adaption_indian_finance_dataset / trainer_state.json
Vishykm's picture
Upload LoRA adapter + model card
f852851 verified
Raw
History Blame Contribute Delete
127 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 139,
"global_step": 695,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007194244604316547,
"grad_norm": 1.2740105390548706,
"learning_rate": 0.0,
"loss": 1.5126953125,
"step": 1
},
{
"epoch": 0.014388489208633094,
"grad_norm": 1.0922791957855225,
"learning_rate": 9.523809523809523e-06,
"loss": 1.4228515625,
"step": 2
},
{
"epoch": 0.02158273381294964,
"grad_norm": 1.1397159099578857,
"learning_rate": 1.9047619047619046e-05,
"loss": 1.4287109375,
"step": 3
},
{
"epoch": 0.02877697841726619,
"grad_norm": 0.8145934343338013,
"learning_rate": 2.857142857142857e-05,
"loss": 1.302734375,
"step": 4
},
{
"epoch": 0.03597122302158273,
"grad_norm": 0.9380262494087219,
"learning_rate": 3.809523809523809e-05,
"loss": 1.369140625,
"step": 5
},
{
"epoch": 0.04316546762589928,
"grad_norm": 0.599651038646698,
"learning_rate": 4.761904761904762e-05,
"loss": 1.2685546875,
"step": 6
},
{
"epoch": 0.050359712230215826,
"grad_norm": 0.6546977162361145,
"learning_rate": 5.714285714285714e-05,
"loss": 1.3193359375,
"step": 7
},
{
"epoch": 0.05755395683453238,
"grad_norm": 0.41727596521377563,
"learning_rate": 6.666666666666667e-05,
"loss": 1.2490234375,
"step": 8
},
{
"epoch": 0.06474820143884892,
"grad_norm": 0.1556597650051117,
"learning_rate": 7.619047619047618e-05,
"loss": 1.16796875,
"step": 9
},
{
"epoch": 0.07194244604316546,
"grad_norm": 0.17217369377613068,
"learning_rate": 8.571428571428571e-05,
"loss": 1.1708984375,
"step": 10
},
{
"epoch": 0.07913669064748201,
"grad_norm": 0.1754201352596283,
"learning_rate": 9.523809523809524e-05,
"loss": 1.06787109375,
"step": 11
},
{
"epoch": 0.08633093525179857,
"grad_norm": 0.15675853192806244,
"learning_rate": 0.00010476190476190477,
"loss": 1.1591796875,
"step": 12
},
{
"epoch": 0.09352517985611511,
"grad_norm": 0.09932417422533035,
"learning_rate": 0.00011428571428571428,
"loss": 0.89385986328125,
"step": 13
},
{
"epoch": 0.10071942446043165,
"grad_norm": 0.08258306980133057,
"learning_rate": 0.0001238095238095238,
"loss": 1.07861328125,
"step": 14
},
{
"epoch": 0.1079136690647482,
"grad_norm": 0.06987421959638596,
"learning_rate": 0.00013333333333333334,
"loss": 1.04150390625,
"step": 15
},
{
"epoch": 0.11510791366906475,
"grad_norm": 0.06813070178031921,
"learning_rate": 0.00014285714285714287,
"loss": 1.07861328125,
"step": 16
},
{
"epoch": 0.1223021582733813,
"grad_norm": 0.07993105053901672,
"learning_rate": 0.00015238095238095237,
"loss": 1.01318359375,
"step": 17
},
{
"epoch": 0.12949640287769784,
"grad_norm": 0.0885189101099968,
"learning_rate": 0.00016190476190476192,
"loss": 0.99951171875,
"step": 18
},
{
"epoch": 0.1366906474820144,
"grad_norm": 0.08386443555355072,
"learning_rate": 0.00017142857142857143,
"loss": 1.017578125,
"step": 19
},
{
"epoch": 0.14388489208633093,
"grad_norm": 0.05822071060538292,
"learning_rate": 0.00018095238095238095,
"loss": 0.9580078125,
"step": 20
},
{
"epoch": 0.1510791366906475,
"grad_norm": 0.057313933968544006,
"learning_rate": 0.00019047619047619048,
"loss": 1.05029296875,
"step": 21
},
{
"epoch": 0.15827338129496402,
"grad_norm": 0.05194910615682602,
"learning_rate": 0.0002,
"loss": 1.015625,
"step": 22
},
{
"epoch": 0.16546762589928057,
"grad_norm": 0.05323383957147598,
"learning_rate": 0.00019999902233137137,
"loss": 0.982421875,
"step": 23
},
{
"epoch": 0.17266187050359713,
"grad_norm": 0.05862591415643692,
"learning_rate": 0.0001999960893467262,
"loss": 1.02294921875,
"step": 24
},
{
"epoch": 0.17985611510791366,
"grad_norm": 0.051530636847019196,
"learning_rate": 0.0001999912011097865,
"loss": 0.9765625,
"step": 25
},
{
"epoch": 0.18705035971223022,
"grad_norm": 0.052456848323345184,
"learning_rate": 0.00019998435772675393,
"loss": 0.982421875,
"step": 26
},
{
"epoch": 0.19424460431654678,
"grad_norm": 0.06001245975494385,
"learning_rate": 0.0001999755593463076,
"loss": 0.98095703125,
"step": 27
},
{
"epoch": 0.2014388489208633,
"grad_norm": 0.040204279124736786,
"learning_rate": 0.00019996480615960084,
"loss": 0.9716796875,
"step": 28
},
{
"epoch": 0.20863309352517986,
"grad_norm": 0.04036633297801018,
"learning_rate": 0.00019995209840025714,
"loss": 1.0419921875,
"step": 29
},
{
"epoch": 0.2158273381294964,
"grad_norm": 0.04662039503455162,
"learning_rate": 0.0001999374363443648,
"loss": 0.998046875,
"step": 30
},
{
"epoch": 0.22302158273381295,
"grad_norm": 0.049975793808698654,
"learning_rate": 0.00019992082031047127,
"loss": 1.02587890625,
"step": 31
},
{
"epoch": 0.2302158273381295,
"grad_norm": 0.03617478907108307,
"learning_rate": 0.00019990225065957595,
"loss": 0.9755859375,
"step": 32
},
{
"epoch": 0.23741007194244604,
"grad_norm": 0.04134185612201691,
"learning_rate": 0.00019988172779512251,
"loss": 1.0048828125,
"step": 33
},
{
"epoch": 0.2446043165467626,
"grad_norm": 0.03744431585073471,
"learning_rate": 0.00019985925216299007,
"loss": 0.888916015625,
"step": 34
},
{
"epoch": 0.2517985611510791,
"grad_norm": 0.040840551257133484,
"learning_rate": 0.00019983482425148363,
"loss": 1.00244140625,
"step": 35
},
{
"epoch": 0.2589928057553957,
"grad_norm": 0.03377190977334976,
"learning_rate": 0.00019980844459132312,
"loss": 0.99560546875,
"step": 36
},
{
"epoch": 0.26618705035971224,
"grad_norm": 0.044599633663892746,
"learning_rate": 0.0001997801137556323,
"loss": 0.96826171875,
"step": 37
},
{
"epoch": 0.2733812949640288,
"grad_norm": 0.039601460099220276,
"learning_rate": 0.000199749832359926,
"loss": 1.015625,
"step": 38
},
{
"epoch": 0.2805755395683453,
"grad_norm": 0.03437861055135727,
"learning_rate": 0.00019971760106209693,
"loss": 0.98291015625,
"step": 39
},
{
"epoch": 0.28776978417266186,
"grad_norm": 0.03787188231945038,
"learning_rate": 0.00019968342056240132,
"loss": 0.94189453125,
"step": 40
},
{
"epoch": 0.2949640287769784,
"grad_norm": 0.03449779376387596,
"learning_rate": 0.0001996472916034436,
"loss": 1.001953125,
"step": 41
},
{
"epoch": 0.302158273381295,
"grad_norm": 0.03647533804178238,
"learning_rate": 0.00019960921497016047,
"loss": 0.89794921875,
"step": 42
},
{
"epoch": 0.30935251798561153,
"grad_norm": 0.04127081111073494,
"learning_rate": 0.0001995691914898037,
"loss": 0.970703125,
"step": 43
},
{
"epoch": 0.31654676258992803,
"grad_norm": 0.03455884009599686,
"learning_rate": 0.00019952722203192216,
"loss": 0.95361328125,
"step": 44
},
{
"epoch": 0.3237410071942446,
"grad_norm": 0.03288467973470688,
"learning_rate": 0.0001994833075083431,
"loss": 0.9228515625,
"step": 45
},
{
"epoch": 0.33093525179856115,
"grad_norm": 0.03765524923801422,
"learning_rate": 0.000199437448873152,
"loss": 0.9755859375,
"step": 46
},
{
"epoch": 0.3381294964028777,
"grad_norm": 0.033325761556625366,
"learning_rate": 0.0001993896471226723,
"loss": 0.9853515625,
"step": 47
},
{
"epoch": 0.34532374100719426,
"grad_norm": 0.03614553064107895,
"learning_rate": 0.0001993399032954433,
"loss": 0.8349609375,
"step": 48
},
{
"epoch": 0.35251798561151076,
"grad_norm": 0.03610741347074509,
"learning_rate": 0.00019928821847219787,
"loss": 0.93359375,
"step": 49
},
{
"epoch": 0.3597122302158273,
"grad_norm": 0.033615849912166595,
"learning_rate": 0.00019923459377583897,
"loss": 0.9326171875,
"step": 50
},
{
"epoch": 0.3669064748201439,
"grad_norm": 0.03550311177968979,
"learning_rate": 0.00019917903037141506,
"loss": 0.93408203125,
"step": 51
},
{
"epoch": 0.37410071942446044,
"grad_norm": 0.033074114471673965,
"learning_rate": 0.00019912152946609496,
"loss": 0.958984375,
"step": 52
},
{
"epoch": 0.381294964028777,
"grad_norm": 0.03114013373851776,
"learning_rate": 0.00019906209230914163,
"loss": 0.861083984375,
"step": 53
},
{
"epoch": 0.38848920863309355,
"grad_norm": 0.034017328172922134,
"learning_rate": 0.0001990007201918849,
"loss": 0.83349609375,
"step": 54
},
{
"epoch": 0.39568345323741005,
"grad_norm": 0.033433377742767334,
"learning_rate": 0.00019893741444769353,
"loss": 0.951171875,
"step": 55
},
{
"epoch": 0.4028776978417266,
"grad_norm": 0.030669622123241425,
"learning_rate": 0.00019887217645194618,
"loss": 0.8057861328125,
"step": 56
},
{
"epoch": 0.41007194244604317,
"grad_norm": 0.03568951413035393,
"learning_rate": 0.0001988050076220016,
"loss": 0.87744140625,
"step": 57
},
{
"epoch": 0.4172661870503597,
"grad_norm": 0.032321978360414505,
"learning_rate": 0.0001987359094171677,
"loss": 0.91015625,
"step": 58
},
{
"epoch": 0.4244604316546763,
"grad_norm": 0.03285544365644455,
"learning_rate": 0.00019866488333866996,
"loss": 0.9775390625,
"step": 59
},
{
"epoch": 0.4316546762589928,
"grad_norm": 0.037065550684928894,
"learning_rate": 0.00019859193092961884,
"loss": 0.91162109375,
"step": 60
},
{
"epoch": 0.43884892086330934,
"grad_norm": 0.03526630997657776,
"learning_rate": 0.00019851705377497617,
"loss": 0.96826171875,
"step": 61
},
{
"epoch": 0.4460431654676259,
"grad_norm": 0.03333820402622223,
"learning_rate": 0.00019844025350152064,
"loss": 0.91552734375,
"step": 62
},
{
"epoch": 0.45323741007194246,
"grad_norm": 0.03711729869246483,
"learning_rate": 0.00019836153177781274,
"loss": 0.939453125,
"step": 63
},
{
"epoch": 0.460431654676259,
"grad_norm": 0.03602234646677971,
"learning_rate": 0.00019828089031415823,
"loss": 0.9169921875,
"step": 64
},
{
"epoch": 0.4676258992805755,
"grad_norm": 0.0468483567237854,
"learning_rate": 0.00019819833086257103,
"loss": 0.921875,
"step": 65
},
{
"epoch": 0.4748201438848921,
"grad_norm": 0.03359710052609444,
"learning_rate": 0.0001981138552167353,
"loss": 0.916015625,
"step": 66
},
{
"epoch": 0.48201438848920863,
"grad_norm": 0.035829126834869385,
"learning_rate": 0.00019802746521196634,
"loss": 0.78118896484375,
"step": 67
},
{
"epoch": 0.4892086330935252,
"grad_norm": 0.03570085018873215,
"learning_rate": 0.00019793916272517083,
"loss": 0.9755859375,
"step": 68
},
{
"epoch": 0.49640287769784175,
"grad_norm": 0.03758750483393669,
"learning_rate": 0.00019784894967480582,
"loss": 0.93701171875,
"step": 69
},
{
"epoch": 0.5035971223021583,
"grad_norm": 0.06137075647711754,
"learning_rate": 0.0001977568280208373,
"loss": 0.87646484375,
"step": 70
},
{
"epoch": 0.5107913669064749,
"grad_norm": 0.03948725014925003,
"learning_rate": 0.0001976627997646976,
"loss": 0.91064453125,
"step": 71
},
{
"epoch": 0.5179856115107914,
"grad_norm": 0.03830637037754059,
