ToastyPigeon's picture
Training in progress, step 585, checkpoint
b6b1ece verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 30,
"global_step": 585,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017094017094017094,
"grad_norm": 0.640625,
"learning_rate": 1.5e-06,
"loss": 2.347,
"step": 1
},
{
"epoch": 0.0017094017094017094,
"eval_loss": 2.301453113555908,
"eval_runtime": 86.8185,
"eval_samples_per_second": 2.949,
"eval_steps_per_second": 0.495,
"step": 1
},
{
"epoch": 0.003418803418803419,
"grad_norm": 0.64453125,
"learning_rate": 3e-06,
"loss": 2.3765,
"step": 2
},
{
"epoch": 0.005128205128205128,
"grad_norm": 0.66015625,
"learning_rate": 4.5e-06,
"loss": 2.4015,
"step": 3
},
{
"epoch": 0.006837606837606838,
"grad_norm": 0.6953125,
"learning_rate": 6e-06,
"loss": 2.307,
"step": 4
},
{
"epoch": 0.008547008547008548,
"grad_norm": 0.67578125,
"learning_rate": 7.5e-06,
"loss": 2.4666,
"step": 5
},
{
"epoch": 0.010256410256410256,
"grad_norm": 0.96484375,
"learning_rate": 9e-06,
"loss": 2.3027,
"step": 6
},
{
"epoch": 0.011965811965811967,
"grad_norm": 0.6171875,
"learning_rate": 1.05e-05,
"loss": 2.4554,
"step": 7
},
{
"epoch": 0.013675213675213675,
"grad_norm": 0.64453125,
"learning_rate": 1.2e-05,
"loss": 2.4017,
"step": 8
},
{
"epoch": 0.015384615384615385,
"grad_norm": 0.57421875,
"learning_rate": 1.3500000000000001e-05,
"loss": 2.3931,
"step": 9
},
{
"epoch": 0.017094017094017096,
"grad_norm": 1.0703125,
"learning_rate": 1.5e-05,
"loss": 2.3904,
"step": 10
},
{
"epoch": 0.018803418803418803,
"grad_norm": 1.359375,
"learning_rate": 1.65e-05,
"loss": 2.4122,
"step": 11
},
{
"epoch": 0.020512820512820513,
"grad_norm": 0.5078125,
"learning_rate": 1.8e-05,
"loss": 2.2968,
"step": 12
},
{
"epoch": 0.022222222222222223,
"grad_norm": 0.76953125,
"learning_rate": 1.95e-05,
"loss": 2.3248,
"step": 13
},
{
"epoch": 0.023931623931623933,
"grad_norm": 0.85546875,
"learning_rate": 2.1e-05,
"loss": 2.3328,
"step": 14
},
{
"epoch": 0.02564102564102564,
"grad_norm": 0.58203125,
"learning_rate": 2.25e-05,
"loss": 2.3261,
"step": 15
},
{
"epoch": 0.02735042735042735,
"grad_norm": 0.7109375,
"learning_rate": 2.4e-05,
"loss": 2.3912,
"step": 16
},
{
"epoch": 0.02905982905982906,
"grad_norm": 0.58203125,
"learning_rate": 2.55e-05,
"loss": 2.2254,
"step": 17
},
{
"epoch": 0.03076923076923077,
"grad_norm": 0.58203125,
"learning_rate": 2.7000000000000002e-05,
"loss": 2.3051,
"step": 18
},
{
"epoch": 0.03247863247863248,
"grad_norm": 0.54296875,
"learning_rate": 2.8499999999999998e-05,
"loss": 2.266,
"step": 19
},
{
"epoch": 0.03418803418803419,
"grad_norm": 0.54296875,
"learning_rate": 3e-05,
"loss": 2.2876,
"step": 20
},
{
"epoch": 0.035897435897435895,
"grad_norm": 0.5078125,
"learning_rate": 2.99997797141509e-05,
"loss": 2.3568,
"step": 21
},
{
"epoch": 0.037606837606837605,
"grad_norm": 0.60546875,
"learning_rate": 2.9999118863414234e-05,
"loss": 2.37,
"step": 22
},
{
"epoch": 0.039316239316239315,
"grad_norm": 0.515625,
"learning_rate": 2.9998017468221747e-05,
"loss": 2.2132,
"step": 23
},
{
"epoch": 0.041025641025641026,
"grad_norm": 0.54296875,
"learning_rate": 2.9996475562625607e-05,
"loss": 2.3333,
"step": 24
},
{
"epoch": 0.042735042735042736,
"grad_norm": 0.51171875,
"learning_rate": 2.9994493194297398e-05,
"loss": 2.3721,
"step": 25
},
{
"epoch": 0.044444444444444446,
"grad_norm": 0.5078125,
"learning_rate": 2.999207042452661e-05,
"loss": 2.3663,
"step": 26
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.5390625,
"learning_rate": 2.998920732821878e-05,
"loss": 2.2828,
"step": 27
},
{
"epoch": 0.04786324786324787,
"grad_norm": 0.62890625,
"learning_rate": 2.9985903993893144e-05,
"loss": 2.2689,
"step": 28
},
{
"epoch": 0.04957264957264957,
"grad_norm": 0.55078125,
"learning_rate": 2.998216052367993e-05,
"loss": 2.2138,
"step": 29
},
{
"epoch": 0.05128205128205128,
"grad_norm": 0.5625,
"learning_rate": 2.9977977033317164e-05,
"loss": 2.306,
"step": 30
},
{
"epoch": 0.05128205128205128,
"eval_loss": 2.2630789279937744,
"eval_runtime": 87.4474,
"eval_samples_per_second": 2.927,
"eval_steps_per_second": 0.492,
"step": 30
},
{
"epoch": 0.05299145299145299,
"grad_norm": 0.515625,
"learning_rate": 2.997335365214713e-05,
"loss": 2.296,
"step": 31
},
{
"epoch": 0.0547008547008547,
"grad_norm": 1.140625,
"learning_rate": 2.996829052311235e-05,
"loss": 2.3959,
"step": 32
},
{
"epoch": 0.05641025641025641,
"grad_norm": 0.53125,
"learning_rate": 2.9962787802751164e-05,
"loss": 2.386,
"step": 33
},
{
"epoch": 0.05811965811965812,
"grad_norm": 0.4921875,
"learning_rate": 2.9956845661192886e-05,
"loss": 2.3119,
"step": 34
},
{
"epoch": 0.05982905982905983,
"grad_norm": 0.52734375,
"learning_rate": 2.9950464282152565e-05,
"loss": 2.4883,
"step": 35
},
{
"epoch": 0.06153846153846154,
"grad_norm": 0.5078125,
"learning_rate": 2.9943643862925295e-05,
"loss": 2.3211,
"step": 36
},
{
"epoch": 0.06324786324786325,
"grad_norm": 0.51171875,
"learning_rate": 2.9936384614380105e-05,
"loss": 2.3355,
"step": 37
},
{
"epoch": 0.06495726495726496,
"grad_norm": 0.51953125,
"learning_rate": 2.992868676095344e-05,
"loss": 2.2054,
"step": 38
},
{
"epoch": 0.06666666666666667,
"grad_norm": 1.28125,
"learning_rate": 2.992055054064225e-05,
"loss": 2.252,
"step": 39
},
{
"epoch": 0.06837606837606838,
"grad_norm": 0.49609375,
"learning_rate": 2.9911976204996588e-05,
"loss": 2.1774,
"step": 40
},
{
"epoch": 0.07008547008547009,
"grad_norm": 0.48046875,
"learning_rate": 2.990296401911187e-05,
"loss": 2.2469,
"step": 41
},
{
"epoch": 0.07179487179487179,
"grad_norm": 0.52734375,
"learning_rate": 2.9893514261620653e-05,
"loss": 2.3641,
"step": 42
},
{
"epoch": 0.0735042735042735,
"grad_norm": 0.49609375,
"learning_rate": 2.988362722468405e-05,
"loss": 2.2189,
"step": 43
},
{
"epoch": 0.07521367521367521,
"grad_norm": 0.52734375,
"learning_rate": 2.9873303213982663e-05,
"loss": 2.2367,
"step": 44
},
{
"epoch": 0.07692307692307693,
"grad_norm": 0.54296875,
"learning_rate": 2.9862542548707153e-05,
"loss": 2.2121,
"step": 45
},
{
"epoch": 0.07863247863247863,
"grad_norm": 0.53125,
"learning_rate": 2.9851345561548373e-05,
"loss": 2.3132,
"step": 46
},
{
"epoch": 0.08034188034188035,
"grad_norm": 0.55859375,
"learning_rate": 2.9839712598687062e-05,
"loss": 2.2336,
"step": 47
},
{
"epoch": 0.08205128205128205,
"grad_norm": 0.5703125,
"learning_rate": 2.982764401978317e-05,
"loss": 2.3433,
"step": 48
},
{
"epoch": 0.08376068376068375,
"grad_norm": 0.546875,
"learning_rate": 2.981514019796471e-05,
"loss": 2.2469,
"step": 49
},
{
"epoch": 0.08547008547008547,
"grad_norm": 0.640625,
"learning_rate": 2.9802201519816253e-05,
"loss": 2.4495,
"step": 50
},
{
"epoch": 0.08717948717948718,
"grad_norm": 0.51171875,
"learning_rate": 2.978882838536695e-05,
"loss": 2.319,
"step": 51
},
{
"epoch": 0.08888888888888889,
"grad_norm": 0.5078125,
"learning_rate": 2.9775021208078166e-05,
"loss": 2.2656,
"step": 52
},
{
"epoch": 0.0905982905982906,
"grad_norm": 0.5390625,
"learning_rate": 2.9760780414830717e-05,
"loss": 2.3204,
"step": 53
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.50390625,
"learning_rate": 2.9746106445911658e-05,
"loss": 2.3461,
"step": 54
},
{
"epoch": 0.09401709401709402,
"grad_norm": 0.51953125,
"learning_rate": 2.9730999755000654e-05,
"loss": 2.3504,
"step": 55
},
{
"epoch": 0.09572649572649573,
"grad_norm": 0.515625,
"learning_rate": 2.9715460809155993e-05,
"loss": 2.235,
"step": 56
},
{
"epoch": 0.09743589743589744,
"grad_norm": 0.482421875,
"learning_rate": 2.9699490088800107e-05,
"loss": 2.3713,
"step": 57
},
{
"epoch": 0.09914529914529914,
"grad_norm": 0.515625,
"learning_rate": 2.968308808770475e-05,
"loss": 2.2396,
"step": 58
},
{
"epoch": 0.10085470085470086,
"grad_norm": 0.57421875,
"learning_rate": 2.9666255312975704e-05,
"loss": 2.2702,
"step": 59
},
{
"epoch": 0.10256410256410256,
"grad_norm": 0.5,
"learning_rate": 2.9648992285037126e-05,
"loss": 2.1792,
"step": 60
},
{
"epoch": 0.10256410256410256,
"eval_loss": 2.235595941543579,
"eval_runtime": 87.3908,
"eval_samples_per_second": 2.929,
"eval_steps_per_second": 0.492,
"step": 60
},
{
"epoch": 0.10427350427350428,
"grad_norm": 0.5078125,
"learning_rate": 2.9631299537615433e-05,
"loss": 2.2673,
"step": 61
},
{
"epoch": 0.10598290598290598,
"grad_norm": 0.494140625,
"learning_rate": 2.9613177617722826e-05,
"loss": 2.1882,
"step": 62
},
{
"epoch": 0.1076923076923077,
"grad_norm": 0.54296875,
"learning_rate": 2.9594627085640357e-05,
"loss": 2.201,
"step": 63
},
{
"epoch": 0.1094017094017094,
"grad_norm": 0.55859375,
"learning_rate": 2.957564851490061e-05,
"loss": 2.2973,
"step": 64
},
{
"epoch": 0.1111111111111111,
"grad_norm": 0.55078125,
"learning_rate": 2.955624249226999e-05,
"loss": 2.2497,
"step": 65
},
{
"epoch": 0.11282051282051282,
"grad_norm": 0.5234375,
"learning_rate": 2.9536409617730553e-05,
"loss": 2.2527,
"step": 66
},
{
"epoch": 0.11452991452991453,
"grad_norm": 0.55078125,
"learning_rate": 2.9516150504461473e-05,
"loss": 2.2438,
"step": 67
},
{
"epoch": 0.11623931623931624,
"grad_norm": 0.5234375,
"learning_rate": 2.9495465778820076e-05,
"loss": 2.2101,
"step": 68
},
{
"epoch": 0.11794871794871795,
"grad_norm": 0.5546875,
"learning_rate": 2.9474356080322488e-05,
"loss": 2.2613,
"step": 69
},
{
"epoch": 0.11965811965811966,
"grad_norm": 0.53515625,
"learning_rate": 2.945282206162384e-05,
"loss": 2.2543,
"step": 70
},
{
"epoch": 0.12136752136752137,
"grad_norm": 0.51953125,
"learning_rate": 2.9430864388498117e-05,
"loss": 2.1064,
"step": 71
},
{
"epoch": 0.12307692307692308,
"grad_norm": 0.52734375,
"learning_rate": 2.940848373981754e-05,
"loss": 2.2559,
"step": 72
},
{
"epoch": 0.12478632478632479,
"grad_norm": 0.5546875,
"learning_rate": 2.938568080753162e-05,
"loss": 2.4249,
