nicoboss's picture
Upload folder using huggingface_hub
b1554b2 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 234,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008547008547008548,
"grad_norm": 0.6336084008216858,
"learning_rate": 2e-05,
"loss": 1.2928,
"step": 1
},
{
"epoch": 0.017094017094017096,
"grad_norm": 0.6126894950866699,
"learning_rate": 4e-05,
"loss": 1.1179,
"step": 2
},
{
"epoch": 0.02564102564102564,
"grad_norm": 0.6590365171432495,
"learning_rate": 6e-05,
"loss": 1.2546,
"step": 3
},
{
"epoch": 0.03418803418803419,
"grad_norm": 0.3842516839504242,
"learning_rate": 8e-05,
"loss": 1.402,
"step": 4
},
{
"epoch": 0.042735042735042736,
"grad_norm": 0.7100726962089539,
"learning_rate": 0.0001,
"loss": 1.1523,
"step": 5
},
{
"epoch": 0.05128205128205128,
"grad_norm": 0.4285312592983246,
"learning_rate": 0.00012,
"loss": 1.4567,
"step": 6
},
{
"epoch": 0.05982905982905983,
"grad_norm": 0.5057687163352966,
"learning_rate": 0.00014,
"loss": 1.2153,
"step": 7
},
{
"epoch": 0.06837606837606838,
"grad_norm": 0.3327566683292389,
"learning_rate": 0.00016,
"loss": 1.1503,
"step": 8
},
{
"epoch": 0.07692307692307693,
"grad_norm": 0.29217734932899475,
"learning_rate": 0.00018,
"loss": 0.9723,
"step": 9
},
{
"epoch": 0.08547008547008547,
"grad_norm": 0.5076949000358582,
"learning_rate": 0.0002,
"loss": 1.5848,
"step": 10
},
{
"epoch": 0.09401709401709402,
"grad_norm": 0.40562769770622253,
"learning_rate": 0.0001999976474595967,
"loss": 1.3397,
"step": 11
},
{
"epoch": 0.10256410256410256,
"grad_norm": 0.33129796385765076,
"learning_rate": 0.00019999058994907564,
"loss": 1.0107,
"step": 12
},
{
"epoch": 0.1111111111111111,
"grad_norm": 0.39453431963920593,
"learning_rate": 0.00019997882780049847,
"loss": 1.1293,
"step": 13
},
{
"epoch": 0.11965811965811966,
"grad_norm": 0.3235519826412201,
"learning_rate": 0.0001999623615672837,
"loss": 1.259,
"step": 14
},
{
"epoch": 0.1282051282051282,
"grad_norm": 0.2598688006401062,
"learning_rate": 0.00019994119202418098,
"loss": 1.2164,
"step": 15
},
{
"epoch": 0.13675213675213677,
"grad_norm": 0.2793278992176056,
"learning_rate": 0.00019991532016723439,
"loss": 1.0104,
"step": 16
},
{
"epoch": 0.1452991452991453,
"grad_norm": 0.24649402499198914,
"learning_rate": 0.00019988474721373568,
"loss": 1.2559,
"step": 17
},
{
"epoch": 0.15384615384615385,
"grad_norm": 0.23192395269870758,
"learning_rate": 0.00019984947460216707,
"loss": 0.8831,
"step": 18
},
{
"epoch": 0.1623931623931624,
"grad_norm": 0.2821623384952545,
"learning_rate": 0.00019980950399213344,
"loss": 0.9643,
"step": 19
},
{
"epoch": 0.17094017094017094,
"grad_norm": 0.2398855984210968,
"learning_rate": 0.00019976483726428422,
"loss": 0.9148,
"step": 20
},
{
"epoch": 0.1794871794871795,
"grad_norm": 0.2592308819293976,
"learning_rate": 0.0001997154765202251,
"loss": 0.8939,
"step": 21
},
{
"epoch": 0.18803418803418803,
"grad_norm": 0.25392013788223267,
"learning_rate": 0.00019966142408241901,
"loss": 0.9752,
"step": 22
},
{
"epoch": 0.19658119658119658,
"grad_norm": 0.2928493022918701,
"learning_rate": 0.00019960268249407675,
"loss": 1.0981,
"step": 23
},
{
"epoch": 0.20512820512820512,
"grad_norm": 0.2692890763282776,
"learning_rate": 0.00019953925451903756,
"loss": 0.9699,
"step": 24
},
{
"epoch": 0.21367521367521367,
"grad_norm": 0.23414169251918793,
"learning_rate": 0.0001994711431416389,
"loss": 1.3802,
"step": 25
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.32594603300094604,
"learning_rate": 0.00019939835156657616,
"loss": 1.3705,
"step": 26
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.27903756499290466,
"learning_rate": 0.00019932088321875172,
"loss": 0.9765,
"step": 27
},
{
"epoch": 0.23931623931623933,
"grad_norm": 0.27631697058677673,
"learning_rate": 0.00019923874174311394,
"loss": 0.7924,
"step": 28
},
{
"epoch": 0.24786324786324787,
"grad_norm": 0.28414595127105713,
"learning_rate": 0.0001991519310044857,
"loss": 1.2446,
"step": 29
},
{
"epoch": 0.2564102564102564,
"grad_norm": 0.280527800321579,