"learning_rate": 0.00019756686694924166,
"loss": 0.78033447265625,
"step": 72
},
{
"epoch": 0.5251798561151079,
"grad_norm": 0.047548238188028336,
"learning_rate": 0.00019746903165870295,
"loss": 0.92431640625,
"step": 73
},
{
"epoch": 0.5323741007194245,
"grad_norm": 0.036909766495227814,
"learning_rate": 0.000197369296018648,
"loss": 0.92578125,
"step": 74
},
{
"epoch": 0.539568345323741,
"grad_norm": 0.03877877816557884,
"learning_rate": 0.00019726766219593027,
"loss": 0.9306640625,
"step": 75
},
{
"epoch": 0.5467625899280576,
"grad_norm": 0.03954843431711197,
"learning_rate": 0.0001971641323986431,
"loss": 0.92236328125,
"step": 76
},
{
"epoch": 0.5539568345323741,
"grad_norm": 0.06077041104435921,
"learning_rate": 0.00019705870887607173,
"loss": 0.88720703125,
"step": 77
},
{
"epoch": 0.5611510791366906,
"grad_norm": 0.03632822260260582,
"learning_rate": 0.00019695139391864437,
"loss": 0.8642578125,
"step": 78
},
{
"epoch": 0.5683453237410072,
"grad_norm": 0.03626861795783043,
"learning_rate": 0.00019684218985788253,
"loss": 0.87060546875,
"step": 79
},
{
"epoch": 0.5755395683453237,
"grad_norm": 0.038949914276599884,
"learning_rate": 0.00019673109906635035,
"loss": 0.9072265625,
"step": 80
},
{
"epoch": 0.5827338129496403,
"grad_norm": 0.03690135106444359,
"learning_rate": 0.0001966181239576029,
"loss": 0.89453125,
"step": 81
},
{
"epoch": 0.5899280575539568,
"grad_norm": 0.03546570986509323,
"learning_rate": 0.000196503266986134,
"loss": 0.89013671875,
"step": 82
},
{
"epoch": 0.5971223021582733,
"grad_norm": 0.03941057249903679,
"learning_rate": 0.0001963865306473227,
"loss": 0.95361328125,
"step": 83
},
{
"epoch": 0.60431654676259,
"grad_norm": 0.03758455812931061,
"learning_rate": 0.00019626791747737911,
"loss": 0.90966796875,
"step": 84
},
{
"epoch": 0.6115107913669064,
"grad_norm": 0.03954232856631279,
"learning_rate": 0.00019614743005328942,
"loss": 0.84033203125,
"step": 85
},
{
"epoch": 0.6187050359712231,
"grad_norm": 0.15771588683128357,
"learning_rate": 0.00019602507099275972,
"loss": 0.81475830078125,
"step": 86
},
{
"epoch": 0.6258992805755396,
"grad_norm": 0.03690027445554733,
"learning_rate": 0.0001959008429541591,
"loss": 0.93359375,
"step": 87
},
{
"epoch": 0.6330935251798561,
"grad_norm": 0.036794792860746384,
"learning_rate": 0.00019577474863646232,
"loss": 0.9453125,
"step": 88
},
{
"epoch": 0.6402877697841727,
"grad_norm": 0.039687883108854294,
"learning_rate": 0.0001956467907791906,
"loss": 0.89501953125,
"step": 89
},
{
"epoch": 0.6474820143884892,
"grad_norm": 0.038429245352745056,
"learning_rate": 0.00019551697216235243,
"loss": 0.94384765625,
"step": 90
},
{
"epoch": 0.6546762589928058,
"grad_norm": 0.04024427756667137,
"learning_rate": 0.00019538529560638316,
"loss": 0.8984375,
"step": 91
},
{
"epoch": 0.6618705035971223,
"grad_norm": 0.038315415382385254,
"learning_rate": 0.0001952517639720836,
"loss": 0.923828125,
"step": 92
},
{
"epoch": 0.6690647482014388,
"grad_norm": 0.04527967795729637,
"learning_rate": 0.000195116380160558,
"loss": 0.92138671875,
"step": 93
},
{
"epoch": 0.6762589928057554,
"grad_norm": 0.03957796469330788,
"learning_rate": 0.00019497914711315092,
"loss": 0.8818359375,
"step": 94
},
{
"epoch": 0.6834532374100719,
"grad_norm": 0.03690025955438614,
"learning_rate": 0.00019484006781138332,
"loss": 0.78460693359375,
"step": 95
},
{
"epoch": 0.6906474820143885,
"grad_norm": 0.038028962910175323,
"learning_rate": 0.00019469914527688793,
"loss": 0.91015625,
"step": 96
},
{
"epoch": 0.697841726618705,
"grad_norm": 0.037732917815446854,
"learning_rate": 0.00019455638257134342,
"loss": 0.8701171875,
"step": 97
},
{
"epoch": 0.7050359712230215,
"grad_norm": 0.03742627054452896,
"learning_rate": 0.00019441178279640798,
"loss": 0.92236328125,
"step": 98
},
{
"epoch": 0.7122302158273381,
"grad_norm": 0.05680155009031296,
"learning_rate": 0.00019426534909365188,
"loss": 0.80908203125,
"step": 99
},
{
"epoch": 0.7194244604316546,
"grad_norm": 0.04044618457555771,
"learning_rate": 0.00019411708464448933,
"loss": 0.92822265625,
"step": 100
},
{
"epoch": 0.7266187050359713,
"grad_norm": 0.03669159486889839,
"learning_rate": 0.00019396699267010926,
"loss": 0.82958984375,
"step": 101
},
{
"epoch": 0.7338129496402878,
"grad_norm": 0.045204147696495056,
"learning_rate": 0.00019381507643140522,
"loss": 0.904296875,
"step": 102
},
{
"epoch": 0.7410071942446043,
"grad_norm": 0.03760795667767525,
"learning_rate": 0.0001936613392289049,
"loss": 0.84033203125,
"step": 103
},
{
"epoch": 0.7482014388489209,
"grad_norm": 0.03825001046061516,
"learning_rate": 0.00019350578440269803,
"loss": 0.91552734375,
"step": 104
},
{
"epoch": 0.7553956834532374,
"grad_norm": 0.04174284636974335,
"learning_rate": 0.000193348415332364,
"loss": 0.85693359375,
"step": 105
},
{
"epoch": 0.762589928057554,
"grad_norm": 0.03811310604214668,
"learning_rate": 0.00019318923543689843,
"loss": 0.8121337890625,
"step": 106
},
{
"epoch": 0.7697841726618705,
"grad_norm": 0.04138203337788582,
"learning_rate": 0.00019302824817463897,
"loss": 0.91796875,
"step": 107
},
{
"epoch": 0.7769784172661871,
"grad_norm": 0.041395582258701324,
"learning_rate": 0.00019286545704318985,
"loss": 0.92138671875,
"step": 108
},
{
"epoch": 0.7841726618705036,
"grad_norm": 0.043065961450338364,
"learning_rate": 0.00019270086557934634,
"loss": 0.92529296875,
"step": 109
},
{
"epoch": 0.7913669064748201,
"grad_norm": 0.04372436925768852,
"learning_rate": 0.00019253447735901748,
"loss": 0.89892578125,
"step": 110
},
{
"epoch": 0.7985611510791367,
"grad_norm": 0.04174291715025902,
"learning_rate": 0.00019236629599714874,
"loss": 0.8544921875,
"step": 111
},
{
"epoch": 0.8057553956834532,
"grad_norm": 0.03858775272965431,
"learning_rate": 0.00019219632514764324,
"loss": 0.8818359375,
"step": 112
},
{
"epoch": 0.8129496402877698,
"grad_norm": 0.04208751022815704,
"learning_rate": 0.00019202456850328246,
"loss": 0.9140625,
"step": 113
},
{
"epoch": 0.8201438848920863,
"grad_norm": 0.035770632326602936,
"learning_rate": 0.00019185102979564603,
"loss": 0.88037109375,
"step": 114
},
{
"epoch": 0.8273381294964028,
"grad_norm": 0.04098818823695183,
"learning_rate": 0.00019167571279503064,
"loss": 0.861328125,
"step": 115
},
{
"epoch": 0.8345323741007195,
"grad_norm": 0.04136794060468674,
"learning_rate": 0.00019149862131036808,
"loss": 0.93408203125,
"step": 116
},
{
"epoch": 0.841726618705036,
"grad_norm": 0.039565086364746094,
"learning_rate": 0.00019131975918914256,
"loss": 0.9208984375,
"step": 117
},
{
"epoch": 0.8489208633093526,
"grad_norm": 0.04092320799827576,
"learning_rate": 0.00019113913031730705,
"loss": 0.77410888671875,
"step": 118
},
{
"epoch": 0.8561151079136691,
"grad_norm": 0.04495199769735336,
"learning_rate": 0.00019095673861919897,
"loss": 0.77880859375,
"step": 119
},
{
"epoch": 0.8633093525179856,
"grad_norm": 0.04074163734912872,
"learning_rate": 0.00019077258805745475,
"loss": 0.8564453125,
"step": 120
},
{
"epoch": 0.8705035971223022,
"grad_norm": 0.041033197194337845,
"learning_rate": 0.00019058668263292392,
"loss": 0.8740234375,
"step": 121
},
{
"epoch": 0.8776978417266187,
"grad_norm": 0.041623760014772415,
"learning_rate": 0.00019039902638458202,
"loss": 0.88232421875,
"step": 122
},
{
"epoch": 0.8848920863309353,
"grad_norm": 0.04127103462815285,
"learning_rate": 0.00019020962338944298,
"loss": 0.86962890625,
"step": 123
},
{
"epoch": 0.8920863309352518,
"grad_norm": 0.04037206247448921,
"learning_rate": 0.00019001847776247059,
"loss": 0.90625,
"step": 124
},
{
"epoch": 0.8992805755395683,
"grad_norm": 0.039783403277397156,
"learning_rate": 0.00018982559365648881,
"loss": 0.9013671875,
"step": 125
},
{
"epoch": 0.9064748201438849,
"grad_norm": 0.04106175899505615,
"learning_rate": 0.00018963097526209194,
"loss": 0.7947998046875,
"step": 126
},
{
"epoch": 0.9136690647482014,
"grad_norm": 0.03610210120677948,
"learning_rate": 0.0001894346268075532,
"loss": 0.7130889892578125,
"step": 127
},
{
"epoch": 0.920863309352518,
"grad_norm": 0.04131530225276947,
"learning_rate": 0.00018923655255873316,
"loss": 0.8466796875,
"step": 128
},
{
"epoch": 0.9280575539568345,
"grad_norm": 0.04450669884681702,
"learning_rate": 0.00018903675681898694,
"loss": 0.85205078125,
"step": 129
},
{
"epoch": 0.935251798561151,
"grad_norm": 0.03795908764004707,
"learning_rate": 0.00018883524392907067,
"loss": 0.859375,
"step": 130
},
{
"epoch": 0.9424460431654677,
"grad_norm": 0.04205196723341942,
"learning_rate": 0.00018863201826704726,
"loss": 0.82275390625,
"step": 131
},
{
"epoch": 0.9496402877697842,
"grad_norm": 0.04331479221582413,
"learning_rate": 0.00018842708424819123,
"loss": 0.84765625,
"step": 132
},
{
"epoch": 0.9568345323741008,
"grad_norm": 0.0463370755314827,
"learning_rate": 0.0001882204463248929,
"loss": 0.84228515625,
"step": 133
},
{
"epoch": 0.9640287769784173,
"grad_norm": 0.03884037211537361,
"learning_rate": 0.00018801210898656138,
"loss": 0.83544921875,
"step": 134
},
{
"epoch": 0.9712230215827338,
"grad_norm": 0.04231853038072586,
"learning_rate": 0.00018780207675952746,
"loss": 0.865234375,
"step": 135
},
{
"epoch": 0.9784172661870504,
"grad_norm": 0.03976970911026001,
"learning_rate": 0.00018759035420694477,
"loss": 0.9111328125,
"step": 136
},
{
"epoch": 0.9856115107913669,
"grad_norm": 0.04041573777794838,
"learning_rate": 0.00018737694592869115,
"loss": 0.8828125,
"step": 137
},
{
"epoch": 0.9928057553956835,
"grad_norm": 0.04609952121973038,
"learning_rate": 0.0001871618565612683,
"loss": 0.8857421875,
"step": 138
},
{
"epoch": 1.0,
"grad_norm": 0.03594762831926346,
"learning_rate": 0.00018694509077770127,
"loss": 0.7578125,
"step": 139
},
{
"epoch": 1.0,
"eval_loss": 0.854248046875,
"eval_runtime": 2.169,
"eval_samples_per_second": 3.227,
"eval_steps_per_second": 0.461,
"step": 139
},
{
"epoch": 1.0071942446043165,
"grad_norm": 0.04719629883766174,
"learning_rate": 0.00018672665328743686,
"loss": 0.8671875,
"step": 140
},
{
"epoch": 1.014388489208633,
"grad_norm": 0.038122113794088364,
"learning_rate": 0.0001865065488362413,
"loss": 0.86572265625,
"step": 141
},
{
"epoch": 1.0215827338129497,
"grad_norm": 0.05462534353137016,
"learning_rate": 0.00018628478220609725,
"loss": 0.8779296875,
"step": 142
},
{
"epoch": 1.0287769784172662,
"grad_norm": 0.040146417915821075,
"learning_rate": 0.00018606135821509976,
"loss": 0.83984375,
"step": 143
},
{
"epoch": 1.0359712230215827,
