909091,
"grad_norm": 1.96875,
"learning_rate": 4.992888225905467e-07,
"loss": 0.154,
"step": 200
},
{
"epoch": 0.9136363636363637,
"grad_norm": 1.9296875,
"learning_rate": 4.509775855592613e-07,
"loss": 0.1198,
"step": 201
},
{
"epoch": 0.9181818181818182,
"grad_norm": 1.5234375,
"learning_rate": 4.0507026385502747e-07,
"loss": 0.1361,
"step": 202
},
{
"epoch": 0.9227272727272727,
"grad_norm": 1.765625,
"learning_rate": 3.615784144005796e-07,
"loss": 0.1278,
"step": 203
},
{
"epoch": 0.9272727272727272,
"grad_norm": 1.8125,
"learning_rate": 3.2051298603643754e-07,
"loss": 0.1477,
"step": 204
},
{
"epoch": 0.9318181818181818,
"grad_norm": 1.9765625,
"learning_rate": 2.818843167645835e-07,
"loss": 0.127,
"step": 205
},
{
"epoch": 0.9363636363636364,
"grad_norm": 1.421875,
"learning_rate": 2.4570213114592957e-07,
"loss": 0.1009,
"step": 206
},
{
"epoch": 0.9409090909090909,
"grad_norm": 1.7421875,
"learning_rate": 2.119755378522137e-07,
"loss": 0.142,
"step": 207
},
{
"epoch": 0.9454545454545454,
"grad_norm": 1.5390625,
"learning_rate": 1.8071302737293294e-07,
"loss": 0.1535,
"step": 208
},
{
"epoch": 0.95,
"grad_norm": 1.671875,
"learning_rate": 1.519224698779198e-07,
"loss": 0.1273,
"step": 209
},
{
"epoch": 0.9545454545454546,
"grad_norm": 1.6640625,
"learning_rate": 1.2561111323605714e-07,
"loss": 0.1358,
"step": 210
},
{
"epoch": 0.9590909090909091,
"grad_norm": 1.7109375,
"learning_rate": 1.0178558119067316e-07,
"loss": 0.1554,
"step": 211
},
{
"epoch": 0.9636363636363636,
"grad_norm": 1.609375,
"learning_rate": 8.04518716920466e-08,
"loss": 0.1452,
"step": 212
},
{
"epoch": 0.9681818181818181,
"grad_norm": 1.6484375,
"learning_rate": 6.161535538745877e-08,
"loss": 0.1299,
"step": 213
},
{
"epoch": 0.9727272727272728,
"grad_norm": 2.046875,
"learning_rate": 4.528077426915412e-08,
"loss": 0.1522,
"step": 214
},
{
"epoch": 0.9772727272727273,
"grad_norm": 1.8828125,
"learning_rate": 3.1452240480577265e-08,
"loss": 0.1676,
"step": 215
},
{
"epoch": 0.9818181818181818,
"grad_norm": 1.5390625,
"learning_rate": 2.013323528115674e-08,
"loss": 0.0946,
"step": 216
},
{
"epoch": 0.9863636363636363,
"grad_norm": 1.8671875,
"learning_rate": 1.1326608169920373e-08,
"loss": 0.1991,
"step": 217
},
{
"epoch": 0.990909090909091,
"grad_norm": 1.734375,
"learning_rate": 5.034576168149175e-09,
"loss": 0.1605,
"step": 218
},
{
"epoch": 0.9954545454545455,
"grad_norm": 1.2109375,
"learning_rate": 1.2587232612493172e-09,
"loss": 0.1109,
"step": 219
},
{
"epoch": 1.0,
"grad_norm": 1.4609375,
"learning_rate": 0.0,
"loss": 0.0889,
"step": 220
},
{
"epoch": 1.0,
"step": 220,
"total_flos": 2.7371800344553062e+17,
"train_loss": 0.184959452226758,
"train_runtime": 985.0488,
"train_samples_per_second": 7.13,
"train_steps_per_second": 0.223
}
],
"logging_steps": 1.0,
"max_steps": 220,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10000,
"total_flos": 2.7371800344553062e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}