"learning_rate": 0.00019906045508738228,
"loss": 1.1986,
"step": 30
},
{
"epoch": 0.26495726495726496,
"grad_norm": 0.25973978638648987,
"learning_rate": 0.0001989643182958196,
"loss": 0.9276,
"step": 31
},
{
"epoch": 0.27350427350427353,
"grad_norm": 0.2691807448863983,
"learning_rate": 0.00019886352515311134,
"loss": 0.9007,
"step": 32
},
{
"epoch": 0.28205128205128205,
"grad_norm": 0.260856032371521,
"learning_rate": 0.0001987580804016563,
"loss": 1.1973,
"step": 33
},
{
"epoch": 0.2905982905982906,
"grad_norm": 0.28188374638557434,
"learning_rate": 0.00019864798900271532,
"loss": 1.1079,
"step": 34
},
{
"epoch": 0.29914529914529914,
"grad_norm": 0.25889885425567627,
"learning_rate": 0.0001985332561361776,
"loss": 0.8755,
"step": 35
},
{
"epoch": 0.3076923076923077,
"grad_norm": 0.2496309131383896,
"learning_rate": 0.00019841388720031727,
"loss": 0.8361,
"step": 36
},
{
"epoch": 0.3162393162393162,
"grad_norm": 0.276593416929245,
"learning_rate": 0.00019828988781153917,
"loss": 0.9342,
"step": 37
},
{
"epoch": 0.3247863247863248,
"grad_norm": 0.24598534405231476,
"learning_rate": 0.00019816126380411476,
"loss": 0.9002,
"step": 38
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.25998443365097046,
"learning_rate": 0.00019802802122990758,
"loss": 1.0115,
"step": 39
},
{
"epoch": 0.3418803418803419,
"grad_norm": 0.2910752594470978,
"learning_rate": 0.00019789016635808837,
"loss": 1.1122,
"step": 40
},
{
"epoch": 0.3504273504273504,
"grad_norm": 0.23144645988941193,
"learning_rate": 0.00019774770567484022,
"loss": 1.0541,
"step": 41
},
{
"epoch": 0.358974358974359,
"grad_norm": 0.23637208342552185,
"learning_rate": 0.00019760064588305345,
"loss": 0.9,
"step": 42
},
{
"epoch": 0.36752136752136755,
"grad_norm": 0.24016380310058594,
"learning_rate": 0.00019744899390201006,
"loss": 0.9473,
"step": 43
},
{
"epoch": 0.37606837606837606,
"grad_norm": 0.23975665867328644,
"learning_rate": 0.0001972927568670583,
"loss": 1.361,
"step": 44
},
{
"epoch": 0.38461538461538464,
"grad_norm": 0.2693803310394287,
"learning_rate": 0.00019713194212927696,
"loss": 1.1029,
"step": 45
},
{
"epoch": 0.39316239316239315,
"grad_norm": 0.2764308452606201,
"learning_rate": 0.00019696655725512933,
"loss": 0.9312,
"step": 46
},
{
"epoch": 0.4017094017094017,
"grad_norm": 0.25453776121139526,
"learning_rate": 0.00019679661002610743,
"loss": 0.9677,
"step": 47
},
{
"epoch": 0.41025641025641024,
"grad_norm": 0.26758676767349243,
"learning_rate": 0.00019662210843836574,
"loss": 0.9591,
"step": 48
},
{
"epoch": 0.4188034188034188,
"grad_norm": 0.27530986070632935,
"learning_rate": 0.0001964430607023449,
"loss": 0.9504,
"step": 49
},
{
"epoch": 0.42735042735042733,
"grad_norm": 0.2969217896461487,
"learning_rate": 0.00019625947524238563,
"loss": 1.11,
"step": 50
},
{
"epoch": 0.4358974358974359,
"grad_norm": 0.26885175704956055,
"learning_rate": 0.00019607136069633212,
"loss": 0.8923,
"step": 51
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.255889892578125,
"learning_rate": 0.0001958787259151258,
"loss": 0.9118,
"step": 52
},
{
"epoch": 0.452991452991453,
"grad_norm": 0.2702856659889221,
"learning_rate": 0.00019568157996238884,
"loss": 0.9143,
"step": 53
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.2267722338438034,
"learning_rate": 0.0001954799321139975,
"loss": 1.1196,
"step": 54
},
{
"epoch": 0.4700854700854701,
"grad_norm": 0.23851439356803894,
"learning_rate": 0.00019527379185764612,
"loss": 0.8702,
"step": 55
},
{
"epoch": 0.47863247863247865,
"grad_norm": 0.30145585536956787,
"learning_rate": 0.00019506316889240027,
"loss": 1.4398,
"step": 56
},
{
"epoch": 0.48717948717948717,
"grad_norm": 0.2665199339389801,
"learning_rate": 0.00019484807312824067,
"loss": 0.8006,
"step": 57
},
{
"epoch": 0.49572649572649574,
"grad_norm": 0.3289227783679962,
"learning_rate": 0.0001946285146855968,
"loss": 0.9466,
"step": 58
},
{
"epoch": 0.5042735042735043,
"grad_norm": 0.2549362778663635,
"learning_rate": 0.0001944045038948709,