"step": 73
},
{
"epoch": 0.1264957264957265,
"grad_norm": 0.5390625,
"learning_rate": 2.936245629664574e-05,
"loss": 2.1672,
"step": 74
},
{
"epoch": 0.1282051282051282,
"grad_norm": 0.51171875,
"learning_rate": 2.933881092519934e-05,
"loss": 2.1782,
"step": 75
},
{
"epoch": 0.12991452991452992,
"grad_norm": 0.54296875,
"learning_rate": 2.9314745424243755e-05,
"loss": 2.2672,
"step": 76
},
{
"epoch": 0.13162393162393163,
"grad_norm": 0.54296875,
"learning_rate": 2.9290260537819593e-05,
"loss": 2.3463,
"step": 77
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.52734375,
"learning_rate": 2.9265357022933717e-05,
"loss": 2.3062,
"step": 78
},
{
"epoch": 0.13504273504273503,
"grad_norm": 0.5625,
"learning_rate": 2.9240035649535893e-05,
"loss": 2.2582,
"step": 79
},
{
"epoch": 0.13675213675213677,
"grad_norm": 0.52734375,
"learning_rate": 2.921429720049491e-05,
"loss": 2.2013,
"step": 80
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.53515625,
"learning_rate": 2.918814247157443e-05,
"loss": 2.3769,
"step": 81
},
{
"epoch": 0.14017094017094017,
"grad_norm": 0.546875,
"learning_rate": 2.9161572271408383e-05,
"loss": 2.1824,
"step": 82
},
{
"epoch": 0.14188034188034188,
"grad_norm": 0.55859375,
"learning_rate": 2.913458742147594e-05,
"loss": 2.3269,
"step": 83
},
{
"epoch": 0.14358974358974358,
"grad_norm": 0.62109375,
"learning_rate": 2.910718875607612e-05,
"loss": 2.2811,
"step": 84
},
{
"epoch": 0.1452991452991453,
"grad_norm": 0.5703125,
"learning_rate": 2.9079377122302015e-05,
"loss": 2.2213,
"step": 85
},
{
"epoch": 0.147008547008547,
"grad_norm": 0.5390625,
"learning_rate": 2.9051153380014605e-05,
"loss": 2.179,
"step": 86
},
{
"epoch": 0.14871794871794872,
"grad_norm": 0.546875,
"learning_rate": 2.9022518401816118e-05,
"loss": 2.1934,
"step": 87
},
{
"epoch": 0.15042735042735042,
"grad_norm": 0.5234375,
"learning_rate": 2.8993473073023123e-05,
"loss": 2.379,
"step": 88
},
{
"epoch": 0.15213675213675212,
"grad_norm": 0.58203125,
"learning_rate": 2.8964018291639117e-05,
"loss": 2.1847,
"step": 89
},
{
"epoch": 0.15384615384615385,
"grad_norm": 0.5703125,
"learning_rate": 2.8934154968326777e-05,
"loss": 2.2576,
"step": 90
},
{
"epoch": 0.15384615384615385,
"eval_loss": 2.2298240661621094,
"eval_runtime": 87.3674,
"eval_samples_per_second": 2.93,
"eval_steps_per_second": 0.492,
"step": 90
},
{
"epoch": 0.15555555555555556,
"grad_norm": 0.53515625,
"learning_rate": 2.890388402637978e-05,
"loss": 2.2151,
"step": 91
},
{
"epoch": 0.15726495726495726,
"grad_norm": 0.57421875,
"learning_rate": 2.8873206401694296e-05,
"loss": 2.239,
"step": 92
},
{
"epoch": 0.15897435897435896,
"grad_norm": 0.6328125,
"learning_rate": 2.8842123042740018e-05,
"loss": 2.1789,
"step": 93
},
{
"epoch": 0.1606837606837607,
"grad_norm": 0.609375,
"learning_rate": 2.8810634910530858e-05,
"loss": 2.2505,
"step": 94
},
{
"epoch": 0.1623931623931624,
"grad_norm": 0.55078125,
"learning_rate": 2.8778742978595237e-05,
"loss": 2.2437,
"step": 95
},
{
"epoch": 0.1641025641025641,
"grad_norm": 0.6171875,
"learning_rate": 2.8746448232945957e-05,
"loss": 2.3353,
"step": 96
},
{
"epoch": 0.1658119658119658,
"grad_norm": 0.62109375,
"learning_rate": 2.8713751672049763e-05,
"loss": 2.1599,
"step": 97
},
{
"epoch": 0.1675213675213675,
"grad_norm": 0.59375,
"learning_rate": 2.8680654306796423e-05,
"loss": 2.1994,
"step": 98
},
{
"epoch": 0.16923076923076924,
"grad_norm": 0.53515625,
"learning_rate": 2.8647157160467517e-05,
"loss": 2.1375,
"step": 99
},
{
"epoch": 0.17094017094017094,
"grad_norm": 0.578125,
"learning_rate": 2.8613261268704776e-05,
"loss": 2.3547,
"step": 100
},
{
"epoch": 0.17264957264957265,
"grad_norm": 0.55078125,
"learning_rate": 2.8578967679478055e-05,
"loss": 2.0798,
"step": 101
},
{
"epoch": 0.17435897435897435,
"grad_norm": 0.6171875,
"learning_rate": 2.8544277453052978e-05,
"loss": 2.3431,
"step": 102
},
{
"epoch": 0.17606837606837608,
"grad_norm": 0.55078125,
"learning_rate": 2.850919166195808e-05,
"loss": 2.1824,
"step": 103
},
{
"epoch": 0.17777777777777778,
"grad_norm": 0.6015625,
"learning_rate": 2.847371139095173e-05,
"loss": 2.2008,
"step": 104
},
{
"epoch": 0.1794871794871795,
"grad_norm": 0.5546875,
"learning_rate": 2.8437837736988546e-05,
"loss": 2.238,
"step": 105
},
{
"epoch": 0.1811965811965812,
"grad_norm": 0.5859375,
"learning_rate": 2.8401571809185472e-05,
"loss": 2.2602,
"step": 106
},
{
"epoch": 0.1829059829059829,
"grad_norm": 0.625,
"learning_rate": 2.836491472878753e-05,
"loss": 2.196,
"step": 107
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.7578125,
"learning_rate": 2.8327867629133112e-05,
"loss": 2.1421,
"step": 108
},
{
"epoch": 0.18632478632478633,
"grad_norm": 0.5859375,
"learning_rate": 2.8290431655618965e-05,
"loss": 2.1574,
"step": 109
},
{
"epoch": 0.18803418803418803,
"grad_norm": 0.58203125,
"learning_rate": 2.8252607965664764e-05,
"loss": 2.13,
"step": 110
},
{
"epoch": 0.18974358974358974,
"grad_norm": 0.60546875,
"learning_rate": 2.8214397728677342e-05,
"loss": 2.2223,
"step": 111
},
{
"epoch": 0.19145299145299147,
"grad_norm": 0.56640625,
"learning_rate": 2.8175802126014526e-05,
"loss": 2.2207,
"step": 112
},
{
"epoch": 0.19316239316239317,
"grad_norm": 0.61328125,
"learning_rate": 2.8136822350948608e-05,
"loss": 2.2286,
"step": 113
},
{
"epoch": 0.19487179487179487,
"grad_norm": 0.6171875,
"learning_rate": 2.8097459608629454e-05,
"loss": 2.2064,
"step": 114
},
{
"epoch": 0.19658119658119658,
"grad_norm": 0.5625,
"learning_rate": 2.805771511604727e-05,
"loss": 2.1825,
"step": 115
},
{
"epoch": 0.19829059829059828,
"grad_norm": 0.5546875,
"learning_rate": 2.8017590101994924e-05,
"loss": 2.2322,
"step": 116
},
{
"epoch": 0.2,
"grad_norm": 0.62890625,
"learning_rate": 2.7977085807030013e-05,
"loss": 2.2489,
"step": 117
},
{
"epoch": 0.20170940170940171,
"grad_norm": 0.56640625,
"learning_rate": 2.793620348343647e-05,
"loss": 2.3559,
"step": 118
},
{
"epoch": 0.20341880341880342,
"grad_norm": 0.578125,
"learning_rate": 2.789494439518584e-05,
"loss": 2.126,
"step": 119
},
{
"epoch": 0.20512820512820512,
"grad_norm": 0.578125,
"learning_rate": 2.7853309817898244e-05,
"loss": 2.1577,
"step": 120
},
{
"epoch": 0.20512820512820512,
"eval_loss": 2.2236061096191406,
"eval_runtime": 87.3684,
"eval_samples_per_second": 2.93,
"eval_steps_per_second": 0.492,
"step": 120
},
{
"epoch": 0.20683760683760682,
"grad_norm": 0.61328125,
"learning_rate": 2.7811301038802903e-05,
"loss": 2.3332,
"step": 121
},
{
"epoch": 0.20854700854700856,
"grad_norm": 0.578125,
"learning_rate": 2.776891935669836e-05,
"loss": 2.279,
"step": 122
},
{
"epoch": 0.21025641025641026,
"grad_norm": 0.56640625,
"learning_rate": 2.77261660819123e-05,
"loss": 2.2138,
"step": 123
},
{
"epoch": 0.21196581196581196,
"grad_norm": 0.5703125,
"learning_rate": 2.7683042536261066e-05,
"loss": 2.1529,
"step": 124
},
{
"epoch": 0.21367521367521367,
"grad_norm": 0.5625,
"learning_rate": 2.763955005300879e-05,
"loss": 2.2875,
"step": 125
},
{
"epoch": 0.2153846153846154,
"grad_norm": 0.59765625,
"learning_rate": 2.7595689976826144e-05,
"loss": 2.1927,
"step": 126
},
{
"epoch": 0.2170940170940171,
"grad_norm": 0.6171875,
"learning_rate": 2.755146366374879e-05,
"loss": 2.2004,
"step": 127
},
{
"epoch": 0.2188034188034188,
"grad_norm": 0.60546875,
"learning_rate": 2.7506872481135472e-05,
"loss": 2.1822,
"step": 128
},
{
"epoch": 0.2205128205128205,
"grad_norm": 0.578125,
"learning_rate": 2.7461917807625683e-05,
"loss": 2.1571,
"step": 129
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.58203125,
"learning_rate": 2.741660103309711e-05,
"loss": 2.2019,
"step": 130
},
{
"epoch": 0.22393162393162394,
"grad_norm": 1.015625,
"learning_rate": 2.7370923558622608e-05,
"loss": 2.2128,
"step": 131
},
{
"epoch": 0.22564102564102564,
"grad_norm": 1.2421875,
"learning_rate": 2.7324886796426928e-05,
"loss": 2.1621,
"step": 132
},
{
"epoch": 0.22735042735042735,
"grad_norm": 0.63671875,
"learning_rate": 2.7278492169843002e-05,
"loss": 2.1667,
"step": 133
},
{
"epoch": 0.22905982905982905,
"grad_norm": 0.58203125,
"learning_rate": 2.723174111326799e-05,
"loss": 2.1954,
"step": 134
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.61328125,
"learning_rate": 2.71846350721189e-05,
"loss": 2.2353,
"step": 135
},
{
"epoch": 0.23247863247863249,
"grad_norm": 0.59375,
"learning_rate": 2.7137175502787905e-05,
"loss": 2.1927,
"step": 136
},
{
"epoch": 0.2341880341880342,
"grad_norm": 0.609375,
"learning_rate": 2.708936387259733e-05,
"loss": 2.3303,
"step": 137
},
{
"epoch": 0.2358974358974359,
"grad_norm": 0.625,
"learning_rate": 2.7041201659754275e-05,
"loss": 2.2955,
"step": 138
},
{
"epoch": 0.2376068376068376,
"grad_norm": 0.66015625,
"learning_rate": 2.6992690353304906e-05,
"loss": 2.1364,
"step": 139
},
{
"epoch": 0.23931623931623933,
"grad_norm": 0.6171875,
"learning_rate": 2.694383145308842e-05,
"loss": 2.2165,
"step": 140
},
{
"epoch": 0.24102564102564103,
"grad_norm": 0.578125,
"learning_rate": 2.6894626469690695e-05,
"loss": 2.1733,
"step": 141
},
{
"epoch": 0.24273504273504273,
"grad_norm": 0.58984375,
"learning_rate": 2.6845076924397558e-05,
"loss": 2.2228,
"step": 142
},
{
"epoch": 0.24444444444444444,
"grad_norm": 0.625,
"learning_rate": 2.6795184349147767e-05,
"loss": 2.1683,
"step": 143
},
{
"epoch": 0.24615384615384617,
"grad_norm": 0.58203125,
"learning_rate": 2.6744950286485654e-05,
"loss": 2.1653,
"step": 144
},
{
"epoch": 0.24786324786324787,
"grad_norm": 0.6484375,
"learning_rate": 2.66943762895134e-05,
"loss": 2.3011,
"step": 145
},
{
"epoch": 0.24957264957264957,
"grad_norm": 0.65625,
"learning_rate": 2.6643463921843072e-05,
"loss": 2.1627,
"step": 146
},
{
"epoch": 0.2512820512820513,
"grad_norm": 0.5859375,
"learning_rate": 2.659221475754822e-05,