"grad_norm": 0.04147570580244064,
"learning_rate": 0.00018583628171735158,
"loss": 0.888671875,
"step": 144
},
{
"epoch": 1.0431654676258992,
"grad_norm": 0.04189106449484825,
"learning_rate": 0.0001856095576028579,
"loss": 0.8828125,
"step": 145
},
{
"epoch": 1.0503597122302157,
"grad_norm": 0.03803461417555809,
"learning_rate": 0.00018538119079741992,
"loss": 0.92333984375,
"step": 146
},
{
"epoch": 1.0575539568345325,
"grad_norm": 0.04352770000696182,
"learning_rate": 0.0001851511862625278,
"loss": 0.91455078125,
"step": 147
},
{
"epoch": 1.064748201438849,
"grad_norm": 0.04023844748735428,
"learning_rate": 0.0001849195489952532,
"loss": 0.904296875,
"step": 148
},
{
"epoch": 1.0719424460431655,
"grad_norm": 0.0442805141210556,
"learning_rate": 0.00018468628402814027,
"loss": 0.89892578125,
"step": 149
},
{
"epoch": 1.079136690647482,
"grad_norm": 0.04029758274555206,
"learning_rate": 0.00018445139642909653,
"loss": 0.82373046875,
"step": 150
},
{
"epoch": 1.0863309352517985,
"grad_norm": 0.042711906135082245,
"learning_rate": 0.00018421489130128284,
"loss": 0.91796875,
"step": 151
},
{
"epoch": 1.0935251798561152,
"grad_norm": 0.04179690405726433,
"learning_rate": 0.0001839767737830024,
"loss": 0.702850341796875,
"step": 152
},
{
"epoch": 1.1007194244604317,
"grad_norm": 0.04072112590074539,
"learning_rate": 0.0001837370490475892,
"loss": 0.86572265625,
"step": 153
},
{
"epoch": 1.1079136690647482,
"grad_norm": 0.04115098714828491,
"learning_rate": 0.00018349572230329545,
"loss": 0.84521484375,
"step": 154
},
{
"epoch": 1.1151079136690647,
"grad_norm": 0.04058322310447693,
"learning_rate": 0.0001832527987931787,
"loss": 0.88623046875,
"step": 155
},
{
"epoch": 1.1223021582733812,
"grad_norm": 0.039891667664051056,
"learning_rate": 0.0001830082837949877,
"loss": 0.8359375,
"step": 156
},
{
"epoch": 1.129496402877698,
"grad_norm": 0.04415520653128624,
"learning_rate": 0.00018276218262104784,
"loss": 0.822265625,
"step": 157
},
{
"epoch": 1.1366906474820144,
"grad_norm": 0.044313881546258926,
"learning_rate": 0.00018251450061814578,
"loss": 0.83349609375,
"step": 158
},
{
"epoch": 1.143884892086331,
"grad_norm": 0.04146198928356171,
"learning_rate": 0.0001822652431674131,
"loss": 0.7998046875,
"step": 159
},
{
"epoch": 1.1510791366906474,
"grad_norm": 0.0369773805141449,
"learning_rate": 0.00018201441568420964,
"loss": 0.89013671875,
"step": 160
},
{
"epoch": 1.158273381294964,
"grad_norm": 0.047404732555150986,
"learning_rate": 0.00018176202361800563,
"loss": 0.8603515625,
"step": 161
},
{
"epoch": 1.1654676258992807,
"grad_norm": 0.03837458789348602,
"learning_rate": 0.00018150807245226336,
"loss": 0.83251953125,
"step": 162
},
{
"epoch": 1.1726618705035972,
"grad_norm": 0.040407221764326096,
"learning_rate": 0.0001812525677043182,
"loss": 0.87109375,
"step": 163
},
{
"epoch": 1.1798561151079137,
"grad_norm": 0.04459042102098465,
"learning_rate": 0.00018099551492525848,
"loss": 0.83154296875,
"step": 164
},
{
"epoch": 1.1870503597122302,
"grad_norm": 0.03853633254766464,
"learning_rate": 0.00018073691969980503,
"loss": 0.84375,
"step": 165
},
{
"epoch": 1.1942446043165469,
"grad_norm": 0.04119209945201874,
"learning_rate": 0.00018047678764618986,
"loss": 0.83837890625,
"step": 166
},
{
"epoch": 1.2014388489208634,
"grad_norm": 0.038234688341617584,
"learning_rate": 0.00018021512441603404,
"loss": 0.8349609375,
"step": 167
},
{
"epoch": 1.20863309352518,
"grad_norm": 0.04290073364973068,
"learning_rate": 0.0001799519356942249,
"loss": 0.91259765625,
"step": 168
},
{
"epoch": 1.2158273381294964,
"grad_norm": 0.040559135377407074,
"learning_rate": 0.00017968722719879265,
"loss": 0.86767578125,
"step": 169
},
{
"epoch": 1.223021582733813,
"grad_norm": 0.04216361045837402,
"learning_rate": 0.00017942100468078593,
"loss": 0.89404296875,
"step": 170
},
{
"epoch": 1.2302158273381294,
"grad_norm": 0.04037407413125038,
"learning_rate": 0.0001791532739241471,
"loss": 0.85400390625,
"step": 171
},
{
"epoch": 1.2374100719424461,
"grad_norm": 0.03771575912833214,
"learning_rate": 0.00017888404074558643,
"loss": 0.87548828125,
"step": 172
},
{
"epoch": 1.2446043165467626,
"grad_norm": 0.03865155950188637,
"learning_rate": 0.00017861331099445568,
"loss": 0.7830810546875,
"step": 173
},
{
"epoch": 1.2517985611510791,
"grad_norm": 0.04672296717762947,
"learning_rate": 0.00017834109055262125,
"loss": 0.88330078125,
"step": 174
},
{
"epoch": 1.2589928057553956,
"grad_norm": 0.03719188645482063,
"learning_rate": 0.00017806738533433612,
"loss": 0.88720703125,
"step": 175
},
{
"epoch": 1.2661870503597124,
"grad_norm": 0.05398380756378174,
"learning_rate": 0.00017779220128611153,
"loss": 0.85107421875,
"step": 176
},
{
"epoch": 1.2733812949640289,
"grad_norm": 0.04401341453194618,
"learning_rate": 0.00017751554438658773,
"loss": 0.90185546875,
"step": 177
},
{
"epoch": 1.2805755395683454,
"grad_norm": 0.04876876249909401,
"learning_rate": 0.0001772374206464041,
"loss": 0.87255859375,
"step": 178
},
{
"epoch": 1.2877697841726619,
"grad_norm": 0.03931674733757973,
"learning_rate": 0.00017695783610806854,
"loss": 0.8349609375,
"step": 179
},
{
"epoch": 1.2949640287769784,
"grad_norm": 0.046616338193416595,
"learning_rate": 0.00017667679684582615,
"loss": 0.8916015625,
"step": 180
},
{
"epoch": 1.3021582733812949,
"grad_norm": 0.04245171695947647,
"learning_rate": 0.0001763943089655275,
"loss": 0.79150390625,
"step": 181
},
{
"epoch": 1.3093525179856116,
"grad_norm": 0.049361031502485275,
"learning_rate": 0.00017611037860449554,
"loss": 0.8642578125,
"step": 182
},
{
"epoch": 1.316546762589928,
"grad_norm": 0.04114909470081329,
"learning_rate": 0.00017582501193139273,
"loss": 0.85302734375,
"step": 183
},
{
"epoch": 1.3237410071942446,
"grad_norm": 0.04921070486307144,
"learning_rate": 0.00017553821514608667,
"loss": 0.826171875,
"step": 184
},
{
"epoch": 1.330935251798561,
"grad_norm": 0.0450618639588356,
"learning_rate": 0.00017524999447951557,
"loss": 0.8720703125,
"step": 185
},
{
"epoch": 1.3381294964028778,
"grad_norm": 0.039828523993492126,
"learning_rate": 0.00017496035619355292,
"loss": 0.88720703125,
"step": 186
},
{
"epoch": 1.3453237410071943,
"grad_norm": 0.04081854596734047,
"learning_rate": 0.0001746693065808712,
"loss": 0.7451171875,
"step": 187
},
{
"epoch": 1.3525179856115108,
"grad_norm": 0.042921580374240875,
"learning_rate": 0.00017437685196480547,
"loss": 0.83984375,
"step": 188
},
{
"epoch": 1.3597122302158273,
"grad_norm": 0.04440734535455704,
"learning_rate": 0.0001740829986992158,
"loss": 0.833984375,
"step": 189
},
{
"epoch": 1.3669064748201438,
"grad_norm": 0.043637990951538086,
"learning_rate": 0.0001737877531683493,
"loss": 0.84326171875,
"step": 190
},
{
"epoch": 1.3741007194244603,
"grad_norm": 0.03986284136772156,
"learning_rate": 0.00017349112178670137,
"loss": 0.86474609375,
"step": 191
},
{
"epoch": 1.381294964028777,
"grad_norm": 0.03892815113067627,
"learning_rate": 0.00017319311099887633,
"loss": 0.77734375,
"step": 192
},
{
"epoch": 1.3884892086330936,
"grad_norm": 0.04087143391370773,
"learning_rate": 0.00017289372727944755,
"loss": 0.7490234375,
"step": 193
},
{
"epoch": 1.39568345323741,
"grad_norm": 0.04417184740304947,
"learning_rate": 0.00017259297713281653,
"loss": 0.85791015625,
"step": 194
},
{
"epoch": 1.4028776978417266,
"grad_norm": 0.03808034956455231,
"learning_rate": 0.0001722908670930718,
"loss": 0.7279052734375,
"step": 195
},
{
"epoch": 1.4100719424460433,
"grad_norm": 0.04262340068817139,
"learning_rate": 0.0001719874037238469,
"loss": 0.78955078125,
"step": 196
},
{
"epoch": 1.4172661870503598,
"grad_norm": 0.03965727612376213,
"learning_rate": 0.0001716825936181777,
"loss": 0.8232421875,
"step": 197
},
{
"epoch": 1.4244604316546763,
"grad_norm": 0.047112174332141876,
"learning_rate": 0.0001713764433983593,
"loss": 0.892578125,
"step": 198
},
{
"epoch": 1.4316546762589928,
"grad_norm": 0.042808737605810165,
"learning_rate": 0.0001710689597158021,
"loss": 0.82275390625,
"step": 199
},
{
"epoch": 1.4388489208633093,
"grad_norm": 0.04719812050461769,
"learning_rate": 0.0001707601492508871,
"loss": 0.88818359375,
"step": 200
},
{
"epoch": 1.4460431654676258,
"grad_norm": 0.03830802068114281,
"learning_rate": 0.00017045001871282116,
"loss": 0.83251953125,
"step": 201
},
{
"epoch": 1.4532374100719425,
"grad_norm": 0.0516834519803524,
"learning_rate": 0.0001701385748394908,
"loss": 0.8544921875,
"step": 202
},
{
"epoch": 1.460431654676259,
"grad_norm": 0.04382869973778725,
"learning_rate": 0.0001698258243973162,
"loss": 0.833984375,
"step": 203
},
{
"epoch": 1.4676258992805755,
"grad_norm": 0.05187080800533295,
"learning_rate": 0.0001695117741811039,
"loss": 0.837890625,
"step": 204
},
{
"epoch": 1.474820143884892,
"grad_norm": 0.04502135515213013,
"learning_rate": 0.0001691964310138993,
"loss": 0.837890625,
"step": 205
},
{
"epoch": 1.4820143884892087,
"grad_norm": 0.043519362807273865,
"learning_rate": 0.00016887980174683852,
"loss": 0.70849609375,
"step": 206
},
{
"epoch": 1.4892086330935252,
"grad_norm": 0.05780479311943054,
"learning_rate": 0.00016856189325899928,
"loss": 0.8955078125,
"step": 207
},
{
"epoch": 1.4964028776978417,
"grad_norm": 0.042303670197725296,
"learning_rate": 0.00016824271245725176,
"loss": 0.85693359375,
"step": 208
},
{
"epoch": 1.5035971223021583,
"grad_norm": 0.0463891327381134,
"learning_rate": 0.00016792226627610832,
"loss": 0.79345703125,
"step": 209
},
{
"epoch": 1.5107913669064748,
"grad_norm": 0.0468367375433445,
"learning_rate": 0.00016760056167757287,
"loss": 0.8291015625,
"step": 210
},
{
"epoch": 1.5179856115107913,
"grad_norm": 0.03986787796020508,
"learning_rate": 0.0001672776056509898,
"loss": 0.7135009765625,
"step": 211
},
{
"epoch": 1.5251798561151078,
"grad_norm": 0.0501888170838356,
"learning_rate": 0.00016695340521289187,
"loss": 0.84619140625,
"step": 212
},
{
"epoch": 1.5323741007194245,
"grad_norm": 0.037934284657239914,
"learning_rate": 0.00016662796740684788,
"loss": 0.8486328125,
"step": 213
},
{
"epoch": 1.539568345323741,
"grad_norm": 0.04309995472431183,
"learning_rate": 0.00016630129930330972,
"loss": 0.85302734375,
"step": 214
},
{
"epoch": 1.5467625899280577,
"grad_norm": 0.044207021594047546,
"learning_rate": 0.00016597340799945863,
"loss": 0.84375,
"step": 215
},
{
"epoch": 1.5539568345323742,
"grad_norm": 0.0449429452419281,
"learning_rate": 0.00016564430061905117,
"loss": 0.80810546875,
"step": 216
},
{