"loss": 0.8871,
"step": 59
},
{
"epoch": 0.5128205128205128,
"grad_norm": 0.289874792098999,
"learning_rate": 0.00019417605129595157,
"loss": 0.8717,
"step": 60
},
{
"epoch": 0.5213675213675214,
"grad_norm": 0.32114192843437195,
"learning_rate": 0.0001939431676377183,
"loss": 0.9448,
"step": 61
},
{
"epoch": 0.5299145299145299,
"grad_norm": 0.2595084309577942,
"learning_rate": 0.0001937058638775353,
"loss": 0.8295,
"step": 62
},
{
"epoch": 0.5384615384615384,
"grad_norm": 0.22089529037475586,
"learning_rate": 0.00019346415118073632,
"loss": 1.2068,
"step": 63
},
{
"epoch": 0.5470085470085471,
"grad_norm": 0.3057108223438263,
"learning_rate": 0.00019321804092009906,
"loss": 0.9483,
"step": 64
},
{
"epoch": 0.5555555555555556,
"grad_norm": 0.2628245949745178,
"learning_rate": 0.00019296754467531014,
"loss": 0.928,
"step": 65
},
{
"epoch": 0.5641025641025641,
"grad_norm": 0.31952518224716187,
"learning_rate": 0.00019271267423242024,
"loss": 0.9064,
"step": 66
},
{
"epoch": 0.5726495726495726,
"grad_norm": 0.2862078845500946,
"learning_rate": 0.00019245344158328972,
"loss": 1.0335,
"step": 67
},
{
"epoch": 0.5811965811965812,
"grad_norm": 0.27666571736335754,
"learning_rate": 0.0001921898589250242,
"loss": 0.8877,
"step": 68
},
{
"epoch": 0.5897435897435898,
"grad_norm": 0.24311263859272003,
"learning_rate": 0.0001919219386594007,
"loss": 0.8868,
"step": 69
},
{
"epoch": 0.5982905982905983,
"grad_norm": 0.2716294825077057,
"learning_rate": 0.00019164969339228422,
"loss": 0.9431,
"step": 70
},
{
"epoch": 0.6068376068376068,
"grad_norm": 0.3183337152004242,
"learning_rate": 0.00019137313593303463,
"loss": 1.0538,
"step": 71
},
{
"epoch": 0.6153846153846154,
"grad_norm": 0.2670356333255768,
"learning_rate": 0.00019109227929390378,
"loss": 1.3404,
"step": 72
},
{
"epoch": 0.6239316239316239,
"grad_norm": 0.26112431287765503,
"learning_rate": 0.00019080713668942356,
"loss": 0.8849,
"step": 73
},
{
"epoch": 0.6324786324786325,
"grad_norm": 0.3271474838256836,
"learning_rate": 0.00019051772153578389,
"loss": 1.0236,
"step": 74
},
{
"epoch": 0.6410256410256411,
"grad_norm": 0.32266974449157715,
"learning_rate": 0.00019022404745020163,
"loss": 0.8979,
"step": 75
},
{
"epoch": 0.6495726495726496,
"grad_norm": 0.2465939223766327,
"learning_rate": 0.00018992612825027976,
"loss": 0.891,
"step": 76
},
{
"epoch": 0.6581196581196581,
"grad_norm": 0.31744077801704407,
"learning_rate": 0.0001896239779533575,
"loss": 1.0727,
"step": 77
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.2582801878452301,
"learning_rate": 0.00018931761077585035,
"loss": 0.9047,
"step": 78
},
{
"epoch": 0.6752136752136753,
"grad_norm": 0.25554949045181274,
"learning_rate": 0.00018900704113258165,
"loss": 0.8029,
"step": 79
},
{
"epoch": 0.6837606837606838,
"grad_norm": 0.2558218836784363,
"learning_rate": 0.00018869228363610404,
"loss": 0.8504,
"step": 80
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.3036883771419525,
"learning_rate": 0.00018837335309601213,
"loss": 0.9286,
"step": 81
},
{
"epoch": 0.7008547008547008,
"grad_norm": 0.24368591606616974,
"learning_rate": 0.00018805026451824546,
"loss": 1.4037,
"step": 82
},
{
"epoch": 0.7094017094017094,
"grad_norm": 0.22905252873897552,
"learning_rate": 0.00018772303310438275,
"loss": 1.2179,
"step": 83
},
{
"epoch": 0.717948717948718,
"grad_norm": 0.3644798696041107,
"learning_rate": 0.00018739167425092644,
"loss": 1.3658,
"step": 84
},
{
"epoch": 0.7264957264957265,
"grad_norm": 0.25496625900268555,
"learning_rate": 0.00018705620354857833,
"loss": 0.7991,
"step": 85
},
{
"epoch": 0.7350427350427351,
"grad_norm": 0.2917548418045044,
"learning_rate": 0.00018671663678150607,
"loss": 0.7979,
"step": 86
},
{
"epoch": 0.7435897435897436,
"grad_norm": 0.2509627342224121,
"learning_rate": 0.0001863729899266004,
"loss": 0.8439,
"step": 87
},
{
"epoch": 0.7521367521367521,
"grad_norm": 0.26703646779060364,
"learning_rate": 0.0001860252791527236,
"loss": 1.1359,
"step": 88
},
{
"epoch": 0.7606837606837606,
"grad_norm": 0.2911994159221649,