"loss": 2.1715,
"step": 147
},
{
"epoch": 0.252991452991453,
"grad_norm": 0.578125,
"learning_rate": 2.654063038111526e-05,
"loss": 2.1621,
"step": 148
},
{
"epoch": 0.2547008547008547,
"grad_norm": 0.578125,
"learning_rate": 2.648871238739447e-05,
"loss": 2.2397,
"step": 149
},
{
"epoch": 0.2564102564102564,
"grad_norm": 0.60546875,
"learning_rate": 2.6436462381550656e-05,
"loss": 2.1493,
"step": 150
},
{
"epoch": 0.2564102564102564,
"eval_loss": 2.2221291065216064,
"eval_runtime": 87.3659,
"eval_samples_per_second": 2.93,
"eval_steps_per_second": 0.492,
"step": 150
},
{
"epoch": 0.25811965811965815,
"grad_norm": 0.58984375,
"learning_rate": 2.638388197901356e-05,
"loss": 2.1664,
"step": 151
},
{
"epoch": 0.25982905982905985,
"grad_norm": 0.66015625,
"learning_rate": 2.6330972805427904e-05,
"loss": 2.1582,
"step": 152
},
{
"epoch": 0.26153846153846155,
"grad_norm": 0.578125,
"learning_rate": 2.627773649660312e-05,
"loss": 2.2686,
"step": 153
},
{
"epoch": 0.26324786324786326,
"grad_norm": 0.64453125,
"learning_rate": 2.6224174698462793e-05,
"loss": 2.2141,
"step": 154
},
{
"epoch": 0.26495726495726496,
"grad_norm": 0.66796875,
"learning_rate": 2.617028906699375e-05,
"loss": 2.2978,
"step": 155
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.5859375,
"learning_rate": 2.611608126819488e-05,
"loss": 2.2701,
"step": 156
},
{
"epoch": 0.26837606837606837,
"grad_norm": 0.62890625,
"learning_rate": 2.6061552978025613e-05,
"loss": 2.1505,
"step": 157
},
{
"epoch": 0.27008547008547007,
"grad_norm": 0.5859375,
"learning_rate": 2.6006705882354133e-05,
"loss": 2.0904,
"step": 158
},
{
"epoch": 0.2717948717948718,
"grad_norm": 0.58203125,
"learning_rate": 2.595154167690521e-05,
"loss": 2.1801,
"step": 159
},
{
"epoch": 0.27350427350427353,
"grad_norm": 0.58984375,
"learning_rate": 2.58960620672078e-05,
"loss": 2.1752,
"step": 160
},
{
"epoch": 0.27521367521367524,
"grad_norm": 0.59765625,
"learning_rate": 2.5840268768542317e-05,
"loss": 2.2138,
"step": 161
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.57421875,
"learning_rate": 2.5784163505887594e-05,
"loss": 1.9268,
"step": 162
},
{
"epoch": 0.27863247863247864,
"grad_norm": 0.625,
"learning_rate": 2.5727748013867548e-05,
"loss": 2.1888,
"step": 163
},
{
"epoch": 0.28034188034188035,
"grad_norm": 0.58984375,
"learning_rate": 2.5671024036697558e-05,
"loss": 2.1613,
"step": 164
},
{
"epoch": 0.28205128205128205,
"grad_norm": 0.59765625,
"learning_rate": 2.5613993328130528e-05,
"loss": 2.1137,
"step": 165
},
{
"epoch": 0.28376068376068375,
"grad_norm": 0.6328125,
"learning_rate": 2.5556657651402683e-05,
"loss": 2.1211,
"step": 166
},
{
"epoch": 0.28547008547008546,
"grad_norm": 0.6171875,
"learning_rate": 2.5499018779179032e-05,
"loss": 2.1484,
"step": 167
},
{
"epoch": 0.28717948717948716,
"grad_norm": 0.5703125,
"learning_rate": 2.5441078493498586e-05,
"loss": 2.1331,
"step": 168
},
{
"epoch": 0.28888888888888886,
"grad_norm": 0.75390625,
"learning_rate": 2.538283858571924e-05,
"loss": 2.0982,
"step": 169
},
{
"epoch": 0.2905982905982906,
"grad_norm": 0.63671875,
"learning_rate": 2.5324300856462403e-05,
"loss": 2.1295,
"step": 170
},
{
"epoch": 0.2923076923076923,
"grad_norm": 0.61328125,
"learning_rate": 2.5265467115557327e-05,
"loss": 2.1661,
"step": 171
},
{
"epoch": 0.294017094017094,
"grad_norm": 0.6171875,
"learning_rate": 2.5206339181985137e-05,
"loss": 2.0045,
"step": 172
},
{
"epoch": 0.29572649572649573,
"grad_norm": 0.61328125,
"learning_rate": 2.5146918883822618e-05,
"loss": 2.1627,
"step": 173
},
{
"epoch": 0.29743589743589743,
"grad_norm": 0.67578125,
"learning_rate": 2.5087208058185676e-05,
"loss": 2.1274,
"step": 174
},
{
"epoch": 0.29914529914529914,
"grad_norm": 0.59375,
"learning_rate": 2.502720855117255e-05,
"loss": 2.0704,
"step": 175
},
{
"epoch": 0.30085470085470084,
"grad_norm": 0.62109375,
"learning_rate": 2.4966922217806723e-05,
"loss": 2.1342,
"step": 176
},
{
"epoch": 0.30256410256410254,
"grad_norm": 0.91796875,
"learning_rate": 2.4906350921979577e-05,
"loss": 2.0359,
"step": 177
},
{
"epoch": 0.30427350427350425,
"grad_norm": 0.62109375,
"learning_rate": 2.4845496536392782e-05,
"loss": 2.1133,
"step": 178
},
{
"epoch": 0.305982905982906,
"grad_norm": 0.6171875,
"learning_rate": 2.4784360942500367e-05,
"loss": 2.1915,
"step": 179
},
{
"epoch": 0.3076923076923077,
"grad_norm": 0.58203125,
"learning_rate": 2.4722946030450576e-05,
"loss": 2.1297,
"step": 180
},
{
"epoch": 0.3076923076923077,
"eval_loss": 2.223208427429199,
"eval_runtime": 87.3927,
"eval_samples_per_second": 2.929,
"eval_steps_per_second": 0.492,
"step": 180
},
{
"epoch": 0.3094017094017094,
"grad_norm": 0.7265625,
"learning_rate": 2.4661253699027413e-05,
"loss": 2.0955,
"step": 181
},
{
"epoch": 0.3111111111111111,
"grad_norm": 0.67578125,
"learning_rate": 2.459928585559195e-05,
"loss": 2.2005,
"step": 182
},
{
"epoch": 0.3128205128205128,
"grad_norm": 0.79296875,
"learning_rate": 2.4537044416023342e-05,
"loss": 2.2348,
"step": 183
},
{
"epoch": 0.3145299145299145,
"grad_norm": 0.68359375,
"learning_rate": 2.4474531304659607e-05,
"loss": 2.1847,
"step": 184
},
{
"epoch": 0.3162393162393162,
"grad_norm": 0.62109375,
"learning_rate": 2.441174845423812e-05,
"loss": 2.0688,
"step": 185
},
{
"epoch": 0.31794871794871793,
"grad_norm": 0.58984375,
"learning_rate": 2.434869780583587e-05,
"loss": 2.0944,
"step": 186
},
{
"epoch": 0.31965811965811963,
"grad_norm": 0.703125,
"learning_rate": 2.4285381308809433e-05,
"loss": 2.0466,
"step": 187
},
{
"epoch": 0.3213675213675214,
"grad_norm": 0.61328125,
"learning_rate": 2.4221800920734716e-05,
"loss": 2.1137,
"step": 188
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.65625,
"learning_rate": 2.4157958607346418e-05,
"loss": 2.1906,
"step": 189
},
{
"epoch": 0.3247863247863248,
"grad_norm": 0.69921875,
"learning_rate": 2.409385634247727e-05,
"loss": 2.1413,
"step": 190
},
{
"epoch": 0.3264957264957265,
"grad_norm": 0.65625,
"learning_rate": 2.4029496107997012e-05,
"loss": 2.108,
"step": 191
},
{
"epoch": 0.3282051282051282,
"grad_norm": 0.69140625,
"learning_rate": 2.3964879893751098e-05,
"loss": 2.1754,
"step": 192
},
{
"epoch": 0.3299145299145299,
"grad_norm": 0.671875,
"learning_rate": 2.3900009697499197e-05,
"loss": 2.4337,
"step": 193
},
{
"epoch": 0.3316239316239316,
"grad_norm": 0.93359375,
"learning_rate": 2.383488752485341e-05,
"loss": 2.1879,
"step": 194
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.64453125,
"learning_rate": 2.3769515389216285e-05,
"loss": 2.1198,
"step": 195
},
{
"epoch": 0.335042735042735,
"grad_norm": 1.1875,
"learning_rate": 2.370389531171854e-05,
"loss": 2.2024,
"step": 196
},
{
"epoch": 0.3367521367521368,
"grad_norm": 0.6796875,
"learning_rate": 2.36380293211566e-05,
"loss": 2.212,
"step": 197
},
{
"epoch": 0.3384615384615385,
"grad_norm": 0.58203125,
"learning_rate": 2.357191945392985e-05,
"loss": 2.0576,
"step": 198
},
{
"epoch": 0.3401709401709402,
"grad_norm": 0.65625,
"learning_rate": 2.3505567753977698e-05,
"loss": 2.1674,
"step": 199
},
{
"epoch": 0.3418803418803419,
"grad_norm": 0.66015625,
"learning_rate": 2.3438976272716353e-05,
"loss": 2.2,
"step": 200
},
{
"epoch": 0.3435897435897436,
"grad_norm": 0.640625,
"learning_rate": 2.3372147068975443e-05,
"loss": 2.2452,
"step": 201
},
{
"epoch": 0.3452991452991453,
"grad_norm": 0.62109375,
"learning_rate": 2.3305082208934306e-05,
"loss": 2.1513,
"step": 202
},
{
"epoch": 0.347008547008547,
"grad_norm": 0.66796875,
"learning_rate": 2.323778376605816e-05,
"loss": 2.1744,
"step": 203
},
{
"epoch": 0.3487179487179487,
"grad_norm": 0.60546875,
"learning_rate": 2.3170253821033978e-05,
"loss": 2.1073,
"step": 204
},
{
"epoch": 0.3504273504273504,
"grad_norm": 0.671875,
"learning_rate": 2.3102494461706138e-05,
"loss": 2.0887,
"step": 205
},
{
"epoch": 0.35213675213675216,
"grad_norm": 0.62109375,
"learning_rate": 2.303450778301191e-05,
"loss": 2.1766,
"step": 206
},
{
"epoch": 0.35384615384615387,
"grad_norm": 0.86328125,
"learning_rate": 2.2966295886916673e-05,
"loss": 2.4313,
"step": 207
},
{
"epoch": 0.35555555555555557,
"grad_norm": 0.640625,
"learning_rate": 2.289786088234889e-05,
"loss": 2.1811,
"step": 208
},
{
"epoch": 0.3572649572649573,
"grad_norm": 0.65234375,
"learning_rate": 2.2829204885134962e-05,
"loss": 2.1768,
"step": 209
},
{
"epoch": 0.358974358974359,
"grad_norm": 0.625,
"learning_rate": 2.2760330017933803e-05,
"loss": 2.1284,
"step": 210
},
{
"epoch": 0.358974358974359,
"eval_loss": 2.217427968978882,
"eval_runtime": 87.372,
"eval_samples_per_second": 2.93,
"eval_steps_per_second": 0.492,
"step": 210
},
{
"epoch": 0.3606837606837607,
"grad_norm": 0.59765625,
"learning_rate": 2.2691238410171176e-05,
"loss": 2.1223,
"step": 211
},
{
"epoch": 0.3623931623931624,
"grad_norm": 0.62109375,
"learning_rate": 2.2621932197973872e-05,
"loss": 2.1968,
"step": 212
},
{
"epoch": 0.3641025641025641,
"grad_norm": 0.69921875,
"learning_rate": 2.2552413524103696e-05,
"loss": 2.031,
"step": 213
},
{
"epoch": 0.3658119658119658,
"grad_norm": 0.66796875,
"learning_rate": 2.24826845378912e-05,
"loss": 2.1201,
"step": 214
},
{
"epoch": 0.36752136752136755,
"grad_norm": 0.62890625,
"learning_rate": 2.24127473951692e-05,
"loss": 2.1512,
"step": 215
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.625,
"learning_rate": 2.234260425820618e-05,
"loss": 2.1336,
"step": 216
},
{
"epoch": 0.37094017094017095,
"grad_norm": 0.7109375,
"learning_rate": 2.2272257295639394e-05,
"loss": 2.1621,
"step": 217
},
{
"epoch": 0.37264957264957266,
"grad_norm": 0.65625,
"learning_rate": 2.220170868240785e-05,
"loss": 2.183,
"step": 218
},
{
"epoch": 0.37435897435897436,
"grad_norm": 0.92578125,
"learning_rate": 2.2130960599685035e-05,
"loss": 2.102,