"epoch": 1.5611510791366907,
"grad_norm": 0.04132893308997154,
"learning_rate": 0.00016531398431226415,
"loss": 0.79248046875,
"step": 217
},
{
"epoch": 1.5683453237410072,
"grad_norm": 0.04205712303519249,
"learning_rate": 0.00016498246625553964,
"loss": 0.79736328125,
"step": 218
},
{
"epoch": 1.5755395683453237,
"grad_norm": 0.04375145211815834,
"learning_rate": 0.00016464975365142878,
"loss": 0.830078125,
"step": 219
},
{
"epoch": 1.5827338129496402,
"grad_norm": 0.04119812697172165,
"learning_rate": 0.00016431585372843558,
"loss": 0.818359375,
"step": 220
},
{
"epoch": 1.5899280575539567,
"grad_norm": 0.03909582644701004,
"learning_rate": 0.00016398077374085948,
"loss": 0.81396484375,
"step": 221
},
{
"epoch": 1.5971223021582732,
"grad_norm": 0.0427253432571888,
"learning_rate": 0.00016364452096863814,
"loss": 0.8798828125,
"step": 222
},
{
"epoch": 1.60431654676259,
"grad_norm": 0.042284633964300156,
"learning_rate": 0.000163307102717189,
"loss": 0.837890625,
"step": 223
},
{
"epoch": 1.6115107913669064,
"grad_norm": 0.040377307683229446,
"learning_rate": 0.00016296852631725073,
"loss": 0.77490234375,
"step": 224
},
{
"epoch": 1.6187050359712232,
"grad_norm": 0.03904381021857262,
"learning_rate": 0.0001626287991247239,
"loss": 0.755767822265625,
"step": 225
},
{
"epoch": 1.6258992805755397,
"grad_norm": 0.03976181894540787,
"learning_rate": 0.0001622879285205111,
"loss": 0.8642578125,
"step": 226
},
{
"epoch": 1.6330935251798562,
"grad_norm": 0.042343683540821075,
"learning_rate": 0.00016194592191035677,
"loss": 0.87158203125,
"step": 227
},
{
"epoch": 1.6402877697841727,
"grad_norm": 0.04713711887598038,
"learning_rate": 0.00016160278672468597,
"loss": 0.82080078125,
"step": 228
},
{
"epoch": 1.6474820143884892,
"grad_norm": 0.04185783118009567,
"learning_rate": 0.00016125853041844341,
"loss": 0.87353515625,
"step": 229
},
{
"epoch": 1.6546762589928057,
"grad_norm": 0.04794565215706825,
"learning_rate": 0.000160913160470931,
"loss": 0.830078125,
"step": 230
},
{
"epoch": 1.6618705035971222,
"grad_norm": 0.0415600910782814,
"learning_rate": 0.00016056668438564582,
"loss": 0.8564453125,
"step": 231
},
{
"epoch": 1.6690647482014387,
"grad_norm": 0.04833108186721802,
"learning_rate": 0.00016021910969011663,
"loss": 0.849609375,
"step": 232
},
{
"epoch": 1.6762589928057554,
"grad_norm": 0.04575372114777565,
"learning_rate": 0.0001598704439357407,
"loss": 0.81298828125,
"step": 233
},
{
"epoch": 1.683453237410072,
"grad_norm": 0.03934381157159805,
"learning_rate": 0.00015952069469761962,
"loss": 0.72552490234375,
"step": 234
},
{
"epoch": 1.6906474820143886,
"grad_norm": 0.049587901681661606,
"learning_rate": 0.00015916986957439466,
"loss": 0.84130859375,
"step": 235
},
{
"epoch": 1.6978417266187051,
"grad_norm": 0.04220333695411682,
"learning_rate": 0.0001588179761880817,
"loss": 0.8076171875,
"step": 236
},
{
"epoch": 1.7050359712230216,
"grad_norm": 0.04653998836874962,
"learning_rate": 0.00015846502218390586,
"loss": 0.85546875,
"step": 237
},
{
"epoch": 1.7122302158273381,
"grad_norm": 0.03816188871860504,
"learning_rate": 0.00015811101523013497,
"loss": 0.7503662109375,
"step": 238
},
{
"epoch": 1.7194244604316546,
"grad_norm": 0.04767630994319916,
"learning_rate": 0.00015775596301791333,
"loss": 0.85888671875,
"step": 239
},
{
"epoch": 1.7266187050359711,
"grad_norm": 0.04678802192211151,
"learning_rate": 0.0001573998732610945,
"loss": 0.76953125,
"step": 240
},
{
"epoch": 1.7338129496402876,
"grad_norm": 0.046845078468322754,
"learning_rate": 0.0001570427536960737,
"loss": 0.8388671875,
"step": 241
},
{
"epoch": 1.7410071942446042,
"grad_norm": 0.043635401874780655,
"learning_rate": 0.00015668461208161972,
"loss": 0.77734375,
"step": 242
},
{
"epoch": 1.7482014388489209,
"grad_norm": 0.04362385720014572,
"learning_rate": 0.0001563254561987063,
"loss": 0.84912109375,
"step": 243
},
{
"epoch": 1.7553956834532374,
"grad_norm": 0.044553980231285095,
"learning_rate": 0.0001559652938503433,
"loss": 0.79345703125,
"step": 244
},
{
"epoch": 1.762589928057554,
"grad_norm": 0.04406202211976051,
"learning_rate": 0.00015560413286140685,
"loss": 0.7530517578125,
"step": 245
},
{
"epoch": 1.7697841726618706,
"grad_norm": 0.04341139644384384,
"learning_rate": 0.0001552419810784696,
"loss": 0.853515625,
"step": 246
},
{
"epoch": 1.776978417266187,
"grad_norm": 0.045188918709754944,
"learning_rate": 0.0001548788463696302,
"loss": 0.85400390625,
"step": 247
},
{
"epoch": 1.7841726618705036,
"grad_norm": 0.04505106061697006,
"learning_rate": 0.0001545147366243422,
"loss": 0.85595703125,
"step": 248
},
{
"epoch": 1.79136690647482,
"grad_norm": 0.04506320506334305,
"learning_rate": 0.0001541496597532429,
"loss": 0.833984375,
"step": 249
},
{
"epoch": 1.7985611510791366,
"grad_norm": 0.04548605903983116,
"learning_rate": 0.0001537836236879812,
"loss": 0.791015625,
"step": 250
},
{
"epoch": 1.8057553956834531,
"grad_norm": 0.04316633567214012,
"learning_rate": 0.00015341663638104554,
"loss": 0.81982421875,
"step": 251
},
{
"epoch": 1.8129496402877698,
"grad_norm": 0.04278340935707092,
"learning_rate": 0.00015304870580559098,
"loss": 0.853515625,
"step": 252
},
{
"epoch": 1.8201438848920863,
"grad_norm": 0.04189430922269821,
"learning_rate": 0.00015267983995526598,
"loss": 0.8193359375,
"step": 253
},
{
"epoch": 1.8273381294964028,
"grad_norm": 0.043314654380083084,
"learning_rate": 0.00015231004684403875,
"loss": 0.80029296875,
"step": 254
},
{
"epoch": 1.8345323741007196,
"grad_norm": 0.04589797183871269,
"learning_rate": 0.0001519393345060232,
"loss": 0.8720703125,
"step": 255
},
{
"epoch": 1.841726618705036,
"grad_norm": 0.04632316529750824,
"learning_rate": 0.00015156771099530418,
"loss": 0.85986328125,
"step": 256
},
{
"epoch": 1.8489208633093526,
"grad_norm": 0.04235149547457695,
"learning_rate": 0.0001511951843857629,
"loss": 0.72198486328125,
"step": 257
},
{
"epoch": 1.856115107913669,
"grad_norm": 0.045621540397405624,
"learning_rate": 0.00015082176277090098,
"loss": 0.724365234375,
"step": 258
},
{
"epoch": 1.8633093525179856,
"grad_norm": 0.04848325625061989,
"learning_rate": 0.00015044745426366518,
"loss": 0.7958984375,
"step": 259
},
{
"epoch": 1.870503597122302,
"grad_norm": 0.045993320643901825,
"learning_rate": 0.00015007226699627064,
"loss": 0.81396484375,
"step": 260
},
{
"epoch": 1.8776978417266186,
"grad_norm": 0.045716602355241776,
"learning_rate": 0.00014969620912002454,
"loss": 0.822265625,
"step": 261
},
{
"epoch": 1.8848920863309353,
"grad_norm": 0.04895888641476631,
"learning_rate": 0.0001493192888051488,
"loss": 0.80908203125,
"step": 262
},
{
"epoch": 1.8920863309352518,
"grad_norm": 0.04477611929178238,
"learning_rate": 0.0001489415142406027,
"loss": 0.849609375,
"step": 263
},
{
"epoch": 1.8992805755395683,
"grad_norm": 0.04289644956588745,
"learning_rate": 0.00014856289363390494,
"loss": 0.841796875,
"step": 264
},
{
"epoch": 1.906474820143885,
"grad_norm": 0.044229451566934586,
"learning_rate": 0.0001481834352109553,
"loss": 0.7408447265625,
"step": 265
},
{
"epoch": 1.9136690647482015,
"grad_norm": 0.03946951776742935,
"learning_rate": 0.0001478031472158559,
"loss": 0.666107177734375,
"step": 266
},
{
"epoch": 1.920863309352518,
"grad_norm": 0.04310256987810135,
"learning_rate": 0.0001474220379107321,
"loss": 0.78857421875,
"step": 267
},
{
"epoch": 1.9280575539568345,
"grad_norm": 0.04882989078760147,
"learning_rate": 0.000147040115575553,
"loss": 0.79248046875,
"step": 268
},
{
"epoch": 1.935251798561151,
"grad_norm": 0.04746069014072418,
"learning_rate": 0.00014665738850795176,
"loss": 0.80029296875,
"step": 269
},
{
"epoch": 1.9424460431654675,
"grad_norm": 0.041401710361242294,
"learning_rate": 0.00014627386502304493,
"loss": 0.76806640625,
"step": 270
},
{
"epoch": 1.949640287769784,
"grad_norm": 0.05159782990813255,
"learning_rate": 0.00014588955345325196,
"loss": 0.78857421875,
"step": 271
},
{
"epoch": 1.9568345323741008,
"grad_norm": 0.04928658902645111,
"learning_rate": 0.00014550446214811445,
"loss": 0.78515625,
"step": 272
},
{
"epoch": 1.9640287769784173,
"grad_norm": 0.043647099286317825,
"learning_rate": 0.00014511859947411427,
"loss": 0.7822265625,
"step": 273
},
{
"epoch": 1.9712230215827338,
"grad_norm": 0.04335784912109375,
"learning_rate": 0.00014473197381449212,
"loss": 0.80810546875,
"step": 274
},
{
"epoch": 1.9784172661870505,
"grad_norm": 0.04860594868659973,
"learning_rate": 0.0001443445935690653,
"loss": 0.85400390625,
"step": 275
},
{
"epoch": 1.985611510791367,
"grad_norm": 0.041789427399635315,
"learning_rate": 0.00014395646715404525,
"loss": 0.8251953125,
"step": 276
},
{
"epoch": 1.9928057553956835,
"grad_norm": 0.05233513563871384,
"learning_rate": 0.0001435676030018546,
"loss": 0.82861328125,
"step": 277
},
{
"epoch": 2.0,
"grad_norm": 0.04310717433691025,
"learning_rate": 0.00014317800956094415,
"loss": 0.69140625,
"step": 278
},
{
"epoch": 2.0,
"eval_loss": 0.828369140625,
"eval_runtime": 2.1901,
"eval_samples_per_second": 3.196,
"eval_steps_per_second": 0.457,
"step": 278
},
{
"epoch": 2.0071942446043165,
"grad_norm": 0.04650307819247246,
"learning_rate": 0.000142787695295609,
"loss": 0.794921875,
"step": 279
},
{
"epoch": 2.014388489208633,
"grad_norm": 0.04894444718956947,
"learning_rate": 0.0001423966686858051,
"loss": 0.81298828125,
"step": 280
},
{
"epoch": 2.0215827338129495,
"grad_norm": 0.05060400068759918,
"learning_rate": 0.00014200493822696454,
"loss": 0.8193359375,
"step": 281
},
{
"epoch": 2.028776978417266,
"grad_norm": 0.046522483229637146,
"learning_rate": 0.00014161251242981142,
"loss": 0.78564453125,
"step": 282
},
{
"epoch": 2.0359712230215825,
"grad_norm": 0.048828475177288055,
"learning_rate": 0.00014121939982017666,
"loss": 0.83447265625,
"step": 283
},
{
"epoch": 2.0431654676258995,
"grad_norm": 0.04334365949034691,
"learning_rate": 0.00014082560893881275,
"loss": 0.83056640625,
"step": 284
},
{
"epoch": 2.050359712230216,
"grad_norm": 0.04892473295331001,
"learning_rate": 0.00014043114834120846,
"loss": 0.87060546875,
"step": 285
},
{
"epoch": 2.0575539568345325,
"grad_norm": 0.0465744249522686,
"learning_rate": 0.00014003602659740268,
"loss": 0.8603515625,
"step": 286
},
{
"epoch": 2.064748201438849,
"grad_norm": 0.04991191625595093,
"learning_rate": 0.00013964025229179836,
"loss": 0.8515625,
"step": 287
},
{
"epoch": 2.0719424460431655,
"grad_norm": 0.047747328877449036,
"learning_rate": 0.00013924383402297603,