"learning_rate": 0.00018567352081994852,
"loss": 1.378,
"step": 89
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.24897685647010803,
"learning_rate": 0.00018531773147878895,
"loss": 1.1141,
"step": 90
},
{
"epoch": 0.7777777777777778,
"grad_norm": 0.28840702772140503,
"learning_rate": 0.0001849579278694209,
"loss": 0.9043,
"step": 91
},
{
"epoch": 0.7863247863247863,
"grad_norm": 0.2617591619491577,
"learning_rate": 0.00018459412692089494,
"loss": 0.7995,
"step": 92
},
{
"epoch": 0.7948717948717948,
"grad_norm": 0.2502082586288452,
"learning_rate": 0.0001842263457503397,
"loss": 0.789,
"step": 93
},
{
"epoch": 0.8034188034188035,
"grad_norm": 0.30928075313568115,
"learning_rate": 0.00018385460166215638,
"loss": 0.9983,
"step": 94
},
{
"epoch": 0.811965811965812,
"grad_norm": 0.33725544810295105,
"learning_rate": 0.00018347891214720477,
"loss": 0.955,
"step": 95
},
{
"epoch": 0.8205128205128205,
"grad_norm": 0.24872225522994995,
"learning_rate": 0.00018309929488198012,
"loss": 1.1854,
"step": 96
},
{
"epoch": 0.8290598290598291,
"grad_norm": 0.2822365462779999,
"learning_rate": 0.00018271576772778154,
"loss": 0.8358,
"step": 97
},
{
"epoch": 0.8376068376068376,
"grad_norm": 0.2920995056629181,
"learning_rate": 0.00018232834872987147,
"loss": 1.3358,
"step": 98
},
{
"epoch": 0.8461538461538461,
"grad_norm": 0.303602397441864,
"learning_rate": 0.00018193705611662696,
"loss": 0.9797,
"step": 99
},
{
"epoch": 0.8547008547008547,
"grad_norm": 0.3406928479671478,
"learning_rate": 0.0001815419082986815,
"loss": 0.9816,
"step": 100
},
{
"epoch": 0.8632478632478633,
"grad_norm": 0.22692528367042542,
"learning_rate": 0.00018114292386805936,
"loss": 1.221,
"step": 101
},
{
"epoch": 0.8717948717948718,
"grad_norm": 0.22570784389972687,
"learning_rate": 0.00018074012159730032,
"loss": 1.1856,
"step": 102
},
{
"epoch": 0.8803418803418803,
"grad_norm": 0.2517668306827545,
"learning_rate": 0.00018033352043857675,
"loss": 1.1498,
"step": 103
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.27244430780410767,
"learning_rate": 0.00017992313952280172,
"loss": 1.1015,
"step": 104
},
{
"epoch": 0.8974358974358975,
"grad_norm": 0.3242965638637543,
"learning_rate": 0.00017950899815872892,
"loss": 1.2942,
"step": 105
},
{
"epoch": 0.905982905982906,
"grad_norm": 0.32707729935646057,
"learning_rate": 0.00017909111583204422,
"loss": 1.2383,
"step": 106
},
{
"epoch": 0.9145299145299145,
"grad_norm": 0.37845203280448914,
"learning_rate": 0.0001786695122044487,
"loss": 0.9584,
"step": 107
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.26341512799263,
"learning_rate": 0.0001782442071127338,
"loss": 1.1443,
"step": 108
},
{
"epoch": 0.9316239316239316,
"grad_norm": 0.3688293397426605,
"learning_rate": 0.0001778152205678477,
"loss": 1.5414,
"step": 109
},
{
"epoch": 0.9401709401709402,
"grad_norm": 0.3266530930995941,
"learning_rate": 0.00017738257275395404,
"loss": 1.0778,
"step": 110
},
{
"epoch": 0.9487179487179487,
"grad_norm": 0.4219954311847687,
"learning_rate": 0.00017694628402748202,
"loss": 1.1903,
"step": 111
},
{
"epoch": 0.9572649572649573,
"grad_norm": 0.28938961029052734,
"learning_rate": 0.0001765063749161688,
"loss": 0.8998,
"step": 112
},
{
"epoch": 0.9658119658119658,
"grad_norm": 0.3432457745075226,
"learning_rate": 0.00017606286611809353,
"loss": 0.9684,
"step": 113
},
{
"epoch": 0.9743589743589743,
"grad_norm": 0.26857873797416687,
"learning_rate": 0.00017561577850070355,
"loss": 1.0045,
"step": 114
},
{
"epoch": 0.9829059829059829,
"grad_norm": 0.24974624812602997,
"learning_rate": 0.00017516513309983253,
"loss": 0.7979,
"step": 115
},
{
"epoch": 0.9914529914529915,
"grad_norm": 0.343883752822876,
"learning_rate": 0.00017471095111871074,
"loss": 1.0162,
"step": 116
},
{
"epoch": 1.0,
"grad_norm": 0.29970595240592957,
"learning_rate": 0.0001742532539269674,
"loss": 0.8354,
"step": 117
},
{
"epoch": 1.0085470085470085,
"grad_norm": 0.2625507414340973,
"learning_rate": 0.00017379206305962526,
"loss": 0.7908,