"step": 219
},
{
"epoch": 0.37606837606837606,
"grad_norm": 0.7109375,
"learning_rate": 2.2060015234811516e-05,
"loss": 2.1166,
"step": 220
},
{
"epoch": 0.37777777777777777,
"grad_norm": 0.765625,
"learning_rate": 2.198887478122728e-05,
"loss": 2.0371,
"step": 221
},
{
"epoch": 0.37948717948717947,
"grad_norm": 0.7265625,
"learning_rate": 2.1917541438403935e-05,
"loss": 2.1866,
"step": 222
},
{
"epoch": 0.3811965811965812,
"grad_norm": 0.66796875,
"learning_rate": 2.184601741177672e-05,
"loss": 2.1378,
"step": 223
},
{
"epoch": 0.38290598290598293,
"grad_norm": 0.62109375,
"learning_rate": 2.1774304912676283e-05,
"loss": 2.2808,
"step": 224
},
{
"epoch": 0.38461538461538464,
"grad_norm": 0.671875,
"learning_rate": 2.170240615826034e-05,
"loss": 2.3453,
"step": 225
},
{
"epoch": 0.38632478632478634,
"grad_norm": 0.63671875,
"learning_rate": 2.1630323371445135e-05,
"loss": 2.0998,
"step": 226
},
{
"epoch": 0.38803418803418804,
"grad_norm": 0.6875,
"learning_rate": 2.1558058780836683e-05,
"loss": 2.1901,
"step": 227
},
{
"epoch": 0.38974358974358975,
"grad_norm": 0.72265625,
"learning_rate": 2.148561462066189e-05,
"loss": 2.1571,
"step": 228
},
{
"epoch": 0.39145299145299145,
"grad_norm": 0.69140625,
"learning_rate": 2.141299313069947e-05,
"loss": 2.1222,
"step": 229
},
{
"epoch": 0.39316239316239315,
"grad_norm": 0.71875,
"learning_rate": 2.1340196556210705e-05,
"loss": 2.0624,
"step": 230
},
{
"epoch": 0.39487179487179486,
"grad_norm": 0.6875,
"learning_rate": 2.126722714787e-05,
"loss": 2.1906,
"step": 231
},
{
"epoch": 0.39658119658119656,
"grad_norm": 1.34375,
"learning_rate": 2.119408716169534e-05,
"loss": 2.1405,
"step": 232
},
{
"epoch": 0.39829059829059826,
"grad_norm": 0.66796875,
"learning_rate": 2.11207788589785e-05,
"loss": 2.1191,
"step": 233
},
{
"epoch": 0.4,
"grad_norm": 0.66796875,
"learning_rate": 2.1047304506215165e-05,
"loss": 2.2563,
"step": 234
},
{
"epoch": 0.4017094017094017,
"grad_norm": 0.62890625,
"learning_rate": 2.0973666375034834e-05,
"loss": 2.1473,
"step": 235
},
{
"epoch": 0.40341880341880343,
"grad_norm": 0.64453125,
"learning_rate": 2.0899866742130593e-05,
"loss": 2.1922,
"step": 236
},
{
"epoch": 0.40512820512820513,
"grad_norm": 0.66015625,
"learning_rate": 2.082590788918873e-05,
"loss": 2.1046,
"step": 237
},
{
"epoch": 0.40683760683760684,
"grad_norm": 0.6484375,
"learning_rate": 2.075179210281819e-05,
"loss": 2.2538,
"step": 238
},
{
"epoch": 0.40854700854700854,
"grad_norm": 0.625,
"learning_rate": 2.067752167447987e-05,
"loss": 2.1669,
"step": 239
},
{
"epoch": 0.41025641025641024,
"grad_norm": 0.61328125,
"learning_rate": 2.06030989004158e-05,
"loss": 2.1102,
"step": 240
},
{
"epoch": 0.41025641025641024,
"eval_loss": 2.2125699520111084,
"eval_runtime": 87.3321,
"eval_samples_per_second": 2.931,
"eval_steps_per_second": 0.492,
"step": 240
},
{
"epoch": 0.41196581196581195,
"grad_norm": 0.66015625,
"learning_rate": 2.0528526081578102e-05,
"loss": 2.1852,
"step": 241
},
{
"epoch": 0.41367521367521365,
"grad_norm": 0.72265625,
"learning_rate": 2.04538055235579e-05,
"loss": 2.1288,
"step": 242
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.67578125,
"learning_rate": 2.0378939536514015e-05,
"loss": 2.1667,
"step": 243
},
{
"epoch": 0.4170940170940171,
"grad_norm": 0.84765625,
"learning_rate": 2.0303930435101532e-05,
"loss": 2.2033,
"step": 244
},
{
"epoch": 0.4188034188034188,
"grad_norm": 0.625,
"learning_rate": 2.0228780538400254e-05,
"loss": 2.0582,
"step": 245
},
{
"epoch": 0.4205128205128205,
"grad_norm": 0.7109375,
"learning_rate": 2.0153492169843002e-05,
"loss": 2.2387,
"step": 246
},
{
"epoch": 0.4222222222222222,
"grad_norm": 0.64453125,
"learning_rate": 2.0078067657143766e-05,
"loss": 1.9239,
"step": 247
},
{
"epoch": 0.4239316239316239,
"grad_norm": 0.66015625,
"learning_rate": 2.000250933222574e-05,
"loss": 2.0464,
"step": 248
},
{
"epoch": 0.4256410256410256,
"grad_norm": 0.6484375,
"learning_rate": 1.9926819531149254e-05,
"loss": 2.3487,
"step": 249
},
{
"epoch": 0.42735042735042733,
"grad_norm": 0.671875,
"learning_rate": 1.9851000594039507e-05,
"loss": 2.1377,
"step": 250
},
{
"epoch": 0.42905982905982903,
"grad_norm": 0.6484375,
"learning_rate": 1.977505486501425e-05,
"loss": 2.1922,
"step": 251
},
{
"epoch": 0.4307692307692308,
"grad_norm": 0.671875,
"learning_rate": 1.9698984692111294e-05,
"loss": 2.2152,
"step": 252
},
{
"epoch": 0.4324786324786325,
"grad_norm": 0.6953125,
"learning_rate": 1.9622792427215913e-05,
"loss": 2.1691,
"step": 253
},
{
"epoch": 0.4341880341880342,
"grad_norm": 0.66796875,
"learning_rate": 1.9546480425988148e-05,
"loss": 2.0905,
"step": 254
},
{
"epoch": 0.4358974358974359,
"grad_norm": 0.640625,
"learning_rate": 1.9470051047789966e-05,
"loss": 2.1187,
"step": 255
},
{
"epoch": 0.4376068376068376,
"grad_norm": 0.78515625,
"learning_rate": 1.9393506655612313e-05,
"loss": 2.0652,
"step": 256
},
{
"epoch": 0.4393162393162393,
"grad_norm": 0.68359375,
"learning_rate": 1.9316849616002043e-05,
"loss": 2.1493,
"step": 257
},
{
"epoch": 0.441025641025641,
"grad_norm": 0.81640625,
"learning_rate": 1.924008229898879e-05,
"loss": 2.141,
"step": 258
},
{
"epoch": 0.4427350427350427,
"grad_norm": 0.6953125,
"learning_rate": 1.916320707801166e-05,
"loss": 2.2666,
"step": 259
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.70703125,
"learning_rate": 1.908622632984584e-05,
"loss": 2.1914,
"step": 260
},
{
"epoch": 0.4461538461538462,
"grad_norm": 0.734375,
"learning_rate": 1.9009142434529165e-05,
"loss": 2.0921,
"step": 261
},
{
"epoch": 0.4478632478632479,
"grad_norm": 0.72265625,
"learning_rate": 1.8931957775288488e-05,
"loss": 2.2453,
"step": 262
},
{
"epoch": 0.4495726495726496,
"grad_norm": 0.703125,
"learning_rate": 1.8854674738466007e-05,
"loss": 2.2583,
"step": 263
},
{
"epoch": 0.4512820512820513,
"grad_norm": 0.62890625,
"learning_rate": 1.8777295713445494e-05,
"loss": 2.2228,
"step": 264
},
{
"epoch": 0.452991452991453,
"grad_norm": 0.69921875,
"learning_rate": 1.8699823092578427e-05,
"loss": 2.1037,
"step": 265
},
{
"epoch": 0.4547008547008547,
"grad_norm": 1.375,
"learning_rate": 1.862225927111001e-05,
"loss": 2.3323,
"step": 266
},
{
"epoch": 0.4564102564102564,
"grad_norm": 0.68359375,
"learning_rate": 1.8544606647105113e-05,
"loss": 2.1672,
"step": 267
},
{
"epoch": 0.4581196581196581,
"grad_norm": 0.70703125,
"learning_rate": 1.8466867621374162e-05,
"loss": 2.0741,
"step": 268
},
{
"epoch": 0.4598290598290598,
"grad_norm": 0.66796875,
"learning_rate": 1.8389044597398877e-05,
"loss": 2.153,
"step": 269
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.69921875,
"learning_rate": 1.831113998125798e-05,
"loss": 2.146,
"step": 270
},
{
"epoch": 0.46153846153846156,
"eval_loss": 2.21103835105896,
"eval_runtime": 87.3912,
"eval_samples_per_second": 2.929,
"eval_steps_per_second": 0.492,
"step": 270
},
{
"epoch": 0.46324786324786327,
"grad_norm": 0.8125,
"learning_rate": 1.8233156181552815e-05,
"loss": 2.23,
"step": 271
},
{
"epoch": 0.46495726495726497,
"grad_norm": 0.6484375,
"learning_rate": 1.8155095609332857e-05,
"loss": 2.1312,
"step": 272
},
{
"epoch": 0.4666666666666667,
"grad_norm": 0.6328125,
"learning_rate": 1.807696067802118e-05,
"loss": 2.2045,
"step": 273
},
{
"epoch": 0.4683760683760684,
"grad_norm": 0.72265625,
"learning_rate": 1.7998753803339846e-05,
"loss": 2.1149,
"step": 274
},
{
"epoch": 0.4700854700854701,
"grad_norm": 0.8359375,
"learning_rate": 1.792047740323522e-05,
"loss": 2.1843,
"step": 275
},
{
"epoch": 0.4717948717948718,
"grad_norm": 0.6796875,
"learning_rate": 1.7842133897803194e-05,
"loss": 2.0823,
"step": 276
},
{
"epoch": 0.4735042735042735,
"grad_norm": 0.79296875,
"learning_rate": 1.776372570921438e-05,
"loss": 2.133,
"step": 277
},
{
"epoch": 0.4752136752136752,
"grad_norm": 0.62109375,
"learning_rate": 1.7685255261639223e-05,
"loss": 2.0865,
"step": 278
},
{
"epoch": 0.47692307692307695,
"grad_norm": 4.28125,
"learning_rate": 1.760672498117304e-05,
"loss": 2.1211,
"step": 279
},
{
"epoch": 0.47863247863247865,
"grad_norm": 0.640625,
"learning_rate": 1.7528137295761025e-05,
"loss": 2.1688,
"step": 280
},
{
"epoch": 0.48034188034188036,
"grad_norm": 0.71484375,
"learning_rate": 1.7449494635123183e-05,
"loss": 2.1924,
"step": 281
},
{
"epoch": 0.48205128205128206,
"grad_norm": 0.68359375,
"learning_rate": 1.737079943067921e-05,
"loss": 2.214,
"step": 282
},
{
"epoch": 0.48376068376068376,
"grad_norm": 0.74609375,
"learning_rate": 1.7292054115473292e-05,
"loss": 2.1239,
"step": 283
},
{
"epoch": 0.48547008547008547,
"grad_norm": 0.6953125,
"learning_rate": 1.7213261124098926e-05,
"loss": 1.9381,
"step": 284
},
{
"epoch": 0.48717948717948717,
"grad_norm": 0.76171875,
"learning_rate": 1.7134422892623625e-05,
"loss": 2.0799,
"step": 285
},
{
"epoch": 0.4888888888888889,
"grad_norm": 0.7421875,
"learning_rate": 1.70555418585136e-05,
"loss": 2.0629,
"step": 286
},
{
"epoch": 0.4905982905982906,
"grad_norm": 0.66796875,
"learning_rate": 1.69766204605584e-05,
"loss": 2.0974,
"step": 287
},
{
"epoch": 0.49230769230769234,
"grad_norm": 1.15625,
"learning_rate": 1.689766113879553e-05,
"loss": 2.0869,
"step": 288
},
{
"epoch": 0.49401709401709404,
"grad_norm": 0.734375,
"learning_rate": 1.6818666334434983e-05,
"loss": 2.037,
"step": 289
},
{
"epoch": 0.49572649572649574,
"grad_norm": 0.8203125,
"learning_rate": 1.673963848978378e-05,
"loss": 2.1412,
"step": 290
},
{
"epoch": 0.49743589743589745,
"grad_norm": 0.734375,
"learning_rate": 1.6660580048170472e-05,
"loss": 2.1773,
"step": 291
},
{
"epoch": 0.49914529914529915,
"grad_norm": 1.078125,
"learning_rate": 1.6581493453869575e-05,
"loss": 2.1232,
"step": 292
},
{
"epoch": 0.5008547008547009,
"grad_norm": 0.65234375,
"learning_rate": 1.6502381152026006e-05,