"loss": 0.8427734375,
"step": 288
},
{
"epoch": 2.079136690647482,
"grad_norm": 0.04737791419029236,
"learning_rate": 0.0001388467804035069,
"loss": 0.7705078125,
"step": 289
},
{
"epoch": 2.0863309352517985,
"grad_norm": 0.043898820877075195,
"learning_rate": 0.0001384491000597658,
"loss": 0.86328125,
"step": 290
},
{
"epoch": 2.093525179856115,
"grad_norm": 0.04313091188669205,
"learning_rate": 0.0001380508016317438,
"loss": 0.657562255859375,
"step": 291
},
{
"epoch": 2.1007194244604315,
"grad_norm": 0.050117526203393936,
"learning_rate": 0.00013765189377286038,
"loss": 0.81103515625,
"step": 292
},
{
"epoch": 2.1079136690647484,
"grad_norm": 0.0447276309132576,
"learning_rate": 0.00013725238514977552,
"loss": 0.791015625,
"step": 293
},
{
"epoch": 2.115107913669065,
"grad_norm": 0.04554459825158119,
"learning_rate": 0.00013685228444220142,
"loss": 0.83251953125,
"step": 294
},
{
"epoch": 2.1223021582733814,
"grad_norm": 0.04546786844730377,
"learning_rate": 0.0001364516003427138,
"loss": 0.7822265625,
"step": 295
},
{
"epoch": 2.129496402877698,
"grad_norm": 0.04588071629405022,
"learning_rate": 0.00013605034155656325,
"loss": 0.7685546875,
"step": 296
},
{
"epoch": 2.1366906474820144,
"grad_norm": 0.05129684880375862,
"learning_rate": 0.00013564851680148592,
"loss": 0.77783203125,
"step": 297
},
{
"epoch": 2.143884892086331,
"grad_norm": 0.045612990856170654,
"learning_rate": 0.0001352461348075142,
"loss": 0.74853515625,
"step": 298
},
{
"epoch": 2.1510791366906474,
"grad_norm": 0.04462664946913719,
"learning_rate": 0.00013484320431678698,
"loss": 0.8388671875,
"step": 299
},
{
"epoch": 2.158273381294964,
"grad_norm": 0.045990847051143646,
"learning_rate": 0.00013443973408335989,
"loss": 0.80908203125,
"step": 300
},
{
"epoch": 2.1654676258992804,
"grad_norm": 0.0487491674721241,
"learning_rate": 0.00013403573287301487,
"loss": 0.78125,
"step": 301
},
{
"epoch": 2.172661870503597,
"grad_norm": 0.04534728825092316,
"learning_rate": 0.0001336312094630699,
"loss": 0.8203125,
"step": 302
},
{
"epoch": 2.1798561151079134,
"grad_norm": 0.049283768981695175,
"learning_rate": 0.00013322617264218835,
"loss": 0.77734375,
"step": 303
},
{
"epoch": 2.1870503597122304,
"grad_norm": 0.050884950906038284,
"learning_rate": 0.00013282063121018776,
"loss": 0.7919921875,
"step": 304
},
{
"epoch": 2.194244604316547,
"grad_norm": 0.04702775552868843,
"learning_rate": 0.0001324145939778489,
"loss": 0.78564453125,
"step": 305
},
{
"epoch": 2.2014388489208634,
"grad_norm": 0.052253250032663345,
"learning_rate": 0.0001320080697667244,
"loss": 0.787109375,
"step": 306
},
{
"epoch": 2.20863309352518,
"grad_norm": 0.04377969354391098,
"learning_rate": 0.00013160106740894682,
"loss": 0.86279296875,
"step": 307
},
{
"epoch": 2.2158273381294964,
"grad_norm": 0.04678820073604584,
"learning_rate": 0.00013119359574703698,
"loss": 0.81396484375,
"step": 308
},
{
"epoch": 2.223021582733813,
"grad_norm": 0.052830882370471954,
"learning_rate": 0.00013078566363371183,
"loss": 0.84326171875,
"step": 309
},
{
"epoch": 2.2302158273381294,
"grad_norm": 0.045458320528268814,
"learning_rate": 0.00013037727993169196,
"loss": 0.8017578125,
"step": 310
},
{
"epoch": 2.237410071942446,
"grad_norm": 0.04562614858150482,
"learning_rate": 0.00012996845351350933,
"loss": 0.82373046875,
"step": 311
},
{
"epoch": 2.2446043165467624,
"grad_norm": 0.04541024938225746,
"learning_rate": 0.0001295591932613142,
"loss": 0.7373046875,
"step": 312
},
{
"epoch": 2.2517985611510793,
"grad_norm": 0.049970611929893494,
"learning_rate": 0.0001291495080666823,
"loss": 0.828125,
"step": 313
},
{
"epoch": 2.258992805755396,
"grad_norm": 0.04790482297539711,
"learning_rate": 0.00012873940683042167,
"loss": 0.8408203125,
"step": 314
},
{
"epoch": 2.2661870503597124,
"grad_norm": 0.05039989575743675,
"learning_rate": 0.00012832889846237937,
"loss": 0.7978515625,
"step": 315
},
{
"epoch": 2.273381294964029,
"grad_norm": 0.04586273804306984,
"learning_rate": 0.00012791799188124764,
"loss": 0.84912109375,
"step": 316
},
{
"epoch": 2.2805755395683454,
"grad_norm": 0.049588415771722794,
"learning_rate": 0.00012750669601437035,
"loss": 0.82080078125,
"step": 317
},
{
"epoch": 2.287769784172662,
"grad_norm": 0.051667772233486176,
"learning_rate": 0.00012709501979754894,
"loss": 0.78173828125,
"step": 318
},
{
"epoch": 2.2949640287769784,
"grad_norm": 0.04927917197346687,
"learning_rate": 0.0001266829721748484,
"loss": 0.83984375,
"step": 319
},
{
"epoch": 2.302158273381295,
"grad_norm": 0.04481778293848038,
"learning_rate": 0.00012627056209840276,
"loss": 0.7431640625,
"step": 320
},
{
"epoch": 2.3093525179856114,
"grad_norm": 0.05266236886382103,
"learning_rate": 0.0001258577985282208,
"loss": 0.81103515625,
"step": 321
},
{
"epoch": 2.316546762589928,
"grad_norm": 0.04762723296880722,
"learning_rate": 0.00012544469043199128,
"loss": 0.802734375,
"step": 322
},
{
"epoch": 2.3237410071942444,
"grad_norm": 0.048896774649620056,
"learning_rate": 0.00012503124678488813,
"loss": 0.775390625,
"step": 323
},
{
"epoch": 2.3309352517985613,
"grad_norm": 0.05462624877691269,
"learning_rate": 0.0001246174765693754,
"loss": 0.81884765625,
"step": 324
},
{
"epoch": 2.338129496402878,
"grad_norm": 0.04576321318745613,
"learning_rate": 0.00012420338877501213,
"loss": 0.83984375,
"step": 325
},
{
"epoch": 2.3453237410071943,
"grad_norm": 0.04447055235505104,
"learning_rate": 0.00012378899239825724,
"loss": 0.69873046875,
"step": 326
},
{
"epoch": 2.352517985611511,
"grad_norm": 0.052814848721027374,
"learning_rate": 0.00012337429644227368,
"loss": 0.791015625,
"step": 327
},
{
"epoch": 2.3597122302158273,
"grad_norm": 0.04949796572327614,
"learning_rate": 0.00012295930991673319,
"loss": 0.7822265625,
"step": 328
},
{
"epoch": 2.366906474820144,
"grad_norm": 0.04833221808075905,
"learning_rate": 0.0001225440418376204,
"loss": 0.78955078125,
"step": 329
},
{
"epoch": 2.3741007194244603,
"grad_norm": 0.05010189116001129,
"learning_rate": 0.0001221285012270369,
"loss": 0.81494140625,
"step": 330
},
{
"epoch": 2.381294964028777,
"grad_norm": 0.046608082950115204,
"learning_rate": 0.00012171269711300534,
"loss": 0.73388671875,
"step": 331
},
{
"epoch": 2.3884892086330938,
"grad_norm": 0.04613162577152252,
"learning_rate": 0.00012129663852927329,
"loss": 0.706298828125,
"step": 332
},
{
"epoch": 2.3956834532374103,
"grad_norm": 0.045513078570365906,
"learning_rate": 0.00012088033451511676,
"loss": 0.8076171875,
"step": 333
},
{
"epoch": 2.402877697841727,
"grad_norm": 0.04832140728831291,
"learning_rate": 0.00012046379411514417,
"loss": 0.6844482421875,
"step": 334
},
{
"epoch": 2.4100719424460433,
"grad_norm": 0.050110142678022385,
"learning_rate": 0.0001200470263790995,
"loss": 0.73974609375,
"step": 335
},
{
"epoch": 2.41726618705036,
"grad_norm": 0.04606263339519501,
"learning_rate": 0.00011963004036166589,
"loss": 0.77392578125,
"step": 336
},
{
"epoch": 2.4244604316546763,
"grad_norm": 0.045919839292764664,
"learning_rate": 0.00011921284512226885,
"loss": 0.84375,
"step": 337
},
{
"epoch": 2.431654676258993,
"grad_norm": 0.052308060228824615,
"learning_rate": 0.00011879544972487946,
"loss": 0.7744140625,
"step": 338
},
{
"epoch": 2.4388489208633093,
"grad_norm": 0.05035803094506264,
"learning_rate": 0.00011837786323781735,
"loss": 0.84130859375,
"step": 339
},
{
"epoch": 2.446043165467626,
"grad_norm": 0.045004814863204956,
"learning_rate": 0.00011796009473355385,
"loss": 0.7841796875,
"step": 340
},
{
"epoch": 2.4532374100719423,
"grad_norm": 0.04761987552046776,
"learning_rate": 0.00011754215328851474,
"loss": 0.802734375,
"step": 341
},
{
"epoch": 2.460431654676259,
"grad_norm": 0.051020294427871704,
"learning_rate": 0.00011712404798288314,
"loss": 0.78564453125,
"step": 342
},
{
"epoch": 2.4676258992805753,
"grad_norm": 0.050860606133937836,
"learning_rate": 0.00011670578790040219,
"loss": 0.78564453125,
"step": 343
},
{
"epoch": 2.4748201438848922,
"grad_norm": 0.046935468912124634,
"learning_rate": 0.00011628738212817765,
"loss": 0.79052734375,
"step": 344
},
{
"epoch": 2.4820143884892087,
"grad_norm": 0.04854678362607956,
"learning_rate": 0.00011586883975648059,
"loss": 0.6683349609375,
"step": 345
},
{
"epoch": 2.4892086330935252,
"grad_norm": 0.044234853237867355,
"learning_rate": 0.00011545016987854984,
"loss": 0.8447265625,
"step": 346
},
{
"epoch": 2.4964028776978417,
"grad_norm": 0.04752020537853241,
"learning_rate": 0.00011503138159039442,
"loss": 0.80859375,
"step": 347
},
{
"epoch": 2.5035971223021583,
"grad_norm": 0.05051235109567642,
"learning_rate": 0.00011461248399059587,
"loss": 0.744140625,
"step": 348
},
{
"epoch": 2.5107913669064748,
"grad_norm": 0.04833044856786728,
"learning_rate": 0.00011419348618011072,
"loss": 0.77783203125,
"step": 349
},
{
"epoch": 2.5179856115107913,
"grad_norm": 0.04062685742974281,
"learning_rate": 0.0001137743972620726,
"loss": 0.67205810546875,
"step": 350
},
{
"epoch": 2.5251798561151078,
"grad_norm": 0.05535674840211868,
"learning_rate": 0.00011335522634159458,
"loss": 0.796875,
"step": 351
},
{
"epoch": 2.5323741007194247,
"grad_norm": 0.04851287230849266,
"learning_rate": 0.00011293598252557133,
"loss": 0.80224609375,
"step": 352
},
{
"epoch": 2.539568345323741,
"grad_norm": 0.05390458181500435,
"learning_rate": 0.00011251667492248119,
"loss": 0.80712890625,
"step": 353
},
{
"epoch": 2.5467625899280577,
"grad_norm": 0.0485994890332222,
"learning_rate": 0.00011209731264218839,
"loss": 0.79345703125,
"step": 354
},
{
"epoch": 2.553956834532374,
"grad_norm": 0.049317073076963425,
"learning_rate": 0.00011167790479574502,
"loss": 0.75830078125,
"step": 355
},
{
"epoch": 2.5611510791366907,
"grad_norm": 0.0525440014898777,
"learning_rate": 0.00011125846049519322,
"loss": 0.74755859375,
"step": 356
},
{
"epoch": 2.568345323741007,
"grad_norm": 0.04876266419887543,
"learning_rate": 0.00011083898885336703,
"loss": 0.751953125,
"step": 357
},
{
"epoch": 2.5755395683453237,
"grad_norm": 0.052858300507068634,
"learning_rate": 0.00011041949898369459,
"loss": 0.783203125,
"step": 358
},
{
"epoch": 2.58273381294964,
"grad_norm": 0.05262572690844536,
"learning_rate": 0.00011000000000000002,
"loss": 0.77099609375,
"step": 359
},
{
"epoch": 2.5899280575539567,
"grad_norm": 0.047345709055662155,
"learning_rate": 0.00010958050101630543,
"loss": 0.76904296875,
"step": 360
},
{
"epoch": 2.597122302158273,
"grad_norm": 0.05140183866024017,
"learning_rate": 0.000109161011146633,