"step": 118
},
{
"epoch": 1.017094017094017,
"grad_norm": 0.2953716814517975,
"learning_rate": 0.00017332740021608722,
"loss": 0.8421,
"step": 119
},
{
"epoch": 1.0256410256410255,
"grad_norm": 0.4784148931503296,
"learning_rate": 0.00017285928725911562,
"loss": 1.2155,
"step": 120
},
{
"epoch": 1.0341880341880343,
"grad_norm": 0.5949030518531799,
"learning_rate": 0.00017238774621380337,
"loss": 1.2108,
"step": 121
},
{
"epoch": 1.0427350427350428,
"grad_norm": 0.41158854961395264,
"learning_rate": 0.00017191279926653761,
"loss": 1.5972,
"step": 122
},
{
"epoch": 1.0512820512820513,
"grad_norm": 0.31010663509368896,
"learning_rate": 0.00017143446876395602,
"loss": 1.1852,
"step": 123
},
{
"epoch": 1.0598290598290598,
"grad_norm": 0.300396203994751,
"learning_rate": 0.00017095277721189528,
"loss": 1.1387,
"step": 124
},
{
"epoch": 1.0683760683760684,
"grad_norm": 0.570995032787323,
"learning_rate": 0.00017046774727433222,
"loss": 1.0398,
"step": 125
},
{
"epoch": 1.0769230769230769,
"grad_norm": 0.3038155734539032,
"learning_rate": 0.00016997940177231722,
"loss": 0.7614,
"step": 126
},
{
"epoch": 1.0854700854700854,
"grad_norm": 0.27748215198516846,
"learning_rate": 0.00016948776368290084,
"loss": 1.0286,
"step": 127
},
{
"epoch": 1.0940170940170941,
"grad_norm": 0.3376232981681824,
"learning_rate": 0.00016899285613805246,
"loss": 0.7464,
"step": 128
},
{
"epoch": 1.1025641025641026,
"grad_norm": 0.33782312273979187,
"learning_rate": 0.00016849470242357196,
"loss": 0.7747,
"step": 129
},
{
"epoch": 1.1111111111111112,
"grad_norm": 0.30509698390960693,
"learning_rate": 0.00016799332597799413,
"loss": 0.8188,
"step": 130
},
{
"epoch": 1.1196581196581197,
"grad_norm": 0.2920445203781128,
"learning_rate": 0.00016748875039148593,
"loss": 1.0563,
"step": 131
},
{
"epoch": 1.1282051282051282,
"grad_norm": 0.30515843629837036,
"learning_rate": 0.0001669809994047364,
"loss": 1.0849,
"step": 132
},
{
"epoch": 1.1367521367521367,
"grad_norm": 0.35152626037597656,
"learning_rate": 0.0001664700969078398,
"loss": 0.9146,
"step": 133
},
{
"epoch": 1.1452991452991452,
"grad_norm": 0.318646103143692,
"learning_rate": 0.00016595606693917142,
"loss": 1.1709,
"step": 134
},
{
"epoch": 1.1538461538461537,
"grad_norm": 0.2702546715736389,
"learning_rate": 0.00016543893368425666,
"loss": 0.7313,
"step": 135
},
{
"epoch": 1.1623931623931625,
"grad_norm": 0.3528870940208435,
"learning_rate": 0.00016491872147463306,
"loss": 0.8208,
"step": 136
},
{
"epoch": 1.170940170940171,
"grad_norm": 0.28231188654899597,
"learning_rate": 0.00016439545478670543,
"loss": 1.7001,
"step": 137
},
{
"epoch": 1.1794871794871795,
"grad_norm": 0.3122393488883972,
"learning_rate": 0.00016386915824059427,
"loss": 0.7343,
"step": 138
},
{
"epoch": 1.188034188034188,
"grad_norm": 0.2875630855560303,
"learning_rate": 0.00016333985659897735,
"loss": 0.7207,
"step": 139
},
{
"epoch": 1.1965811965811965,
"grad_norm": 0.38364624977111816,
"learning_rate": 0.00016280757476592466,
"loss": 0.779,
"step": 140
},
{
"epoch": 1.205128205128205,
"grad_norm": 0.30091550946235657,
"learning_rate": 0.0001622723377857265,
"loss": 0.7685,
"step": 141
},
{
"epoch": 1.2136752136752136,
"grad_norm": 0.28651681542396545,
"learning_rate": 0.00016173417084171536,
"loss": 1.1618,
"step": 142
},
{
"epoch": 1.2222222222222223,
"grad_norm": 0.3049664795398712,
"learning_rate": 0.00016119309925508078,
"loss": 0.7262,
"step": 143
},
{
"epoch": 1.2307692307692308,
"grad_norm": 0.38781028985977173,
"learning_rate": 0.0001606491484836782,
"loss": 0.8057,
"step": 144
},
{
"epoch": 1.2393162393162394,
"grad_norm": 0.3604777455329895,
"learning_rate": 0.00016010234412083086,
"loss": 0.8435,
"step": 145
},
{
"epoch": 1.2478632478632479,
"grad_norm": 0.3753257691860199,
"learning_rate": 0.00015955271189412598,
"loss": 0.8945,
"step": 146
},
{
"epoch": 1.2564102564102564,
"grad_norm": 0.35498958826065063,
"learning_rate": 0.00015900027766420393,
"loss": 0.7545,
"step": 147
},
{
"epoch": 1.264957264957265,