"loss": 2.1975,
"step": 293
},
{
"epoch": 0.5025641025641026,
"grad_norm": 0.7109375,
"learning_rate": 1.64232455885795e-05,
"loss": 2.0626,
"step": 294
},
{
"epoch": 0.5042735042735043,
"grad_norm": 0.68359375,
"learning_rate": 1.634408921018898e-05,
"loss": 2.0798,
"step": 295
},
{
"epoch": 0.505982905982906,
"grad_norm": 0.72265625,
"learning_rate": 1.62649144641569e-05,
"loss": 2.1388,
"step": 296
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.69140625,
"learning_rate": 1.6185723798353594e-05,
"loss": 2.1995,
"step": 297
},
{
"epoch": 0.5094017094017094,
"grad_norm": 0.69140625,
"learning_rate": 1.6106519661141607e-05,
"loss": 2.188,
"step": 298
},
{
"epoch": 0.5111111111111111,
"grad_norm": 0.91015625,
"learning_rate": 1.6027304501299966e-05,
"loss": 2.1787,
"step": 299
},
{
"epoch": 0.5128205128205128,
"grad_norm": 0.75390625,
"learning_rate": 1.5948080767948492e-05,
"loss": 2.2056,
"step": 300
},
{
"epoch": 0.5128205128205128,
"eval_loss": 2.2115139961242676,
"eval_runtime": 87.3545,
"eval_samples_per_second": 2.931,
"eval_steps_per_second": 0.492,
"step": 300
},
{
"epoch": 0.5145299145299145,
"grad_norm": 0.7109375,
"learning_rate": 1.586885091047209e-05,
"loss": 2.2719,
"step": 301
},
{
"epoch": 0.5162393162393163,
"grad_norm": 0.6796875,
"learning_rate": 1.578961737844498e-05,
"loss": 2.2123,
"step": 302
},
{
"epoch": 0.517948717948718,
"grad_norm": 0.7578125,
"learning_rate": 1.571038262155502e-05,
"loss": 2.0851,
"step": 303
},
{
"epoch": 0.5196581196581197,
"grad_norm": 0.6484375,
"learning_rate": 1.5631149089527914e-05,
"loss": 2.1001,
"step": 304
},
{
"epoch": 0.5213675213675214,
"grad_norm": 0.66015625,
"learning_rate": 1.555191923205151e-05,
"loss": 2.0935,
"step": 305
},
{
"epoch": 0.5230769230769231,
"grad_norm": 0.6875,
"learning_rate": 1.547269549870004e-05,
"loss": 2.1564,
"step": 306
},
{
"epoch": 0.5247863247863248,
"grad_norm": 0.65625,
"learning_rate": 1.5393480338858396e-05,
"loss": 2.1377,
"step": 307
},
{
"epoch": 0.5264957264957265,
"grad_norm": 0.71484375,
"learning_rate": 1.531427620164641e-05,
"loss": 2.1372,
"step": 308
},
{
"epoch": 0.5282051282051282,
"grad_norm": 0.71484375,
"learning_rate": 1.5235085535843107e-05,
"loss": 2.1712,
"step": 309
},
{
"epoch": 0.5299145299145299,
"grad_norm": 0.6796875,
"learning_rate": 1.515591078981102e-05,
"loss": 2.1177,
"step": 310
},
{
"epoch": 0.5316239316239316,
"grad_norm": 0.73046875,
"learning_rate": 1.5076754411420503e-05,
"loss": 2.1463,
"step": 311
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.6953125,
"learning_rate": 1.4997618847973994e-05,
"loss": 2.1804,
"step": 312
},
{
"epoch": 0.535042735042735,
"grad_norm": 0.72265625,
"learning_rate": 1.4918506546130428e-05,
"loss": 1.9995,
"step": 313
},
{
"epoch": 0.5367521367521367,
"grad_norm": 0.73046875,
"learning_rate": 1.4839419951829531e-05,
"loss": 2.1211,
"step": 314
},
{
"epoch": 0.5384615384615384,
"grad_norm": 0.6875,
"learning_rate": 1.4760361510216222e-05,
"loss": 2.1448,
"step": 315
},
{
"epoch": 0.5401709401709401,
"grad_norm": 0.8046875,
"learning_rate": 1.4681333665565023e-05,
"loss": 2.1807,
"step": 316
},
{
"epoch": 0.5418803418803418,
"grad_norm": 0.72265625,
"learning_rate": 1.4602338861204476e-05,
"loss": 2.0128,
"step": 317
},
{
"epoch": 0.5435897435897435,
"grad_norm": 0.6796875,
"learning_rate": 1.45233795394416e-05,
"loss": 2.0709,
"step": 318
},
{
"epoch": 0.5452991452991452,
"grad_norm": 0.7109375,
"learning_rate": 1.4444458141486407e-05,
"loss": 2.078,
"step": 319
},
{
"epoch": 0.5470085470085471,
"grad_norm": 0.921875,
"learning_rate": 1.4365577107376375e-05,
"loss": 2.298,
"step": 320
},
{
"epoch": 0.5487179487179488,
"grad_norm": 0.68359375,
"learning_rate": 1.4286738875901076e-05,
"loss": 2.2792,
"step": 321
},
{
"epoch": 0.5504273504273505,
"grad_norm": 0.6015625,
"learning_rate": 1.4207945884526711e-05,
"loss": 2.0561,
"step": 322
},
{
"epoch": 0.5521367521367522,
"grad_norm": 0.6875,
"learning_rate": 1.4129200569320792e-05,
"loss": 2.003,
"step": 323
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.7421875,
"learning_rate": 1.4050505364876817e-05,
"loss": 2.1131,
"step": 324
},
{
"epoch": 0.5555555555555556,
"grad_norm": 0.69921875,
"learning_rate": 1.397186270423898e-05,
"loss": 2.1349,
"step": 325
},
{
"epoch": 0.5572649572649573,
"grad_norm": 0.6953125,
"learning_rate": 1.3893275018826964e-05,
"loss": 2.0442,
"step": 326
},
{
"epoch": 0.558974358974359,
"grad_norm": 0.75390625,
"learning_rate": 1.381474473836078e-05,
"loss": 1.954,
"step": 327
},
{
"epoch": 0.5606837606837607,
"grad_norm": 0.890625,
"learning_rate": 1.3736274290785618e-05,
"loss": 2.2209,
"step": 328
},
{
"epoch": 0.5623931623931624,
"grad_norm": 0.71875,
"learning_rate": 1.3657866102196804e-05,
"loss": 2.1763,
"step": 329
},
{
"epoch": 0.5641025641025641,
"grad_norm": 0.7109375,
"learning_rate": 1.3579522596764779e-05,
"loss": 2.2332,
"step": 330
},
{
"epoch": 0.5641025641025641,
"eval_loss": 2.2132272720336914,
"eval_runtime": 87.4216,
"eval_samples_per_second": 2.928,
"eval_steps_per_second": 0.492,
"step": 330
},
{
"epoch": 0.5658119658119658,
"grad_norm": 0.69140625,
"learning_rate": 1.350124619666015e-05,
"loss": 2.1367,
"step": 331
},
{
"epoch": 0.5675213675213675,
"grad_norm": 0.6796875,
"learning_rate": 1.3423039321978823e-05,
"loss": 2.3374,
"step": 332
},
{
"epoch": 0.5692307692307692,
"grad_norm": 0.7265625,
"learning_rate": 1.334490439066715e-05,
"loss": 2.1575,
"step": 333
},
{
"epoch": 0.5709401709401709,
"grad_norm": 0.7265625,
"learning_rate": 1.3266843818447187e-05,
"loss": 2.1563,
"step": 334
},
{
"epoch": 0.5726495726495726,
"grad_norm": 0.7421875,
"learning_rate": 1.318886001874202e-05,
"loss": 2.1058,
"step": 335
},
{
"epoch": 0.5743589743589743,
"grad_norm": 0.63671875,
"learning_rate": 1.3110955402601127e-05,
"loss": 2.1521,
"step": 336
},
{
"epoch": 0.576068376068376,
"grad_norm": 0.9921875,
"learning_rate": 1.3033132378625841e-05,
"loss": 2.2566,
"step": 337
},
{
"epoch": 0.5777777777777777,
"grad_norm": 0.77734375,
"learning_rate": 1.295539335289489e-05,
"loss": 2.0666,
"step": 338
},
{
"epoch": 0.5794871794871795,
"grad_norm": 0.7265625,
"learning_rate": 1.2877740728889991e-05,
"loss": 2.1595,
"step": 339
},
{
"epoch": 0.5811965811965812,
"grad_norm": 0.6484375,
"learning_rate": 1.2800176907421574e-05,
"loss": 2.185,
"step": 340
},
{
"epoch": 0.582905982905983,
"grad_norm": 0.84765625,
"learning_rate": 1.2722704286554509e-05,
"loss": 1.9905,
"step": 341
},
{
"epoch": 0.5846153846153846,
"grad_norm": 0.765625,
"learning_rate": 1.2645325261533997e-05,
"loss": 2.2428,
"step": 342
},
{
"epoch": 0.5863247863247864,
"grad_norm": 0.64453125,
"learning_rate": 1.2568042224711517e-05,
"loss": 2.1675,
"step": 343
},
{
"epoch": 0.588034188034188,
"grad_norm": 0.69140625,
"learning_rate": 1.2490857565470835e-05,
"loss": 2.1204,
"step": 344
},
{
"epoch": 0.5897435897435898,
"grad_norm": 0.84765625,
"learning_rate": 1.2413773670154163e-05,
"loss": 2.1769,
"step": 345
},
{
"epoch": 0.5914529914529915,
"grad_norm": 0.6796875,
"learning_rate": 1.2336792921988348e-05,
"loss": 2.0688,
"step": 346
},
{
"epoch": 0.5931623931623932,
"grad_norm": 0.84765625,
"learning_rate": 1.225991770101121e-05,
"loss": 2.1087,
"step": 347
},
{
"epoch": 0.5948717948717949,
"grad_norm": 0.70703125,
"learning_rate": 1.2183150383997957e-05,
"loss": 2.0413,
"step": 348
},
{
"epoch": 0.5965811965811966,
"grad_norm": 0.703125,
"learning_rate": 1.2106493344387692e-05,
"loss": 2.0163,
"step": 349
},
{
"epoch": 0.5982905982905983,
"grad_norm": 0.7734375,
"learning_rate": 1.2029948952210032e-05,
"loss": 2.0951,
"step": 350
},
{
"epoch": 0.6,
"grad_norm": 0.921875,
"learning_rate": 1.1953519574011852e-05,
"loss": 2.2931,
"step": 351
},
{
"epoch": 0.6017094017094017,
"grad_norm": 0.71875,
"learning_rate": 1.1877207572784085e-05,
"loss": 2.0968,
"step": 352
},
{
"epoch": 0.6034188034188034,
"grad_norm": 0.70703125,
"learning_rate": 1.1801015307888711e-05,
"loss": 2.0985,
"step": 353
},
{
"epoch": 0.6051282051282051,
"grad_norm": 0.73828125,
"learning_rate": 1.1724945134985752e-05,
"loss": 2.0038,
"step": 354
},
{
"epoch": 0.6068376068376068,
"grad_norm": 0.69140625,
"learning_rate": 1.164899940596049e-05,
"loss": 2.077,
"step": 355
},
{
"epoch": 0.6085470085470085,
"grad_norm": 0.71484375,
"learning_rate": 1.1573180468850746e-05,
"loss": 2.2948,
"step": 356
},
{
"epoch": 0.6102564102564103,
"grad_norm": 0.671875,
"learning_rate": 1.1497490667774266e-05,
"loss": 2.1145,
"step": 357
},
{
"epoch": 0.611965811965812,
"grad_norm": 0.703125,
"learning_rate": 1.1421932342856239e-05,
"loss": 2.2228,
"step": 358
},
{
"epoch": 0.6136752136752137,
"grad_norm": 0.76171875,
"learning_rate": 1.1346507830157e-05,
"loss": 2.057,
"step": 359
},
{
"epoch": 0.6153846153846154,
"grad_norm": 0.65234375,
"learning_rate": 1.1271219461599744e-05,
"loss": 2.0817,
"step": 360
},
{
"epoch": 0.6153846153846154,
"eval_loss": 2.2105114459991455,
"eval_runtime": 87.3006,
"eval_samples_per_second": 2.932,
"eval_steps_per_second": 0.493,
"step": 360
},
{
"epoch": 0.6170940170940171,
"grad_norm": 0.72265625,
"learning_rate": 1.119606956489847e-05,
"loss": 2.1956,
"step": 361
},
{
"epoch": 0.6188034188034188,
"grad_norm": 0.7578125,
"learning_rate": 1.1121060463485988e-05,
"loss": 2.0876,
"step": 362
},
{
"epoch": 0.6205128205128205,
"grad_norm": 0.71875,
"learning_rate": 1.1046194476442102e-05,
"loss": 2.1283,
"step": 363
},
{
"epoch": 0.6222222222222222,
"grad_norm": 0.71484375,
"learning_rate": 1.0971473918421902e-05,
"loss": 2.2499,
"step": 364
},
{
"epoch": 0.6239316239316239,
"grad_norm": 0.66015625,
"learning_rate": 1.0896901099584205e-05,
"loss": 2.2043,
"step": 365
},
{
"epoch": 0.6256410256410256,