"loss": 0.83154296875,
"step": 361
},
{
"epoch": 2.6043165467625897,
"grad_norm": 0.05102568864822388,
"learning_rate": 0.00010874153950480682,
"loss": 0.79248046875,
"step": 362
},
{
"epoch": 2.6115107913669062,
"grad_norm": 0.045782215893268585,
"learning_rate": 0.000108322095204255,
"loss": 0.7314453125,
"step": 363
},
{
"epoch": 2.618705035971223,
"grad_norm": 0.050807852298021317,
"learning_rate": 0.00010790268735781164,
"loss": 0.71722412109375,
"step": 364
},
{
"epoch": 2.6258992805755397,
"grad_norm": 0.051522769033908844,
"learning_rate": 0.00010748332507751883,
"loss": 0.818359375,
"step": 365
},
{
"epoch": 2.633093525179856,
"grad_norm": 0.04913736507296562,
"learning_rate": 0.00010706401747442871,
"loss": 0.82373046875,
"step": 366
},
{
"epoch": 2.6402877697841727,
"grad_norm": 0.05782147869467735,
"learning_rate": 0.00010664477365840544,
"loss": 0.771484375,
"step": 367
},
{
"epoch": 2.647482014388489,
"grad_norm": 0.04873919114470482,
"learning_rate": 0.00010622560273792743,
"loss": 0.828125,
"step": 368
},
{
"epoch": 2.6546762589928057,
"grad_norm": 0.05088592693209648,
"learning_rate": 0.00010580651381988933,
"loss": 0.784912109375,
"step": 369
},
{
"epoch": 2.661870503597122,
"grad_norm": 0.05531268194317818,
"learning_rate": 0.00010538751600940415,
"loss": 0.81201171875,
"step": 370
},
{
"epoch": 2.6690647482014387,
"grad_norm": 0.05034675449132919,
"learning_rate": 0.00010496861840960563,
"loss": 0.80126953125,
"step": 371
},
{
"epoch": 2.6762589928057556,
"grad_norm": 0.05312187969684601,
"learning_rate": 0.00010454983012145017,
"loss": 0.76806640625,
"step": 372
},
{
"epoch": 2.683453237410072,
"grad_norm": 0.047288570553064346,
"learning_rate": 0.0001041311602435194,
"loss": 0.684967041015625,
"step": 373
},
{
"epoch": 2.6906474820143886,
"grad_norm": 0.2075473666191101,
"learning_rate": 0.00010371261787182236,
"loss": 0.79541015625,
"step": 374
},
{
"epoch": 2.697841726618705,
"grad_norm": 0.05510100722312927,
"learning_rate": 0.00010329421209959782,
"loss": 0.76611328125,
"step": 375
},
{
"epoch": 2.7050359712230216,
"grad_norm": 0.05734541639685631,
"learning_rate": 0.00010287595201711687,
"loss": 0.81201171875,
"step": 376
},
{
"epoch": 2.712230215827338,
"grad_norm": 0.04358500987291336,
"learning_rate": 0.00010245784671148527,
"loss": 0.7137451171875,
"step": 377
},
{
"epoch": 2.7194244604316546,
"grad_norm": 0.06229035183787346,
"learning_rate": 0.00010203990526644616,
"loss": 0.81787109375,
"step": 378
},
{
"epoch": 2.726618705035971,
"grad_norm": 0.05049343407154083,
"learning_rate": 0.00010162213676218268,
"loss": 0.728515625,
"step": 379
},
{
"epoch": 2.7338129496402876,
"grad_norm": 0.04830893874168396,
"learning_rate": 0.0001012045502751206,
"loss": 0.79638671875,
"step": 380
},
{
"epoch": 2.741007194244604,
"grad_norm": 0.05644870549440384,
"learning_rate": 0.00010078715487773119,
"loss": 0.734375,
"step": 381
},
{
"epoch": 2.7482014388489207,
"grad_norm": 0.05439073592424393,
"learning_rate": 0.00010036995963833413,
"loss": 0.80517578125,
"step": 382
},
{
"epoch": 2.755395683453237,
"grad_norm": 0.045659180730581284,
"learning_rate": 9.995297362090053e-05,
"loss": 0.750244140625,
"step": 383
},
{
"epoch": 2.762589928057554,
"grad_norm": 0.04973863810300827,
"learning_rate": 9.953620588485584e-05,
"loss": 0.7125244140625,
"step": 384
},
{
"epoch": 2.7697841726618706,
"grad_norm": 0.052991315722465515,
"learning_rate": 9.911966548488325e-05,
"loss": 0.80859375,
"step": 385
},
{
"epoch": 2.776978417266187,
"grad_norm": 0.04987526684999466,
"learning_rate": 9.870336147072674e-05,
"loss": 0.810546875,
"step": 386
},
{
"epoch": 2.7841726618705036,
"grad_norm": 0.0535612478852272,
"learning_rate": 9.828730288699466e-05,
"loss": 0.81103515625,
"step": 387
},
{
"epoch": 2.79136690647482,
"grad_norm": 0.05203310772776604,
"learning_rate": 9.787149877296313e-05,
"loss": 0.78857421875,
"step": 388
},
{
"epoch": 2.7985611510791366,
"grad_norm": 0.050753235816955566,
"learning_rate": 9.745595816237965e-05,
"loss": 0.74755859375,
"step": 389
},
{
"epoch": 2.805755395683453,
"grad_norm": 0.04751288890838623,
"learning_rate": 9.704069008326682e-05,
"loss": 0.77587890625,
"step": 390
},
{
"epoch": 2.81294964028777,
"grad_norm": 0.049112122505903244,
"learning_rate": 9.662570355772635e-05,
"loss": 0.81005859375,
"step": 391
},
{
"epoch": 2.8201438848920866,
"grad_norm": 0.053297240287065506,
"learning_rate": 9.62110076017428e-05,
"loss": 0.779296875,
"step": 392
},
{
"epoch": 2.827338129496403,
"grad_norm": 0.05029544606804848,
"learning_rate": 9.579661122498789e-05,
"loss": 0.7578125,
"step": 393
},
{
"epoch": 2.8345323741007196,
"grad_norm": 0.054014552384614944,
"learning_rate": 9.538252343062467e-05,
"loss": 0.82861328125,
"step": 394
},
{
"epoch": 2.841726618705036,
"grad_norm": 0.05070069804787636,
"learning_rate": 9.496875321511192e-05,
"loss": 0.814453125,
"step": 395
},
{
"epoch": 2.8489208633093526,
"grad_norm": 0.050118040293455124,
"learning_rate": 9.455530956800874e-05,
"loss": 0.6856689453125,
"step": 396
},
{
"epoch": 2.856115107913669,
"grad_norm": 0.05564381182193756,
"learning_rate": 9.414220147177924e-05,
"loss": 0.684326171875,
"step": 397
},
{
"epoch": 2.8633093525179856,
"grad_norm": 0.05447627604007721,
"learning_rate": 9.372943790159728e-05,
"loss": 0.75390625,
"step": 398
},
{
"epoch": 2.870503597122302,
"grad_norm": 0.055909764021635056,
"learning_rate": 9.331702782515163e-05,
"loss": 0.77294921875,
"step": 399
},
{
"epoch": 2.8776978417266186,
"grad_norm": 0.0563516765832901,
"learning_rate": 9.290498020245107e-05,
"loss": 0.77880859375,
"step": 400
},
{
"epoch": 2.884892086330935,
"grad_norm": 0.053766004741191864,
"learning_rate": 9.249330398562967e-05,
"loss": 0.76611328125,
"step": 401
},
{
"epoch": 2.8920863309352516,
"grad_norm": 0.05877723917365074,
"learning_rate": 9.208200811875236e-05,
"loss": 0.80908203125,
"step": 402
},
{
"epoch": 2.899280575539568,
"grad_norm": 0.057588957250118256,
"learning_rate": 9.167110153762062e-05,
"loss": 0.802734375,
"step": 403
},
{
"epoch": 2.906474820143885,
"grad_norm": 0.0489775650203228,
"learning_rate": 9.126059316957833e-05,
"loss": 0.703369140625,
"step": 404
},
{
"epoch": 2.9136690647482015,
"grad_norm": 0.04787963256239891,
"learning_rate": 9.085049193331774e-05,
"loss": 0.6331939697265625,
"step": 405
},
{
"epoch": 2.920863309352518,
"grad_norm": 0.0641121044754982,
"learning_rate": 9.044080673868587e-05,
"loss": 0.75146484375,
"step": 406
},
{
"epoch": 2.9280575539568345,
"grad_norm": 0.05303160101175308,
"learning_rate": 9.003154648649071e-05,
"loss": 0.74853515625,
"step": 407
},
{
"epoch": 2.935251798561151,
"grad_norm": 0.06356843560934067,
"learning_rate": 8.962272006830806e-05,
"loss": 0.7587890625,
"step": 408
},
{
"epoch": 2.9424460431654675,
"grad_norm": 0.0638933926820755,
"learning_rate": 8.921433636628819e-05,
"loss": 0.73193359375,
"step": 409
},
{
"epoch": 2.949640287769784,
"grad_norm": 0.05463378503918648,
"learning_rate": 8.880640425296304e-05,
"loss": 0.7451171875,
"step": 410
},
{
"epoch": 2.956834532374101,
"grad_norm": 0.05607324466109276,
"learning_rate": 8.839893259105321e-05,
"loss": 0.74462890625,
"step": 411
},
{
"epoch": 2.9640287769784175,
"grad_norm": 0.05459370091557503,
"learning_rate": 8.799193023327563e-05,
"loss": 0.7431640625,
"step": 412
},
{
"epoch": 2.971223021582734,
"grad_norm": 0.05387922376394272,
"learning_rate": 8.75854060221511e-05,
"loss": 0.76318359375,
"step": 413
},
{
"epoch": 2.9784172661870505,
"grad_norm": 0.052306290715932846,
"learning_rate": 8.71793687898123e-05,
"loss": 0.8154296875,
"step": 414
},
{
"epoch": 2.985611510791367,
"grad_norm": 0.05124146118760109,
"learning_rate": 8.677382735781167e-05,
"loss": 0.783203125,
"step": 415
},
{
"epoch": 2.9928057553956835,
"grad_norm": 0.05628963187336922,
"learning_rate": 8.63687905369301e-05,
"loss": 0.78564453125,
"step": 416
},
{
"epoch": 3.0,
"grad_norm": 0.048284124583005905,
"learning_rate": 8.596426712698517e-05,
"loss": 0.637939453125,
"step": 417
},
{
"epoch": 3.0,
"eval_loss": 0.82177734375,
"eval_runtime": 2.2016,
"eval_samples_per_second": 3.179,
"eval_steps_per_second": 0.454,
"step": 417
},
{
"epoch": 3.0071942446043165,
"grad_norm": 0.05124033987522125,
"learning_rate": 8.556026591664015e-05,
"loss": 0.736083984375,
"step": 418
},
{
"epoch": 3.014388489208633,
"grad_norm": 0.05780182033777237,
"learning_rate": 8.515679568321304e-05,
"loss": 0.771484375,
"step": 419
},
{
"epoch": 3.0215827338129495,
"grad_norm": 0.05943476781249046,
"learning_rate": 8.475386519248584e-05,
"loss": 0.7783203125,
"step": 420
},
{
"epoch": 3.028776978417266,
"grad_norm": 0.05019712448120117,
"learning_rate": 8.435148319851411e-05,
"loss": 0.74462890625,
"step": 421
},
{
"epoch": 3.0359712230215825,
"grad_norm": 0.054737389087677,
"learning_rate": 8.394965844343678e-05,
"loss": 0.79443359375,
"step": 422
},
{
"epoch": 3.0431654676258995,
"grad_norm": 0.04977088421583176,
"learning_rate": 8.354839965728625e-05,
"loss": 0.78955078125,
"step": 423
},
{
"epoch": 3.050359712230216,
"grad_norm": 0.04908246546983719,
"learning_rate": 8.314771555779861e-05,
"loss": 0.83056640625,
"step": 424
},
{
"epoch": 3.0575539568345325,
"grad_norm": 0.04794957861304283,
"learning_rate": 8.274761485022448e-05,
"loss": 0.81689453125,
"step": 425
},
{
"epoch": 3.064748201438849,
"grad_norm": 0.05270487070083618,
"learning_rate": 8.234810622713964e-05,
"loss": 0.80908203125,
"step": 426
},
{
"epoch": 3.0719424460431655,
"grad_norm": 0.0510353185236454,
"learning_rate": 8.194919836825621e-05,
"loss": 0.7998046875,
"step": 427
},
{
"epoch": 3.079136690647482,
"grad_norm": 0.04862328991293907,
"learning_rate": 8.15508999402342e-05,
"loss": 0.72900390625,
"step": 428
},
{
"epoch": 3.0863309352517985,
"grad_norm": 0.04735175892710686,
"learning_rate": 8.115321959649312e-05,
"loss": 0.82177734375,
"step": 429
},
{
"epoch": 3.093525179856115,
"grad_norm": 0.04738014563918114,
"learning_rate": 8.0756165977024e-05,
"loss": 0.623687744140625,
"step": 430
},
{
"epoch": 3.1007194244604315,
"grad_norm": 0.05122707411646843,
"learning_rate": 8.035974770820168e-05,
"loss": 0.76904296875,
"step": 431
},
{
"epoch": 3.1079136690647484,
"grad_norm": 0.04897474870085716,
"learning_rate": 7.996397340259733e-05,
"loss": 0.7490234375,
"step": 432
},
{
"epoch": 3.115107913669065,
"grad_norm": 0.049110472202301025,
"learning_rate": 7.956885165879155e-05,