"grad_norm": 0.337697833776474,
"learning_rate": 0.00015844506742354164,
"loss": 0.8178,
"step": 148
},
{
"epoch": 1.2735042735042734,
"grad_norm": 0.34326887130737305,
"learning_rate": 0.00015788710729522953,
"loss": 0.9658,
"step": 149
},
{
"epoch": 1.282051282051282,
"grad_norm": 0.3605210483074188,
"learning_rate": 0.00015732642353174259,
"loss": 1.1598,
"step": 150
},
{
"epoch": 1.2905982905982907,
"grad_norm": 0.2907405197620392,
"learning_rate": 0.0001567630425137049,
"loss": 0.6474,
"step": 151
},
{
"epoch": 1.2991452991452992,
"grad_norm": 0.36666378378868103,
"learning_rate": 0.00015619699074864864,
"loss": 0.772,
"step": 152
},
{
"epoch": 1.3076923076923077,
"grad_norm": 0.42435774207115173,
"learning_rate": 0.00015562829486976673,
"loss": 0.8633,
"step": 153
},
{
"epoch": 1.3162393162393162,
"grad_norm": 0.34810835123062134,
"learning_rate": 0.00015505698163465986,
"loss": 0.982,
"step": 154
},
{
"epoch": 1.3247863247863247,
"grad_norm": 0.38605523109436035,
"learning_rate": 0.00015448307792407734,
"loss": 0.7854,
"step": 155
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.3216642439365387,
"learning_rate": 0.00015390661074065256,
"loss": 0.7786,
"step": 156
},
{
"epoch": 1.341880341880342,
"grad_norm": 0.3482376039028168,
"learning_rate": 0.00015332760720763232,
"loss": 1.1516,
"step": 157
},
{
"epoch": 1.3504273504273505,
"grad_norm": 0.4383181035518646,
"learning_rate": 0.00015274609456760073,
"loss": 0.8356,
"step": 158
},
{
"epoch": 1.358974358974359,
"grad_norm": 0.415587842464447,
"learning_rate": 0.00015216210018119733,
"loss": 1.0019,
"step": 159
},
{
"epoch": 1.3675213675213675,
"grad_norm": 0.36597633361816406,
"learning_rate": 0.00015157565152583002,
"loss": 0.7382,
"step": 160
},
{
"epoch": 1.376068376068376,
"grad_norm": 0.36167895793914795,
"learning_rate": 0.0001509867761943818,
"loss": 0.9089,
"step": 161
},
{
"epoch": 1.3846153846153846,
"grad_norm": 0.35900619626045227,
"learning_rate": 0.00015039550189391298,
"loss": 0.7338,
"step": 162
},
{
"epoch": 1.393162393162393,
"grad_norm": 0.3245941996574402,
"learning_rate": 0.0001498018564443571,
"loss": 1.0774,
"step": 163
},
{
"epoch": 1.4017094017094016,
"grad_norm": 0.3721596896648407,
"learning_rate": 0.0001492058677772123,
"loss": 0.9292,
"step": 164
},
{
"epoch": 1.4102564102564101,
"grad_norm": 0.37743324041366577,
"learning_rate": 0.000148607563934227,
"loss": 0.812,
"step": 165
},
{
"epoch": 1.4188034188034189,
"grad_norm": 0.30644622445106506,
"learning_rate": 0.00014800697306608044,
"loss": 0.6427,
"step": 166
},
{
"epoch": 1.4273504273504274,
"grad_norm": 0.39433762431144714,
"learning_rate": 0.00014740412343105828,
"loss": 0.9262,
"step": 167
},
{
"epoch": 1.435897435897436,
"grad_norm": 0.34150931239128113,
"learning_rate": 0.00014679904339372302,
"loss": 0.7721,
"step": 168
},
{
"epoch": 1.4444444444444444,
"grad_norm": 0.3927769064903259,
"learning_rate": 0.00014619176142357935,
"loss": 0.7861,
"step": 169
},
{
"epoch": 1.452991452991453,
"grad_norm": 0.3742867410182953,
"learning_rate": 0.0001455823060937347,
"loss": 0.8983,
"step": 170
},
{
"epoch": 1.4615384615384617,
"grad_norm": 0.3988594114780426,
"learning_rate": 0.00014497070607955476,
"loss": 0.7946,
"step": 171
},
{
"epoch": 1.4700854700854702,
"grad_norm": 0.3588651418685913,
"learning_rate": 0.00014435699015731448,
"loss": 0.7881,
"step": 172
},
{
"epoch": 1.4786324786324787,
"grad_norm": 0.3405568599700928,
"learning_rate": 0.00014374118720284388,
"loss": 0.8645,
"step": 173
},
{
"epoch": 1.4871794871794872,
"grad_norm": 0.2791353762149811,
"learning_rate": 0.00014312332619016965,
"loss": 0.9498,
"step": 174
},
{
"epoch": 1.4957264957264957,
"grad_norm": 0.3834662139415741,
"learning_rate": 0.0001425034361901516,
"loss": 0.8281,
"step": 175
},
{
"epoch": 1.5042735042735043,
"grad_norm": 0.40144065022468567,
"learning_rate": 0.00014188154636911524,
"loss": 1.4235,
"step": 176
},
{
"epoch": 1.5128205128205128,
"grad_norm": 0.4115220606327057,
"learning_rate": 0.0001412576859874791,