"grad_norm": 0.671875,
"learning_rate": 1.0822478325520127e-05,
"loss": 2.1081,
"step": 366
},
{
"epoch": 0.6273504273504273,
"grad_norm": 0.71484375,
"learning_rate": 1.0748207897181813e-05,
"loss": 2.1708,
"step": 367
},
{
"epoch": 0.629059829059829,
"grad_norm": 0.828125,
"learning_rate": 1.0674092110811267e-05,
"loss": 2.1264,
"step": 368
},
{
"epoch": 0.6307692307692307,
"grad_norm": 0.671875,
"learning_rate": 1.0600133257869412e-05,
"loss": 2.184,
"step": 369
},
{
"epoch": 0.6324786324786325,
"grad_norm": 0.76171875,
"learning_rate": 1.052633362496517e-05,
"loss": 2.1171,
"step": 370
},
{
"epoch": 0.6341880341880342,
"grad_norm": 0.71875,
"learning_rate": 1.0452695493784833e-05,
"loss": 1.9935,
"step": 371
},
{
"epoch": 0.6358974358974359,
"grad_norm": 0.734375,
"learning_rate": 1.03792211410215e-05,
"loss": 2.1755,
"step": 372
},
{
"epoch": 0.6376068376068376,
"grad_norm": 0.68359375,
"learning_rate": 1.0305912838304668e-05,
"loss": 1.9702,
"step": 373
},
{
"epoch": 0.6393162393162393,
"grad_norm": 0.73046875,
"learning_rate": 1.0232772852129998e-05,
"loss": 2.1635,
"step": 374
},
{
"epoch": 0.6410256410256411,
"grad_norm": 0.75390625,
"learning_rate": 1.0159803443789298e-05,
"loss": 2.061,
"step": 375
},
{
"epoch": 0.6427350427350428,
"grad_norm": 0.6171875,
"learning_rate": 1.0087006869300527e-05,
"loss": 2.2011,
"step": 376
},
{
"epoch": 0.6444444444444445,
"grad_norm": 0.83984375,
"learning_rate": 1.001438537933811e-05,
"loss": 2.1676,
"step": 377
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.6640625,
"learning_rate": 9.941941219163322e-06,
"loss": 2.2201,
"step": 378
},
{
"epoch": 0.6478632478632479,
"grad_norm": 0.70703125,
"learning_rate": 9.869676628554868e-06,
"loss": 2.1526,
"step": 379
},
{
"epoch": 0.6495726495726496,
"grad_norm": 0.68359375,
"learning_rate": 9.79759384173966e-06,
"loss": 1.926,
"step": 380
},
{
"epoch": 0.6512820512820513,
"grad_norm": 0.7265625,
"learning_rate": 9.725695087323722e-06,
"loss": 2.013,
"step": 381
},
{
"epoch": 0.652991452991453,
"grad_norm": 0.7890625,
"learning_rate": 9.653982588223286e-06,
"loss": 2.1558,
"step": 382
},
{
"epoch": 0.6547008547008547,
"grad_norm": 0.69140625,
"learning_rate": 9.582458561596068e-06,
"loss": 2.0393,
"step": 383
},
{
"epoch": 0.6564102564102564,
"grad_norm": 0.6796875,
"learning_rate": 9.511125218772721e-06,
"loss": 2.1331,
"step": 384
},
{
"epoch": 0.6581196581196581,
"grad_norm": 0.6484375,
"learning_rate": 9.439984765188486e-06,
"loss": 2.1312,
"step": 385
},
{
"epoch": 0.6598290598290598,
"grad_norm": 0.70703125,
"learning_rate": 9.369039400314967e-06,
"loss": 2.0472,
"step": 386
},
{
"epoch": 0.6615384615384615,
"grad_norm": 0.7421875,
"learning_rate": 9.298291317592157e-06,
"loss": 2.1349,
"step": 387
},
{
"epoch": 0.6632478632478632,
"grad_norm": 0.73046875,
"learning_rate": 9.227742704360611e-06,
"loss": 2.2088,
"step": 388
},
{
"epoch": 0.6649572649572649,
"grad_norm": 0.9375,
"learning_rate": 9.157395741793826e-06,
"loss": 2.0779,
"step": 389
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.7890625,
"learning_rate": 9.087252604830799e-06,
"loss": 2.1018,
"step": 390
},
{
"epoch": 0.6666666666666666,
"eval_loss": 2.210728168487549,
"eval_runtime": 87.3336,
"eval_samples_per_second": 2.931,
"eval_steps_per_second": 0.492,
"step": 390
},
{
"epoch": 0.6683760683760683,
"grad_norm": 0.77734375,
"learning_rate": 9.017315462108801e-06,
"loss": 2.1392,
"step": 391
},
{
"epoch": 0.67008547008547,
"grad_norm": 0.8671875,
"learning_rate": 8.947586475896297e-06,
"loss": 2.0877,
"step": 392
},
{
"epoch": 0.6717948717948717,
"grad_norm": 0.74609375,
"learning_rate": 8.878067802026128e-06,
"loss": 2.0754,
"step": 393
},
{
"epoch": 0.6735042735042736,
"grad_norm": 0.7265625,
"learning_rate": 8.808761589828834e-06,
"loss": 2.0953,
"step": 394
},
{
"epoch": 0.6752136752136753,
"grad_norm": 0.92578125,
"learning_rate": 8.739669982066198e-06,
"loss": 2.2066,
"step": 395
},
{
"epoch": 0.676923076923077,
"grad_norm": 0.68359375,
"learning_rate": 8.670795114865037e-06,
"loss": 2.1994,
"step": 396
},
{
"epoch": 0.6786324786324787,
"grad_norm": 0.6875,
"learning_rate": 8.60213911765112e-06,
"loss": 2.3178,
"step": 397
},
{
"epoch": 0.6803418803418804,
"grad_norm": 0.6875,
"learning_rate": 8.533704113083332e-06,
"loss": 2.0433,
"step": 398
},
{
"epoch": 0.6820512820512821,
"grad_norm": 0.70703125,
"learning_rate": 8.465492216988088e-06,
"loss": 2.1401,
"step": 399
},
{
"epoch": 0.6837606837606838,
"grad_norm": 0.66015625,
"learning_rate": 8.397505538293864e-06,
"loss": 2.2311,
"step": 400
},
{
"epoch": 0.6854700854700855,
"grad_norm": 0.671875,
"learning_rate": 8.329746178966025e-06,
"loss": 2.2968,
"step": 401
},
{
"epoch": 0.6871794871794872,
"grad_norm": 0.6953125,
"learning_rate": 8.262216233941844e-06,
"loss": 2.2976,
"step": 402
},
{
"epoch": 0.6888888888888889,
"grad_norm": 0.71484375,
"learning_rate": 8.194917791065696e-06,
"loss": 2.2814,
"step": 403
},
{
"epoch": 0.6905982905982906,
"grad_norm": 0.7578125,
"learning_rate": 8.127852931024559e-06,
"loss": 2.1567,
"step": 404
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.6875,
"learning_rate": 8.061023727283647e-06,
"loss": 2.0597,
"step": 405
},
{
"epoch": 0.694017094017094,
"grad_norm": 0.7265625,
"learning_rate": 7.9944322460223e-06,
"loss": 2.1498,
"step": 406
},
{
"epoch": 0.6957264957264957,
"grad_norm": 0.71484375,
"learning_rate": 7.928080546070154e-06,
"loss": 2.121,
"step": 407
},
{
"epoch": 0.6974358974358974,
"grad_norm": 0.73046875,
"learning_rate": 7.8619706788434e-06,
"loss": 2.1727,
"step": 408
},
{
"epoch": 0.6991452991452991,
"grad_norm": 0.71875,
"learning_rate": 7.79610468828146e-06,
"loss": 2.002,
"step": 409
},
{
"epoch": 0.7008547008547008,
"grad_norm": 0.7265625,
"learning_rate": 7.730484610783716e-06,
"loss": 2.0831,
"step": 410
},
{
"epoch": 0.7025641025641025,
"grad_norm": 0.7109375,
"learning_rate": 7.665112475146588e-06,
"loss": 2.0879,
"step": 411
},
{
"epoch": 0.7042735042735043,
"grad_norm": 0.81640625,
"learning_rate": 7.5999903025008055e-06,
"loss": 2.2322,
"step": 412
},
{
"epoch": 0.705982905982906,
"grad_norm": 0.7421875,
"learning_rate": 7.535120106248905e-06,
"loss": 2.1575,
"step": 413
},
{
"epoch": 0.7076923076923077,
"grad_norm": 0.6796875,
"learning_rate": 7.47050389200299e-06,
"loss": 2.1564,
"step": 414
},
{
"epoch": 0.7094017094017094,
"grad_norm": 0.7109375,
"learning_rate": 7.4061436575227315e-06,
"loss": 2.0875,
"step": 415
},
{
"epoch": 0.7111111111111111,
"grad_norm": 0.77734375,
"learning_rate": 7.342041392653582e-06,
"loss": 2.1155,
"step": 416
},
{
"epoch": 0.7128205128205128,
"grad_norm": 0.76953125,
"learning_rate": 7.2781990792652846e-06,
"loss": 2.0785,
"step": 417
},
{
"epoch": 0.7145299145299145,
"grad_norm": 0.72265625,
"learning_rate": 7.214618691190564e-06,
"loss": 2.341,
"step": 418
},
{
"epoch": 0.7162393162393162,
"grad_norm": 0.75,
"learning_rate": 7.151302194164131e-06,
"loss": 2.2056,
"step": 419
},
{
"epoch": 0.717948717948718,
"grad_norm": 0.8203125,
"learning_rate": 7.088251545761883e-06,
"loss": 2.0424,
"step": 420
},
{
"epoch": 0.717948717948718,
"eval_loss": 2.2081644535064697,
"eval_runtime": 87.4416,
"eval_samples_per_second": 2.928,
"eval_steps_per_second": 0.492,
"step": 420
},
{
"epoch": 0.7196581196581197,
"grad_norm": 0.7265625,
"learning_rate": 7.0254686953403975e-06,
"loss": 2.1406,
"step": 421
},
{
"epoch": 0.7213675213675214,
"grad_norm": 0.69921875,
"learning_rate": 6.962955583976662e-06,
"loss": 2.0345,
"step": 422
},
{
"epoch": 0.7230769230769231,
"grad_norm": 0.69140625,
"learning_rate": 6.900714144408054e-06,
"loss": 2.0704,
"step": 423
},
{
"epoch": 0.7247863247863248,
"grad_norm": 0.7109375,
"learning_rate": 6.838746300972587e-06,
"loss": 2.3178,
"step": 424
},
{
"epoch": 0.7264957264957265,
"grad_norm": 0.66015625,
"learning_rate": 6.777053969549426e-06,
"loss": 2.1059,
"step": 425
},
{
"epoch": 0.7282051282051282,
"grad_norm": 0.8125,
"learning_rate": 6.715639057499635e-06,
"loss": 2.0215,
"step": 426
},
{
"epoch": 0.7299145299145299,
"grad_norm": 0.734375,
"learning_rate": 6.654503463607223e-06,
"loss": 2.028,
"step": 427
},
{
"epoch": 0.7316239316239316,
"grad_norm": 0.7421875,
"learning_rate": 6.593649078020428e-06,
"loss": 2.2264,
"step": 428
},
{
"epoch": 0.7333333333333333,
"grad_norm": 0.67578125,
"learning_rate": 6.533077782193286e-06,
"loss": 2.1076,
"step": 429
},
{
"epoch": 0.7350427350427351,
"grad_norm": 0.71484375,
"learning_rate": 6.472791448827452e-06,
"loss": 2.089,
"step": 430
},
{
"epoch": 0.7367521367521368,
"grad_norm": 0.71875,
"learning_rate": 6.412791941814323e-06,
"loss": 2.1637,
"step": 431
},
{
"epoch": 0.7384615384615385,
"grad_norm": 1.2578125,
"learning_rate": 6.353081116177383e-06,
"loss": 2.1359,
"step": 432
},
{
"epoch": 0.7401709401709402,
"grad_norm": 0.7578125,
"learning_rate": 6.293660818014867e-06,
"loss": 2.0733,
"step": 433
},
{
"epoch": 0.7418803418803419,
"grad_norm": 0.73046875,
"learning_rate": 6.23453288444268e-06,
"loss": 2.0951,
"step": 434
},
{
"epoch": 0.7435897435897436,
"grad_norm": 0.703125,
"learning_rate": 6.175699143537598e-06,
"loss": 2.1378,
"step": 435
},
{
"epoch": 0.7452991452991453,
"grad_norm": 0.72265625,
"learning_rate": 6.117161414280762e-06,
"loss": 2.074,
"step": 436
},
{
"epoch": 0.747008547008547,
"grad_norm": 0.8359375,
"learning_rate": 6.058921506501418e-06,
"loss": 2.1458,
"step": 437
},
{
"epoch": 0.7487179487179487,
"grad_norm": 0.6953125,
"learning_rate": 6.000981220820969e-06,
"loss": 2.1018,
"step": 438
},
{
"epoch": 0.7504273504273504,
"grad_norm": 0.734375,
"learning_rate": 5.943342348597321e-06,
"loss": 2.0058,
"step": 439
},
{
"epoch": 0.7521367521367521,
"grad_norm": 3.015625,