"loss": 0.79345703125,
"step": 433
},
{
"epoch": 3.1223021582733814,
"grad_norm": 0.05037524923682213,
"learning_rate": 7.917439106118727e-05,
"loss": 0.7421875,
"step": 434
},
{
"epoch": 3.129496402877698,
"grad_norm": 0.05342976003885269,
"learning_rate": 7.87806001798234e-05,
"loss": 0.72802734375,
"step": 435
},
{
"epoch": 3.1366906474820144,
"grad_norm": 0.05058697238564491,
"learning_rate": 7.838748757018862e-05,
"loss": 0.7353515625,
"step": 436
},
{
"epoch": 3.143884892086331,
"grad_norm": 0.05026276037096977,
"learning_rate": 7.799506177303549e-05,
"loss": 0.70849609375,
"step": 437
},
{
"epoch": 3.1510791366906474,
"grad_norm": 0.057681672275066376,
"learning_rate": 7.760333131419495e-05,
"loss": 0.79931640625,
"step": 438
},
{
"epoch": 3.158273381294964,
"grad_norm": 0.050785940140485764,
"learning_rate": 7.7212304704391e-05,
"loss": 0.76904296875,
"step": 439
},
{
"epoch": 3.1654676258992804,
"grad_norm": 0.049005765467882156,
"learning_rate": 7.682199043905589e-05,
"loss": 0.74267578125,
"step": 440
},
{
"epoch": 3.172661870503597,
"grad_norm": 0.058562297374010086,
"learning_rate": 7.643239699814539e-05,
"loss": 0.78271484375,
"step": 441
},
{
"epoch": 3.1798561151079134,
"grad_norm": 0.0556296780705452,
"learning_rate": 7.604353284595478e-05,
"loss": 0.73388671875,
"step": 442
},
{
"epoch": 3.1870503597122304,
"grad_norm": 0.05670291185379028,
"learning_rate": 7.565540643093472e-05,
"loss": 0.75244140625,
"step": 443
},
{
"epoch": 3.194244604316547,
"grad_norm": 0.06160172075033188,
"learning_rate": 7.526802618550792e-05,
"loss": 0.74560546875,
"step": 444
},
{
"epoch": 3.2014388489208634,
"grad_norm": 0.052574463188648224,
"learning_rate": 7.488140052588579e-05,
"loss": 0.74658203125,
"step": 445
},
{
"epoch": 3.20863309352518,
"grad_norm": 0.05169880762696266,
"learning_rate": 7.449553785188559e-05,
"loss": 0.8251953125,
"step": 446
},
{
"epoch": 3.2158273381294964,
"grad_norm": 0.05542999878525734,
"learning_rate": 7.411044654674806e-05,
"loss": 0.7744140625,
"step": 447
},
{
"epoch": 3.223021582733813,
"grad_norm": 0.05371973663568497,
"learning_rate": 7.372613497695513e-05,
"loss": 0.80078125,
"step": 448
},
{
"epoch": 3.2302158273381294,
"grad_norm": 0.04892808571457863,
"learning_rate": 7.334261149204826e-05,
"loss": 0.76123046875,
"step": 449
},
{
"epoch": 3.237410071942446,
"grad_norm": 0.056769244372844696,
"learning_rate": 7.295988442444699e-05,
"loss": 0.787109375,
"step": 450
},
{
"epoch": 3.2446043165467624,
"grad_norm": 0.0478750616312027,
"learning_rate": 7.257796208926795e-05,
"loss": 0.701416015625,
"step": 451
},
{
"epoch": 3.2517985611510793,
"grad_norm": 0.05442335456609726,
"learning_rate": 7.219685278414415e-05,
"loss": 0.787109375,
"step": 452
},
{
"epoch": 3.258992805755396,
"grad_norm": 0.055913351476192474,
"learning_rate": 7.181656478904471e-05,
"loss": 0.80419921875,
"step": 453
},
{
"epoch": 3.2661870503597124,
"grad_norm": 0.05457060784101486,
"learning_rate": 7.143710636609506e-05,
"loss": 0.75830078125,
"step": 454
},
{
"epoch": 3.273381294964029,
"grad_norm": 0.05049818009138107,
"learning_rate": 7.10584857593973e-05,
"loss": 0.810546875,
"step": 455
},
{
"epoch": 3.2805755395683454,
"grad_norm": 0.05422035977244377,
"learning_rate": 7.068071119485123e-05,
"loss": 0.779296875,
"step": 456
},
{
"epoch": 3.287769784172662,
"grad_norm": 0.051914189010858536,
"learning_rate": 7.030379087997549e-05,
"loss": 0.74169921875,
"step": 457
},
{
"epoch": 3.2949640287769784,
"grad_norm": 0.05313270911574364,
"learning_rate": 6.992773300372939e-05,
"loss": 0.80078125,
"step": 458
},
{
"epoch": 3.302158273381295,
"grad_norm": 0.05497153475880623,
"learning_rate": 6.955254573633485e-05,
"loss": 0.70556640625,
"step": 459
},
{
"epoch": 3.3093525179856114,
"grad_norm": 0.05494280159473419,
"learning_rate": 6.917823722909902e-05,
"loss": 0.77001953125,
"step": 460
},
{
"epoch": 3.316546762589928,
"grad_norm": 0.051706552505493164,
"learning_rate": 6.880481561423715e-05,
"loss": 0.76513671875,
"step": 461
},
{
"epoch": 3.3237410071942444,
"grad_norm": 0.05260934680700302,
"learning_rate": 6.843228900469585e-05,
"loss": 0.7353515625,
"step": 462
},
{
"epoch": 3.3309352517985613,
"grad_norm": 0.05296942964196205,
"learning_rate": 6.806066549397684e-05,
"loss": 0.77734375,
"step": 463
},
{
"epoch": 3.338129496402878,
"grad_norm": 0.04702047258615494,
"learning_rate": 6.768995315596127e-05,
"loss": 0.802734375,
"step": 464
},
{
"epoch": 3.3453237410071943,
"grad_norm": 0.048695724457502365,
"learning_rate": 6.732016004473404e-05,
"loss": 0.66455078125,
"step": 465
},
{
"epoch": 3.352517985611511,
"grad_norm": 0.055471207946538925,
"learning_rate": 6.695129419440903e-05,
"loss": 0.75244140625,
"step": 466
},
{
"epoch": 3.3597122302158273,
"grad_norm": 0.05254025384783745,
"learning_rate": 6.658336361895448e-05,
"loss": 0.74169921875,
"step": 467
},
{
"epoch": 3.366906474820144,
"grad_norm": 0.051775965839624405,
"learning_rate": 6.621637631201882e-05,
"loss": 0.75,
"step": 468
},
{
"epoch": 3.3741007194244603,
"grad_norm": 0.0537375845015049,
"learning_rate": 6.585034024675715e-05,
"loss": 0.7744140625,
"step": 469
},
{
"epoch": 3.381294964028777,
"grad_norm": 0.04723677411675453,
"learning_rate": 6.548526337565782e-05,
"loss": 0.699462890625,
"step": 470
},
{
"epoch": 3.3884892086330938,
"grad_norm": 0.05137712508440018,
"learning_rate": 6.512115363036982e-05,
"loss": 0.67333984375,
"step": 471
},
{
"epoch": 3.3956834532374103,
"grad_norm": 0.05072665959596634,
"learning_rate": 6.475801892153042e-05,
"loss": 0.7685546875,
"step": 472
},
{
"epoch": 3.402877697841727,
"grad_norm": 0.048014163970947266,
"learning_rate": 6.439586713859319e-05,
"loss": 0.6507568359375,
"step": 473
},
{
"epoch": 3.4100719424460433,
"grad_norm": 0.05200881510972977,
"learning_rate": 6.403470614965674e-05,
"loss": 0.701171875,
"step": 474
},
{
"epoch": 3.41726618705036,
"grad_norm": 0.0488160140812397,
"learning_rate": 6.367454380129371e-05,
"loss": 0.7373046875,
"step": 475
},
{
"epoch": 3.4244604316546763,
"grad_norm": 0.04956590384244919,
"learning_rate": 6.331538791838029e-05,
"loss": 0.80810546875,
"step": 476
},
{
"epoch": 3.431654676258993,
"grad_norm": 0.051326870918273926,
"learning_rate": 6.295724630392632e-05,
"loss": 0.73876953125,
"step": 477
},
{
"epoch": 3.4388489208633093,
"grad_norm": 0.0495428666472435,
"learning_rate": 6.260012673890552e-05,
"loss": 0.8037109375,
"step": 478
},
{
"epoch": 3.446043165467626,
"grad_norm": 0.05170230194926262,
"learning_rate": 6.22440369820867e-05,
"loss": 0.74755859375,
"step": 479
},
{
"epoch": 3.4532374100719423,
"grad_norm": 0.05247701331973076,
"learning_rate": 6.188898476986506e-05,
"loss": 0.76708984375,
"step": 480
},
{
"epoch": 3.460431654676259,
"grad_norm": 0.05309170484542847,
"learning_rate": 6.153497781609416e-05,
"loss": 0.74658203125,
"step": 481
},
{
"epoch": 3.4676258992805753,
"grad_norm": 0.05857396870851517,
"learning_rate": 6.118202381191828e-05,
"loss": 0.74365234375,
"step": 482
},
{
"epoch": 3.4748201438848922,
"grad_norm": 0.04985760524868965,
"learning_rate": 6.083013042560538e-05,
"loss": 0.75341796875,
"step": 483
},
{
"epoch": 3.4820143884892087,
"grad_norm": 0.048217304050922394,
"learning_rate": 6.047930530238042e-05,
"loss": 0.63482666015625,
"step": 484
},
{
"epoch": 3.4892086330935252,
"grad_norm": 0.054268497973680496,
"learning_rate": 6.012955606425933e-05,
"loss": 0.8095703125,
"step": 485
},
{
"epoch": 3.4964028776978417,
"grad_norm": 0.055208269506692886,
"learning_rate": 5.978089030988341e-05,
"loss": 0.7705078125,
"step": 486
},
{
"epoch": 3.5035971223021583,
"grad_norm": 0.05179133266210556,
"learning_rate": 5.943331561435424e-05,
"loss": 0.70849609375,
"step": 487
},
{
"epoch": 3.5107913669064748,
"grad_norm": 0.05390201508998871,
"learning_rate": 5.9086839529069e-05,
"loss": 0.7412109375,
"step": 488
},
{
"epoch": 3.5179856115107913,
"grad_norm": 0.048443473875522614,
"learning_rate": 5.874146958155663e-05,
"loss": 0.642425537109375,
"step": 489
},
{
"epoch": 3.5251798561151078,
"grad_norm": 0.05413110926747322,
"learning_rate": 5.8397213275314046e-05,
"loss": 0.7607421875,
"step": 490
},
{
"epoch": 3.5323741007194247,
"grad_norm": 0.048942968249320984,
"learning_rate": 5.805407808964327e-05,
"loss": 0.767578125,
"step": 491
},
{
"epoch": 3.539568345323741,
"grad_norm": 0.050069428980350494,
"learning_rate": 5.771207147948889e-05,
"loss": 0.77001953125,
"step": 492
},
{
"epoch": 3.5467625899280577,
"grad_norm": 0.05499282106757164,
"learning_rate": 5.737120087527612e-05,
"loss": 0.75927734375,
"step": 493
},
{
"epoch": 3.553956834532374,
"grad_norm": 0.05234140530228615,
"learning_rate": 5.703147368274929e-05,
"loss": 0.7216796875,
"step": 494
},
{
"epoch": 3.5611510791366907,
"grad_norm": 0.04955899715423584,
"learning_rate": 5.669289728281104e-05,
"loss": 0.71337890625,
"step": 495
},
{
"epoch": 3.568345323741007,
"grad_norm": 0.050279274582862854,
"learning_rate": 5.635547903136191e-05,
"loss": 0.71630859375,
"step": 496
},
{
"epoch": 3.5755395683453237,
"grad_norm": 0.053482405841350555,
"learning_rate": 5.6019226259140554e-05,
"loss": 0.74462890625,
"step": 497
},
{
"epoch": 3.58273381294964,
"grad_norm": 0.052684132009744644,
"learning_rate": 5.5684146271564465e-05,
"loss": 0.737060546875,
"step": 498
},
{
"epoch": 3.5899280575539567,
"grad_norm": 0.05227554216980934,
"learning_rate": 5.535024634857122e-05,
"loss": 0.7353515625,
"step": 499
},
{
"epoch": 3.597122302158273,
"grad_norm": 0.05112195014953613,
"learning_rate": 5.5017533744460405e-05,
"loss": 0.7978515625,
"step": 500
},
{
"epoch": 3.6043165467625897,
"grad_norm": 0.05106304585933685,
"learning_rate": 5.468601568773588e-05,
"loss": 0.76025390625,
"step": 501
},
{
"epoch": 3.6115107913669062,
"grad_norm": 0.0527038611471653,
"learning_rate": 5.435569938094884e-05,
"loss": 0.69970703125,
"step": 502
},
{
"epoch": 3.618705035971223,
"grad_norm": 0.04788810387253761,
"learning_rate": 5.402659200054133e-05,
"loss": 0.687713623046875,
"step": 503
},
{
"epoch": 3.6258992805755397,
"grad_norm": 0.049707453697919846,
"learning_rate": 5.369870069669027e-05,
"loss": 0.78466796875,
"step": 504
},
{
"epoch": 3.633093525179856,
"grad_norm": 0.050782762467861176,
"learning_rate": 5.337203259315212e-05,
"loss": 0.78759765625,
"step": 505
},
{
"epoch": 3.6402877697841727,
"grad_norm": 0.0569625087082386,
"learning_rate": 5.3046594787108136e-05,