"loss": 0.7451,
"step": 177
},
{
"epoch": 1.5213675213675213,
"grad_norm": 0.3392897844314575,
"learning_rate": 0.00014063188439837832,
"loss": 0.7047,
"step": 178
},
{
"epoch": 1.5299145299145298,
"grad_norm": 0.3308214545249939,
"learning_rate": 0.0001400041710462833,
"loss": 0.7011,
"step": 179
},
{
"epoch": 1.5384615384615383,
"grad_norm": 0.3544357419013977,
"learning_rate": 0.0001393745754656146,
"loss": 0.7985,
"step": 180
},
{
"epoch": 1.547008547008547,
"grad_norm": 0.3125544488430023,
"learning_rate": 0.00013874312727935292,
"loss": 0.7115,
"step": 181
},
{
"epoch": 1.5555555555555556,
"grad_norm": 0.31898999214172363,
"learning_rate": 0.00013810985619764572,
"loss": 1.1459,
"step": 182
},
{
"epoch": 1.564102564102564,
"grad_norm": 0.3448270857334137,
"learning_rate": 0.00013747479201640914,
"loss": 0.6875,
"step": 183
},
{
"epoch": 1.5726495726495726,
"grad_norm": 0.4556581676006317,
"learning_rate": 0.00013683796461592604,
"loss": 0.8871,
"step": 184
},
{
"epoch": 1.5811965811965814,
"grad_norm": 0.3367992341518402,
"learning_rate": 0.00013619940395944027,
"loss": 0.7687,
"step": 185
},
{
"epoch": 1.5897435897435899,
"grad_norm": 0.35872966051101685,
"learning_rate": 0.00013555914009174663,
"loss": 0.8261,
"step": 186
},
{
"epoch": 1.5982905982905984,
"grad_norm": 0.3715200424194336,
"learning_rate": 0.00013491720313777756,
"loss": 1.3308,
"step": 187
},
{
"epoch": 1.606837606837607,
"grad_norm": 0.3741316497325897,
"learning_rate": 0.00013427362330118543,
"loss": 0.7169,
"step": 188
},
{
"epoch": 1.6153846153846154,
"grad_norm": 0.3634923994541168,
"learning_rate": 0.0001336284308629216,
"loss": 0.9805,
"step": 189
},
{
"epoch": 1.623931623931624,
"grad_norm": 0.3144815266132355,
"learning_rate": 0.00013298165617981172,
"loss": 1.0045,
"step": 190
},
{
"epoch": 1.6324786324786325,
"grad_norm": 0.4095522463321686,
"learning_rate": 0.00013233332968312715,
"loss": 1.1136,
"step": 191
},
{
"epoch": 1.641025641025641,
"grad_norm": 0.35933032631874084,
"learning_rate": 0.0001316834818771535,
"loss": 0.8102,
"step": 192
},
{
"epoch": 1.6495726495726495,
"grad_norm": 0.4028998911380768,
"learning_rate": 0.00013103214333775521,
"loss": 0.843,
"step": 193
},
{
"epoch": 1.658119658119658,
"grad_norm": 0.401076078414917,
"learning_rate": 0.00013037934471093682,
"loss": 0.6997,
"step": 194
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.36478322744369507,
"learning_rate": 0.00012972511671140125,
"loss": 0.7362,
"step": 195
},
{
"epoch": 1.6752136752136753,
"grad_norm": 0.3325231969356537,
"learning_rate": 0.00012906949012110456,
"loss": 0.9889,
"step": 196
},
{
"epoch": 1.6837606837606838,
"grad_norm": 0.3909556567668915,
"learning_rate": 0.00012841249578780757,
"loss": 0.8985,
"step": 197
},
{
"epoch": 1.6923076923076923,
"grad_norm": 0.31815868616104126,
"learning_rate": 0.00012775416462362457,
"loss": 0.8205,
"step": 198
},
{
"epoch": 1.7008547008547008,
"grad_norm": 0.3717130124568939,
"learning_rate": 0.00012709452760356884,
"loss": 1.2108,
"step": 199
},
{
"epoch": 1.7094017094017095,
"grad_norm": 0.3459589183330536,
"learning_rate": 0.00012643361576409516,
"loss": 0.8245,
"step": 200
},
{
"epoch": 1.717948717948718,
"grad_norm": 0.3962521255016327,
"learning_rate": 0.00012577146020163968,
"loss": 0.8364,
"step": 201
},
{
"epoch": 1.7264957264957266,
"grad_norm": 0.41842907667160034,
"learning_rate": 0.00012510809207115666,
"loss": 0.7526,
"step": 202
},
{
"epoch": 1.735042735042735,
"grad_norm": 0.3551943302154541,
"learning_rate": 0.00012444354258465268,
"loss": 0.7563,
"step": 203
},
{
"epoch": 1.7435897435897436,
"grad_norm": 0.3701689541339874,
"learning_rate": 0.00012377784300971807,
"loss": 1.0242,
"step": 204
},
{
"epoch": 1.7521367521367521,
"grad_norm": 0.34136760234832764,
"learning_rate": 0.0001231110246680558,
"loss": 1.1623,
"step": 205
},
{
"epoch": 1.7606837606837606,
"grad_norm": 0.45741143822669983,
"learning_rate": 0.00012244311893400763,
"loss": 0.912,
"step": 206
},
{