"learning_rate": 5.886006671869475e-06,
"loss": 2.09,
"step": 440
},
{
"epoch": 0.7538461538461538,
"grad_norm": 0.69921875,
"learning_rate": 5.828975963302447e-06,
"loss": 2.0972,
"step": 441
},
{
"epoch": 0.7555555555555555,
"grad_norm": 0.703125,
"learning_rate": 5.7722519861324555e-06,
"loss": 2.1123,
"step": 442
},
{
"epoch": 0.7572649572649572,
"grad_norm": 0.6796875,
"learning_rate": 5.7158364941124055e-06,
"loss": 2.088,
"step": 443
},
{
"epoch": 0.7589743589743589,
"grad_norm": 0.71875,
"learning_rate": 5.659731231457683e-06,
"loss": 2.1566,
"step": 444
},
{
"epoch": 0.7606837606837606,
"grad_norm": 0.75,
"learning_rate": 5.603937932792203e-06,
"loss": 1.9951,
"step": 445
},
{
"epoch": 0.7623931623931623,
"grad_norm": 0.80859375,
"learning_rate": 5.548458323094793e-06,
"loss": 2.2468,
"step": 446
},
{
"epoch": 0.764102564102564,
"grad_norm": 0.75,
"learning_rate": 5.4932941176458695e-06,
"loss": 2.2119,
"step": 447
},
{
"epoch": 0.7658119658119659,
"grad_norm": 0.7578125,
"learning_rate": 5.438447021974384e-06,
"loss": 2.1758,
"step": 448
},
{
"epoch": 0.7675213675213676,
"grad_norm": 0.6796875,
"learning_rate": 5.383918731805125e-06,
"loss": 2.1041,
"step": 449
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.7734375,
"learning_rate": 5.3297109330062525e-06,
"loss": 2.1552,
"step": 450
},
{
"epoch": 0.7692307692307693,
"eval_loss": 2.2086074352264404,
"eval_runtime": 87.3865,
"eval_samples_per_second": 2.93,
"eval_steps_per_second": 0.492,
"step": 450
},
{
"epoch": 0.770940170940171,
"grad_norm": 0.71875,
"learning_rate": 5.275825301537206e-06,
"loss": 2.2678,
"step": 451
},
{
"epoch": 0.7726495726495727,
"grad_norm": 0.8046875,
"learning_rate": 5.222263503396878e-06,
"loss": 2.0226,
"step": 452
},
{
"epoch": 0.7743589743589744,
"grad_norm": 0.75,
"learning_rate": 5.1690271945721015e-06,
"loss": 2.0454,
"step": 453
},
{
"epoch": 0.7760683760683761,
"grad_norm": 0.72265625,
"learning_rate": 5.116118020986442e-06,
"loss": 2.0621,
"step": 454
},
{
"epoch": 0.7777777777777778,
"grad_norm": 0.7109375,
"learning_rate": 5.063537618449347e-06,
"loss": 2.0435,
"step": 455
},
{
"epoch": 0.7794871794871795,
"grad_norm": 0.76953125,
"learning_rate": 5.011287612605528e-06,
"loss": 2.1819,
"step": 456
},
{
"epoch": 0.7811965811965812,
"grad_norm": 0.6875,
"learning_rate": 4.959369618884735e-06,
"loss": 2.1221,
"step": 457
},
{
"epoch": 0.7829059829059829,
"grad_norm": 0.7734375,
"learning_rate": 4.90778524245178e-06,
"loss": 2.0608,
"step": 458
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.80859375,
"learning_rate": 4.856536078156933e-06,
"loss": 2.0939,
"step": 459
},
{
"epoch": 0.7863247863247863,
"grad_norm": 0.70703125,
"learning_rate": 4.805623710486602e-06,
"loss": 2.137,
"step": 460
},
{
"epoch": 0.788034188034188,
"grad_norm": 0.6796875,
"learning_rate": 4.755049713514353e-06,
"loss": 2.1058,
"step": 461
},
{
"epoch": 0.7897435897435897,
"grad_norm": 0.69921875,
"learning_rate": 4.704815650852232e-06,
"loss": 2.0698,
"step": 462
},
{
"epoch": 0.7914529914529914,
"grad_norm": 0.78125,
"learning_rate": 4.654923075602445e-06,
"loss": 2.06,
"step": 463
},
{
"epoch": 0.7931623931623931,
"grad_norm": 0.828125,
"learning_rate": 4.6053735303093046e-06,
"loss": 2.1291,
"step": 464
},
{
"epoch": 0.7948717948717948,
"grad_norm": 0.69140625,
"learning_rate": 4.556168546911584e-06,
"loss": 2.0345,
"step": 465
},
{
"epoch": 0.7965811965811965,
"grad_norm": 0.6953125,
"learning_rate": 4.5073096466950995e-06,
"loss": 2.0718,
"step": 466
},
{
"epoch": 0.7982905982905983,
"grad_norm": 0.7890625,
"learning_rate": 4.458798340245725e-06,
"loss": 2.1008,
"step": 467
},
{
"epoch": 0.8,
"grad_norm": 0.65625,
"learning_rate": 4.410636127402669e-06,
"loss": 1.9628,
"step": 468
},
{
"epoch": 0.8017094017094017,
"grad_norm": 0.96484375,
"learning_rate": 4.362824497212098e-06,
"loss": 2.2516,
"step": 469
},
{
"epoch": 0.8034188034188035,
"grad_norm": 0.73046875,
"learning_rate": 4.315364927881103e-06,
"loss": 2.0779,
"step": 470
},
{
"epoch": 0.8051282051282052,
"grad_norm": 0.76953125,
"learning_rate": 4.268258886732013e-06,
"loss": 2.1376,
"step": 471
},
{
"epoch": 0.8068376068376069,
"grad_norm": 0.7578125,
"learning_rate": 4.221507830157001e-06,
"loss": 2.297,
"step": 472
},
{
"epoch": 0.8085470085470086,
"grad_norm": 0.734375,
"learning_rate": 4.175113203573074e-06,
"loss": 2.1401,
"step": 473
},
{
"epoch": 0.8102564102564103,
"grad_norm": 0.7421875,
"learning_rate": 4.129076441377391e-06,
"loss": 2.0322,
"step": 474
},
{
"epoch": 0.811965811965812,
"grad_norm": 0.65625,
"learning_rate": 4.08339896690289e-06,
"loss": 2.1333,
"step": 475
},
{
"epoch": 0.8136752136752137,
"grad_norm": 0.76953125,
"learning_rate": 4.038082192374318e-06,
"loss": 2.2644,
"step": 476
},
{
"epoch": 0.8153846153846154,
"grad_norm": 0.6953125,
"learning_rate": 3.993127518864533e-06,
"loss": 2.1901,
"step": 477
},
{
"epoch": 0.8170940170940171,
"grad_norm": 1.0859375,
"learning_rate": 3.948536336251211e-06,
"loss": 2.24,
"step": 478
},
{
"epoch": 0.8188034188034188,
"grad_norm": 0.73046875,
"learning_rate": 3.9043100231738625e-06,
"loss": 1.9705,
"step": 479
},
{
"epoch": 0.8205128205128205,
"grad_norm": 0.75390625,
"learning_rate": 3.8604499469912116e-06,
"loss": 2.2877,
"step": 480
},
{
"epoch": 0.8205128205128205,
"eval_loss": 2.2091357707977295,
"eval_runtime": 87.4532,
"eval_samples_per_second": 2.927,
"eval_steps_per_second": 0.492,
"step": 480
},
{
"epoch": 0.8222222222222222,
"grad_norm": 0.67578125,
"learning_rate": 3.816957463738934e-06,
"loss": 2.2656,
"step": 481
},
{
"epoch": 0.8239316239316239,
"grad_norm": 0.77734375,
"learning_rate": 3.773833918087703e-06,
"loss": 2.0435,
"step": 482
},
{
"epoch": 0.8256410256410256,
"grad_norm": 0.83984375,
"learning_rate": 3.73108064330164e-06,
"loss": 2.1914,
"step": 483
},
{
"epoch": 0.8273504273504273,
"grad_norm": 0.80078125,
"learning_rate": 3.688698961197094e-06,
"loss": 2.0562,
"step": 484
},
{
"epoch": 0.8290598290598291,
"grad_norm": 0.82421875,
"learning_rate": 3.646690182101756e-06,
"loss": 2.1656,
"step": 485
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.78515625,
"learning_rate": 3.6050556048141637e-06,
"loss": 2.0894,
"step": 486
},
{
"epoch": 0.8324786324786325,
"grad_norm": 0.71875,
"learning_rate": 3.5637965165635367e-06,
"loss": 2.3121,
"step": 487
},
{
"epoch": 0.8341880341880342,
"grad_norm": 0.765625,
"learning_rate": 3.5229141929699866e-06,
"loss": 2.1339,
"step": 488
},
{
"epoch": 0.8358974358974359,
"grad_norm": 0.72265625,
"learning_rate": 3.4824098980050767e-06,
"loss": 2.2859,
"step": 489
},
{
"epoch": 0.8376068376068376,
"grad_norm": 0.7734375,
"learning_rate": 3.4422848839527354e-06,
"loss": 2.1567,
"step": 490
},
{
"epoch": 0.8393162393162393,
"grad_norm": 0.6953125,
"learning_rate": 3.402540391370549e-06,
"loss": 1.9865,
"step": 491
},
{
"epoch": 0.841025641025641,
"grad_norm": 0.703125,
"learning_rate": 3.3631776490513983e-06,
"loss": 2.2139,
"step": 492
},
{
"epoch": 0.8427350427350427,
"grad_norm": 0.7109375,
"learning_rate": 3.324197873985478e-06,
"loss": 2.11,
"step": 493
},
{
"epoch": 0.8444444444444444,
"grad_norm": 0.703125,
"learning_rate": 3.285602271322657e-06,
"loss": 2.25,
"step": 494
},
{
"epoch": 0.8461538461538461,
"grad_norm": 0.83984375,
"learning_rate": 3.247392034335236e-06,
"loss": 2.2385,
"step": 495
},
{
"epoch": 0.8478632478632478,
"grad_norm": 0.67578125,
"learning_rate": 3.209568344381034e-06,
"loss": 2.0947,
"step": 496
},
{
"epoch": 0.8495726495726496,
"grad_norm": 0.63671875,
"learning_rate": 3.1721323708668882e-06,
"loss": 2.0096,
"step": 497
},
{
"epoch": 0.8512820512820513,
"grad_norm": 0.7109375,
"learning_rate": 3.1350852712124743e-06,
"loss": 2.1469,
"step": 498
},
{
"epoch": 0.852991452991453,
"grad_norm": 0.6640625,
"learning_rate": 3.0984281908145287e-06,
"loss": 2.1556,
"step": 499
},
{
"epoch": 0.8547008547008547,
"grad_norm": 0.74609375,
"learning_rate": 3.0621622630114583e-06,
"loss": 2.0789,
"step": 500
},
{
"epoch": 0.8564102564102564,
"grad_norm": 0.6875,
"learning_rate": 3.02628860904827e-06,
"loss": 2.171,
"step": 501
},
{
"epoch": 0.8581196581196581,
"grad_norm": 0.76171875,
"learning_rate": 2.9908083380419203e-06,
"loss": 2.0982,
"step": 502
},
{
"epoch": 0.8598290598290599,
"grad_norm": 0.6875,
"learning_rate": 2.955722546947026e-06,
"loss": 2.2207,
"step": 503
},
{
"epoch": 0.8615384615384616,
"grad_norm": 0.78125,
"learning_rate": 2.9210323205219425e-06,
"loss": 1.9915,
"step": 504
},
{
"epoch": 0.8632478632478633,
"grad_norm": 0.734375,
"learning_rate": 2.886738731295229e-06,
"loss": 1.9974,
"step": 505
},
{
"epoch": 0.864957264957265,
"grad_norm": 0.76953125,
"learning_rate": 2.8528428395324852e-06,
"loss": 2.1326,
"step": 506
},
{
"epoch": 0.8666666666666667,
"grad_norm": 0.75,
"learning_rate": 2.8193456932035775e-06,
"loss": 1.9414,
"step": 507
},
{
"epoch": 0.8683760683760684,
"grad_norm": 0.734375,
"learning_rate": 2.7862483279502403e-06,
"loss": 2.0916,
"step": 508
},
{
"epoch": 0.8700854700854701,
"grad_norm": 0.70703125,
"learning_rate": 2.7535517670540443e-06,
"loss": 2.0711,
"step": 509
},
{
"epoch": 0.8717948717948718,
"grad_norm": 0.6875,
"learning_rate": 2.721257021404765e-06,
"loss": 2.191,
"step": 510
},
{
"epoch": 0.8717948717948718,
"eval_loss": 2.2089662551879883,
"eval_runtime": 87.4207,
"eval_samples_per_second": 2.928,
"eval_steps_per_second": 0.492,
"step": 510
},
{
"epoch": 0.8735042735042735,
"grad_norm": 0.72265625,
"learning_rate": 2.6893650894691435e-06,
"loss": 2.2509,
"step": 511
},
{
"epoch": 0.8752136752136752,
"grad_norm": 1.0546875,
"learning_rate": 2.657876957259984e-06,
"loss": 2.107,
"step": 512
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.78515625,
"learning_rate": 2.6267935983057076e-06,
"loss": 2.1271,
"step": 513
},
{
"epoch": 0.8786324786324786,
"grad_norm": 0.73046875,
"learning_rate": 2.5961159736202228e-06,
"loss": 2.0806,
"step": 514
},
{
"epoch": 0.8803418803418803,
"grad_norm": 0.69140625,
"learning_rate": 2.565845031673226e-06,
"loss": 2.101,
"step": 515
},
{
"epoch": 0.882051282051282,
"grad_norm": 0.72265625,
"learning_rate": 2.5359817083608814e-06,
"loss": 2.1485,
"step": 516
},
{
"epoch": 0.8837606837606837,
"grad_norm": 0.7265625,
"learning_rate": 2.506526926976878e-06,
"loss": 2.0093,
"step": 517
},
{
"epoch": 0.8854700854700854,
"grad_norm": 0.81640625,
"learning_rate": 2.477481598183887e-06,
"loss": 2.181,
"step": 518
},
{
"epoch": 0.8871794871794871,
"grad_norm": 0.72265625,
"learning_rate": 2.448846619985401e-06,
"loss": 2.0669,
"step": 519
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.7421875,
"learning_rate": 2.4206228776979827e-06,
"loss": 2.0877,
"step": 520
},
{
"epoch": 0.8905982905982905,
"grad_norm": 0.73828125,
"learning_rate": 2.3928112439238826e-06,
"loss": 2.184,
"step": 521
},
{
"epoch": 0.8923076923076924,
"grad_norm": 0.69140625,
"learning_rate": 2.365412578524063e-06,
"loss": 2.1018,
"step": 522
},
{
"epoch": 0.8940170940170941,
"grad_norm": 0.68359375,
"learning_rate": 2.338427728591617e-06,
"loss": 2.1302,
"step": 523
},
{
"epoch": 0.8957264957264958,
"grad_norm": 0.68359375,
"learning_rate": 2.3118575284255688e-06,
"loss": 2.0938,
"step": 524
},
{
"epoch": 0.8974358974358975,
"grad_norm": 0.7265625,
"learning_rate": 2.285702799505096e-06,
"loss": 2.1044,
"step": 525
},
{
"epoch": 0.8991452991452992,
"grad_norm": 0.76171875,
"learning_rate": 2.2599643504641106e-06,
"loss": 2.0759,
"step": 526
},
{
"epoch": 0.9008547008547009,
"grad_norm": 0.7265625,
"learning_rate": 2.234642977066282e-06,
"loss": 2.0786,
"step": 527
},
{
"epoch": 0.9025641025641026,
"grad_norm": 0.7109375,
"learning_rate": 2.2097394621804117e-06,
"loss": 1.9392,
"step": 528
},
{
"epoch": 0.9042735042735043,
"grad_norm": 0.75,
"learning_rate": 2.1852545757562464e-06,
"loss": 2.0321,
"step": 529
},
{
"epoch": 0.905982905982906,
"grad_norm": 0.6875,
"learning_rate": 2.1611890748006623e-06,
"loss": 2.1365,
"step": 530
},
{
"epoch": 0.9076923076923077,
"grad_norm": 0.77734375,
"learning_rate": 2.1375437033542615e-06,
"loss": 1.9962,
"step": 531
},
{
"epoch": 0.9094017094017094,
"grad_norm": 0.84765625,
"learning_rate": 2.114319192468378e-06,
"loss": 2.1792,
"step": 532
},
{
"epoch": 0.9111111111111111,
"grad_norm": 0.703125,
"learning_rate": 2.0915162601824627e-06,
"loss": 2.2453,
"step": 533
},
{
"epoch": 0.9128205128205128,
"grad_norm": 0.80859375,
"learning_rate": 2.069135611501888e-06,
"loss": 2.0895,
"step": 534
},
{
"epoch": 0.9145299145299145,
"grad_norm": 0.6953125,
"learning_rate": 2.0471779383761617e-06,
"loss": 2.0457,
"step": 535
},
{
"epoch": 0.9162393162393162,
"grad_norm": 0.6953125,
"learning_rate": 2.025643919677515e-06,
"loss": 2.1252,
"step": 536
},
{
"epoch": 0.9179487179487179,
"grad_norm": 0.90234375,
"learning_rate": 2.0045342211799233e-06,
"loss": 2.1175,
"step": 537
},
{
"epoch": 0.9196581196581196,
"grad_norm": 0.75,
"learning_rate": 1.9838494955385296e-06,
"loss": 2.046,
"step": 538
},
{
"epoch": 0.9213675213675213,
"grad_norm": 0.6796875,
"learning_rate": 1.9635903822694477e-06,
"loss": 2.0661,
"step": 539
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.79296875,
"learning_rate": 1.9437575077300116e-06,
"loss": 2.0968,
"step": 540
},
{
"epoch": 0.9230769230769231,
"eval_loss": 2.209021806716919,
"eval_runtime": 87.3032,
"eval_samples_per_second": 2.932,
"eval_steps_per_second": 0.493,
"step": 540
},
{
"epoch": 0.9247863247863248,
"grad_norm": 0.828125,
"learning_rate": 1.924351485099391e-06,
"loss": 1.9799,
"step": 541
},
{
"epoch": 0.9264957264957265,
"grad_norm": 0.703125,
"learning_rate": 1.9053729143596474e-06,
"loss": 2.0514,
"step": 542
},
{
"epoch": 0.9282051282051282,
"grad_norm": 0.72265625,
"learning_rate": 1.8868223822771762e-06,
"loss": 1.9773,
"step": 543
},
{
"epoch": 0.9299145299145299,
"grad_norm": 0.8046875,
"learning_rate": 1.868700462384567e-06,
"loss": 2.0766,
"step": 544
},
{
"epoch": 0.9316239316239316,
"grad_norm": 0.76953125,
"learning_rate": 1.8510077149628763e-06,
"loss": 1.9097,
"step": 545
},
{
"epoch": 0.9333333333333333,
"grad_norm": 0.7578125,
"learning_rate": 1.8337446870242962e-06,
"loss": 2.2116,
"step": 546
},
{
"epoch": 0.935042735042735,
"grad_norm": 0.82421875,
"learning_rate": 1.8169119122952521e-06,
"loss": 2.2928,
"step": 547
},
{
"epoch": 0.9367521367521368,
"grad_norm": 0.6796875,
"learning_rate": 1.8005099111998956e-06,
"loss": 1.9799,
"step": 548
},
{
"epoch": 0.9384615384615385,
"grad_norm": 0.75390625,
"learning_rate": 1.7845391908440125e-06,
"loss": 2.0919,
"step": 549
},
{
"epoch": 0.9401709401709402,
"grad_norm": 0.71484375,
"learning_rate": 1.769000244999349e-06,
"loss": 2.2308,
"step": 550
},
{
"epoch": 0.9418803418803419,
"grad_norm": 0.765625,
"learning_rate": 1.7538935540883466e-06,
"loss": 2.3013,
"step": 551
},
{
"epoch": 0.9435897435897436,
"grad_norm": 0.8046875,
"learning_rate": 1.739219585169283e-06,
"loss": 2.0904,
"step": 552
},
{
"epoch": 0.9452991452991453,
"grad_norm": 0.6875,
"learning_rate": 1.724978791921835e-06,
"loss": 2.0995,
"step": 553
},
{
"epoch": 0.947008547008547,
"grad_norm": 0.7265625,
"learning_rate": 1.7111716146330527e-06,
"loss": 2.0714,
"step": 554
},
{
"epoch": 0.9487179487179487,
"grad_norm": 0.74609375,
"learning_rate": 1.6977984801837467e-06,
"loss": 2.1596,
"step": 555
},
{
"epoch": 0.9504273504273504,
"grad_norm": 0.6953125,
"learning_rate": 1.6848598020352917e-06,
"loss": 2.1768,
"step": 556
},
{
"epoch": 0.9521367521367521,
"grad_norm": 0.7109375,
"learning_rate": 1.672355980216835e-06,
"loss": 2.0674,
"step": 557
},
{
"epoch": 0.9538461538461539,
"grad_norm": 0.7265625,
"learning_rate": 1.6602874013129399e-06,
"loss": 2.1522,
"step": 558
},
{
"epoch": 0.9555555555555556,
"grad_norm": 0.671875,
"learning_rate": 1.6486544384516285e-06,
"loss": 2.2992,
"step": 559
},
{
"epoch": 0.9572649572649573,
"grad_norm": 0.671875,
"learning_rate": 1.637457451292845e-06,
"loss": 2.2374,
"step": 560
},
{
"epoch": 0.958974358974359,
"grad_norm": 0.77734375,
"learning_rate": 1.6266967860173367e-06,
"loss": 2.0391,
"step": 561
},
{
"epoch": 0.9606837606837607,
"grad_norm": 0.76171875,
"learning_rate": 1.6163727753159502e-06,
"loss": 2.1023,
"step": 562
},
{
"epoch": 0.9623931623931624,
"grad_norm": 0.7578125,
"learning_rate": 1.606485738379346e-06,
"loss": 2.0974,
"step": 563
},
{
"epoch": 0.9641025641025641,
"grad_norm": 1.125,
"learning_rate": 1.5970359808881342e-06,
"loss": 2.1806,
"step": 564
},
{
"epoch": 0.9658119658119658,
"grad_norm": 0.78515625,
"learning_rate": 1.588023795003415e-06,
"loss": 2.0956,
"step": 565
},
{
"epoch": 0.9675213675213675,
"grad_norm": 0.71875,
"learning_rate": 1.579449459357751e-06,
"loss": 2.1201,
"step": 566
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.85546875,
"learning_rate": 1.5713132390465588e-06,
"loss": 2.2254,
"step": 567
},
{
"epoch": 0.9709401709401709,
"grad_norm": 0.79296875,
"learning_rate": 1.5636153856198966e-06,
"loss": 2.0627,
"step": 568
},
{
"epoch": 0.9726495726495726,
"grad_norm": 0.734375,
"learning_rate": 1.5563561370747035e-06,
"loss": 2.3508,
"step": 569
},
{
"epoch": 0.9743589743589743,
"grad_norm": 0.67578125,
"learning_rate": 1.5495357178474338e-06,
"loss": 2.2092,
"step": 570
},
{
"epoch": 0.9743589743589743,
"eval_loss": 2.208782434463501,
"eval_runtime": 87.3408,
"eval_samples_per_second": 2.931,
"eval_steps_per_second": 0.492,
"step": 570
},
{
"epoch": 0.976068376068376,
"grad_norm": 0.73046875,
"learning_rate": 1.5431543388071168e-06,
"loss": 2.3499,
"step": 571
},
{
"epoch": 0.9777777777777777,
"grad_norm": 0.75390625,
"learning_rate": 1.5372121972488396e-06,
"loss": 2.0441,
"step": 572
},
{
"epoch": 0.9794871794871794,
"grad_norm": 0.7421875,
"learning_rate": 1.531709476887649e-06,
"loss": 2.1133,
"step": 573
},
{
"epoch": 0.9811965811965812,
"grad_norm": 0.734375,
"learning_rate": 1.5266463478528673e-06,
"loss": 2.1159,
"step": 574
},
{
"epoch": 0.9829059829059829,
"grad_norm": 0.76953125,
"learning_rate": 1.5220229666828372e-06,
"loss": 2.0736,
"step": 575
},
{
"epoch": 0.9846153846153847,
"grad_norm": 0.765625,
"learning_rate": 1.5178394763200736e-06,
"loss": 2.1035,
"step": 576
},
{
"epoch": 0.9863247863247864,
"grad_norm": 0.75,
"learning_rate": 1.5140960061068578e-06,
"loss": 2.1625,
"step": 577
},
{
"epoch": 0.9880341880341881,
"grad_norm": 0.6953125,
"learning_rate": 1.5107926717812242e-06,
"loss": 2.1688,
"step": 578
},
{
"epoch": 0.9897435897435898,
"grad_norm": 0.71484375,
"learning_rate": 1.5079295754733923e-06,
"loss": 2.069,
"step": 579
},
{
"epoch": 0.9914529914529915,
"grad_norm": 0.73046875,
"learning_rate": 1.505506805702605e-06,
"loss": 2.0701,
"step": 580
},
{
"epoch": 0.9931623931623932,
"grad_norm": 0.73828125,
"learning_rate": 1.5035244373743923e-06,
"loss": 2.1343,
"step": 581
},
{
"epoch": 0.9948717948717949,
"grad_norm": 0.796875,
"learning_rate": 1.5019825317782511e-06,
"loss": 2.1275,
"step": 582
},
{
"epoch": 0.9965811965811966,
"grad_norm": 0.90625,
"learning_rate": 1.5008811365857625e-06,
"loss": 2.0288,
"step": 583
},
{
"epoch": 0.9982905982905983,
"grad_norm": 0.74609375,
"learning_rate": 1.5002202858491019e-06,
"loss": 2.0961,
"step": 584
},
{
"epoch": 1.0,
"grad_norm": 0.7265625,
"learning_rate": 1.5e-06,
"loss": 2.016,
"step": 585
}
],
"logging_steps": 1,
"max_steps": 585,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 293,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.091496455831552e+17,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}