"epoch": 1.7692307692307692,
"grad_norm": 0.44242578744888306,
"learning_rate": 0.00012177415723307808,
"loss": 0.7916,
"step": 207
},
{
"epoch": 1.7777777777777777,
"grad_norm": 0.3459125757217407,
"learning_rate": 0.00012110417104045575,
"loss": 0.6614,
"step": 208
},
{
"epoch": 1.7863247863247862,
"grad_norm": 0.3435271382331848,
"learning_rate": 0.00012043319187953241,
"loss": 0.8433,
"step": 209
},
{
"epoch": 1.7948717948717947,
"grad_norm": 0.404305636882782,
"learning_rate": 0.00011976125132041974,
"loss": 0.8646,
"step": 210
},
{
"epoch": 1.8034188034188035,
"grad_norm": 0.5799421668052673,
"learning_rate": 0.00011908838097846404,
"loss": 1.3677,
"step": 211
},
{
"epoch": 1.811965811965812,
"grad_norm": 0.370825856924057,
"learning_rate": 0.00011841461251275867,
"loss": 1.0736,
"step": 212
},
{
"epoch": 1.8205128205128205,
"grad_norm": 0.43012121319770813,
"learning_rate": 0.00011773997762465429,
"loss": 0.8208,
"step": 213
},
{
"epoch": 1.8290598290598292,
"grad_norm": 0.33933213353157043,
"learning_rate": 0.0001170645080562676,
"loss": 0.7598,
"step": 214
},
{
"epoch": 1.8376068376068377,
"grad_norm": 0.35830000042915344,
"learning_rate": 0.00011638823558898762,
"loss": 0.7402,
"step": 215
},
{
"epoch": 1.8461538461538463,
"grad_norm": 0.37512725591659546,
"learning_rate": 0.00011571119204198037,
"loss": 0.7306,
"step": 216
},
{
"epoch": 1.8547008547008548,
"grad_norm": 0.35193270444869995,
"learning_rate": 0.00011503340927069189,
"loss": 0.8577,
"step": 217
},
{
"epoch": 1.8632478632478633,
"grad_norm": 0.3259103000164032,
"learning_rate": 0.00011435491916534919,
"loss": 0.7147,
"step": 218
},
{
"epoch": 1.8717948717948718,
"grad_norm": 0.3664517402648926,
"learning_rate": 0.00011367575364946006,
"loss": 0.7411,
"step": 219
},
{
"epoch": 1.8803418803418803,
"grad_norm": 0.428186297416687,
"learning_rate": 0.00011299594467831078,
"loss": 0.7532,
"step": 220
},
{
"epoch": 1.8888888888888888,
"grad_norm": 0.4050661623477936,
"learning_rate": 0.00011231552423746283,
"loss": 0.7799,
"step": 221
},
{
"epoch": 1.8974358974358974,
"grad_norm": 0.3434165120124817,
"learning_rate": 0.00011163452434124773,
"loss": 0.7433,
"step": 222
},
{
"epoch": 1.9059829059829059,
"grad_norm": 0.4107282757759094,
"learning_rate": 0.00011095297703126093,
"loss": 0.7374,
"step": 223
},
{
"epoch": 1.9145299145299144,
"grad_norm": 0.4014933109283447,
"learning_rate": 0.00011027091437485404,
"loss": 0.9252,
"step": 224
},
{
"epoch": 1.9230769230769231,
"grad_norm": 0.3325748145580292,
"learning_rate": 0.00010958836846362621,
"loss": 0.9575,
"step": 225
},
{
"epoch": 1.9316239316239316,
"grad_norm": 0.3845024108886719,
"learning_rate": 0.00010890537141191417,
"loss": 0.7212,
"step": 226
},
{
"epoch": 1.9401709401709402,
"grad_norm": 0.3581906855106354,
"learning_rate": 0.00010822195535528106,
"loss": 1.015,
"step": 227
},
{
"epoch": 1.9487179487179487,
"grad_norm": 0.38040146231651306,
"learning_rate": 0.00010753815244900458,
"loss": 0.6995,
"step": 228
},
{
"epoch": 1.9572649572649574,
"grad_norm": 0.4363343119621277,
"learning_rate": 0.00010685399486656406,
"loss": 0.7875,
"step": 229
},
{
"epoch": 1.965811965811966,
"grad_norm": 0.374661386013031,
"learning_rate": 0.00010616951479812658,
"loss": 0.7548,
"step": 230
},
{
"epoch": 1.9743589743589745,
"grad_norm": 0.37670278549194336,
"learning_rate": 0.00010548474444903247,
"loss": 0.6929,
"step": 231
},
{
"epoch": 1.982905982905983,
"grad_norm": 0.3678586483001709,
"learning_rate": 0.00010479971603828,
"loss": 0.6928,
"step": 232
},
{
"epoch": 1.9914529914529915,
"grad_norm": 0.33861783146858215,
"learning_rate": 0.00010411446179700943,
"loss": 0.7386,
"step": 233
},
{
"epoch": 2.0,
"grad_norm": 0.8249924182891846,
"learning_rate": 0.00010342901396698659,
"loss": 1.1202,
"step": 234
}
],
"logging_steps": 1,
"max_steps": 468,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 117,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.575906760753152e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}