"loss": 0.73388671875,
"step": 506
},
{
"epoch": 3.647482014388489,
"grad_norm": 0.04848095029592514,
"learning_rate": 5.272239434901021e-05,
"loss": 0.7939453125,
"step": 507
},
{
"epoch": 3.6546762589928057,
"grad_norm": 0.050739582628011703,
"learning_rate": 5.239943832242712e-05,
"loss": 0.748291015625,
"step": 508
},
{
"epoch": 3.661870503597122,
"grad_norm": 0.050485655665397644,
"learning_rate": 5.20777337238917e-05,
"loss": 0.77734375,
"step": 509
},
{
"epoch": 3.6690647482014387,
"grad_norm": 0.053736161440610886,
"learning_rate": 5.1757287542748265e-05,
"loss": 0.76708984375,
"step": 510
},
{
"epoch": 3.6762589928057556,
"grad_norm": 0.04893803969025612,
"learning_rate": 5.143810674100075e-05,
"loss": 0.73291015625,
"step": 511
},
{
"epoch": 3.683453237410072,
"grad_norm": 0.04592687264084816,
"learning_rate": 5.112019825316152e-05,
"loss": 0.658294677734375,
"step": 512
},
{
"epoch": 3.6906474820143886,
"grad_norm": 0.05054721608757973,
"learning_rate": 5.080356898610072e-05,
"loss": 0.7607421875,
"step": 513
},
{
"epoch": 3.697841726618705,
"grad_norm": 0.05290023982524872,
"learning_rate": 5.048822581889614e-05,
"loss": 0.73193359375,
"step": 514
},
{
"epoch": 3.7050359712230216,
"grad_norm": 0.05200814828276634,
"learning_rate": 5.017417560268383e-05,
"loss": 0.7763671875,
"step": 515
},
{
"epoch": 3.712230215827338,
"grad_norm": 0.045379430055618286,
"learning_rate": 4.9861425160509225e-05,
"loss": 0.6854248046875,
"step": 516
},
{
"epoch": 3.7194244604316546,
"grad_norm": 0.05427764728665352,
"learning_rate": 4.954998128717889e-05,
"loss": 0.77978515625,
"step": 517
},
{
"epoch": 3.726618705035971,
"grad_norm": 0.048872821033000946,
"learning_rate": 4.9239850749112916e-05,
"loss": 0.697265625,
"step": 518
},
{
"epoch": 3.7338129496402876,
"grad_norm": 0.049144014716148376,
"learning_rate": 4.893104028419794e-05,
"loss": 0.76220703125,
"step": 519
},
{
"epoch": 3.741007194244604,
"grad_norm": 0.05242089554667473,
"learning_rate": 4.86235566016407e-05,
"loss": 0.69775390625,
"step": 520
},
{
"epoch": 3.7482014388489207,
"grad_norm": 0.05214497447013855,
"learning_rate": 4.8317406381822316e-05,
"loss": 0.77001953125,
"step": 521
},
{
"epoch": 3.755395683453237,
"grad_norm": 0.05071490630507469,
"learning_rate": 4.8012596276153135e-05,
"loss": 0.71630859375,
"step": 522
},
{
"epoch": 3.762589928057554,
"grad_norm": 0.04996147379279137,
"learning_rate": 4.770913290692823e-05,
"loss": 0.6812744140625,
"step": 523
},
{
"epoch": 3.7697841726618706,
"grad_norm": 0.050162509083747864,
"learning_rate": 4.740702286718352e-05,
"loss": 0.77392578125,
"step": 524
},
{
"epoch": 3.776978417266187,
"grad_norm": 0.05255437269806862,
"learning_rate": 4.710627272055249e-05,
"loss": 0.77587890625,
"step": 525
},
{
"epoch": 3.7841726618705036,
"grad_norm": 0.053341519087553024,
"learning_rate": 4.6806889001123685e-05,
"loss": 0.77490234375,
"step": 526
},
{
"epoch": 3.79136690647482,
"grad_norm": 0.05236722156405449,
"learning_rate": 4.650887821329867e-05,
"loss": 0.75390625,
"step": 527
},
{
"epoch": 3.7985611510791366,
"grad_norm": 0.053622376173734665,
"learning_rate": 4.6212246831650704e-05,
"loss": 0.7138671875,
"step": 528
},
{
"epoch": 3.805755395683453,
"grad_norm": 0.05114729702472687,
"learning_rate": 4.5917001300784195e-05,
"loss": 0.7431640625,
"step": 529
},
{
"epoch": 3.81294964028777,
"grad_norm": 0.049589745700359344,
"learning_rate": 4.5623148035194536e-05,
"loss": 0.77880859375,
"step": 530
},
{
"epoch": 3.8201438848920866,
"grad_norm": 0.05088301748037338,
"learning_rate": 4.533069341912882e-05,
"loss": 0.74658203125,
"step": 531
},
{
"epoch": 3.827338129496403,
"grad_norm": 0.052272845059633255,
"learning_rate": 4.5039643806447105e-05,
"loss": 0.724609375,
"step": 532
},
{
"epoch": 3.8345323741007196,
"grad_norm": 0.04949336498975754,
"learning_rate": 4.4750005520484416e-05,
"loss": 0.7958984375,
"step": 533
},
{
"epoch": 3.841726618705036,
"grad_norm": 0.05118298903107643,
"learning_rate": 4.446178485391334e-05,
"loss": 0.78125,
"step": 534
},
{
"epoch": 3.8489208633093526,
"grad_norm": 0.047677114605903625,
"learning_rate": 4.417498806860728e-05,
"loss": 0.6572113037109375,
"step": 535
},
{
"epoch": 3.856115107913669,
"grad_norm": 0.05299853906035423,
"learning_rate": 4.388962139550447e-05,
"loss": 0.652587890625,
"step": 536
},
{
"epoch": 3.8633093525179856,
"grad_norm": 0.053162094205617905,
"learning_rate": 4.3605691034472523e-05,
"loss": 0.720703125,
"step": 537
},
{
"epoch": 3.870503597122302,
"grad_norm": 0.053543951362371445,
"learning_rate": 4.332320315417383e-05,
"loss": 0.740234375,
"step": 538
},
{
"epoch": 3.8776978417266186,
"grad_norm": 0.05336477607488632,
"learning_rate": 4.3042163891931485e-05,
"loss": 0.74560546875,
"step": 539
},
{
"epoch": 3.884892086330935,
"grad_norm": 0.05142592266201973,
"learning_rate": 4.276257935359591e-05,
"loss": 0.73388671875,
"step": 540
},
{
"epoch": 3.8920863309352516,
"grad_norm": 0.05190040543675423,
"learning_rate": 4.2484455613412275e-05,
"loss": 0.779296875,
"step": 541
},
{
"epoch": 3.899280575539568,
"grad_norm": 0.05213189870119095,
"learning_rate": 4.220779871388848e-05,
"loss": 0.76953125,
"step": 542
},
{
"epoch": 3.906474820143885,
"grad_norm": 0.05089110508561134,
"learning_rate": 4.193261466566389e-05,
"loss": 0.6767578125,
"step": 543
},
{
"epoch": 3.9136690647482015,
"grad_norm": 0.042859405279159546,
"learning_rate": 4.165890944737877e-05,
"loss": 0.609222412109375,
"step": 544
},
{
"epoch": 3.920863309352518,
"grad_norm": 0.0537886843085289,
"learning_rate": 4.138668900554433e-05,
"loss": 0.71923828125,
"step": 545
},
{
"epoch": 3.9280575539568345,
"grad_norm": 0.055188652127981186,
"learning_rate": 4.111595925441363e-05,
"loss": 0.7177734375,
"step": 546
},
{
"epoch": 3.935251798561151,
"grad_norm": 0.051305752247571945,
"learning_rate": 4.084672607585293e-05,
"loss": 0.72607421875,
"step": 547
},
{
"epoch": 3.9424460431654675,
"grad_norm": 0.04906954616308212,
"learning_rate": 4.0578995319214095e-05,
"loss": 0.701171875,
"step": 548
},
{
"epoch": 3.949640287769784,
"grad_norm": 0.0526224747300148,
"learning_rate": 4.03127728012074e-05,
"loss": 0.71484375,
"step": 549
},
{
"epoch": 3.956834532374101,
"grad_norm": 0.05646233260631561,
"learning_rate": 4.004806430577512e-05,
"loss": 0.7138671875,
"step": 550
},
{
"epoch": 3.9640287769784175,
"grad_norm": 0.051627133041620255,
"learning_rate": 3.9784875583966006e-05,
"loss": 0.71435546875,
"step": 551
},
{
"epoch": 3.971223021582734,
"grad_norm": 0.05187356472015381,
"learning_rate": 3.952321235381018e-05,
"loss": 0.73291015625,
"step": 552
},
{
"epoch": 3.9784172661870505,
"grad_norm": 0.049104101955890656,
"learning_rate": 3.926308030019501e-05,
"loss": 0.7841796875,
"step": 553
},
{
"epoch": 3.985611510791367,
"grad_norm": 0.05155986174941063,
"learning_rate": 3.900448507474154e-05,
"loss": 0.751953125,
"step": 554
},
{
"epoch": 3.9928057553956835,
"grad_norm": 0.054259348660707474,
"learning_rate": 3.874743229568181e-05,
"loss": 0.75439453125,
"step": 555
},
{
"epoch": 4.0,
"grad_norm": 0.05910147354006767,
"learning_rate": 3.849192754773665e-05,
"loss": 0.599365234375,
"step": 556
},
{
"epoch": 4.0,
"eval_loss": 0.822265625,
"eval_runtime": 2.1989,
"eval_samples_per_second": 3.183,
"eval_steps_per_second": 0.455,
"step": 556
},
{
"epoch": 4.0071942446043165,
"grad_norm": 0.05912397429347038,
"learning_rate": 3.82379763819944e-05,
"loss": 0.693603515625,
"step": 557
},
{
"epoch": 4.014388489208633,
"grad_norm": 0.06123586371541023,
"learning_rate": 3.798558431579038e-05,
"loss": 0.74169921875,
"step": 558
},
{
"epoch": 4.0215827338129495,
"grad_norm": 0.0732521265745163,
"learning_rate": 3.773475683258689e-05,
"loss": 0.74658203125,
"step": 559
},
{
"epoch": 4.028776978417266,
"grad_norm": 0.05880795791745186,
"learning_rate": 3.7485499381854226e-05,
"loss": 0.716796875,
"step": 560
},
{
"epoch": 4.0359712230215825,
"grad_norm": 0.059538763016462326,
"learning_rate": 3.723781737895216e-05,
"loss": 0.765625,
"step": 561
},
{
"epoch": 4.043165467625899,
"grad_norm": 0.05364465340971947,
"learning_rate": 3.6991716205012315e-05,
"loss": 0.763671875,
"step": 562
},
{
"epoch": 4.0503597122302155,
"grad_norm": 0.05475439876317978,
"learning_rate": 3.674720120682132e-05,
"loss": 0.80224609375,
"step": 563
},
{
"epoch": 4.057553956834532,
"grad_norm": 0.055658478289842606,
"learning_rate": 3.650427769670456e-05,
"loss": 0.7900390625,
"step": 564
},
{
"epoch": 4.0647482014388485,
"grad_norm": 0.05783562362194061,
"learning_rate": 3.6262950952410824e-05,
"loss": 0.7802734375,
"step": 565
},
{
"epoch": 4.071942446043165,
"grad_norm": 0.05364576727151871,
"learning_rate": 3.602322621699759e-05,
"loss": 0.771484375,
"step": 566
},
{
"epoch": 4.079136690647482,
"grad_norm": 0.05449522286653519,
"learning_rate": 3.5785108698717166e-05,
"loss": 0.6982421875,
"step": 567
},
{
"epoch": 4.086330935251799,
"grad_norm": 0.05523834750056267,
"learning_rate": 3.5548603570903495e-05,
"loss": 0.794921875,
"step": 568
},
{
"epoch": 4.093525179856115,
"grad_norm": 0.05030881613492966,
"learning_rate": 3.531371597185976e-05,
"loss": 0.5995635986328125,
"step": 569
},
{
"epoch": 4.100719424460432,
"grad_norm": 0.0534730926156044,
"learning_rate": 3.508045100474682e-05,
"loss": 0.740234375,
"step": 570
},
{
"epoch": 4.107913669064748,
"grad_norm": 0.05776934325695038,
"learning_rate": 3.484881373747218e-05,
"loss": 0.72216796875,
"step": 571
},
{
"epoch": 4.115107913669065,
"grad_norm": 0.055672962218523026,
"learning_rate": 3.461880920258012e-05,
"loss": 0.7666015625,
"step": 572
},
{
"epoch": 4.122302158273381,
"grad_norm": 0.05157998576760292,
"learning_rate": 3.439044239714211e-05,
"loss": 0.7158203125,
"step": 573
},
{
"epoch": 4.129496402877698,
"grad_norm": 0.05499252304434776,
"learning_rate": 3.416371828264842e-05,
"loss": 0.70068359375,
"step": 574
},
{
"epoch": 4.136690647482014,
"grad_norm": 0.05596167594194412,
"learning_rate": 3.393864178490025e-05,
"loss": 0.70703125,
"step": 575
},
{
"epoch": 4.143884892086331,
"grad_norm": 0.05461525544524193,
"learning_rate": 3.3715217793902736e-05,
"loss": 0.6806640625,
"step": 576
},
{
"epoch": 4.151079136690647,
"grad_norm": 0.050671517848968506,
"learning_rate": 3.349345116375868e-05,
"loss": 0.77197265625,
"step": 577
},
{
"epoch": 4.158273381294964,
"grad_norm": 0.052400026470422745,
"learning_rate": 3.327334671256316e-05,
"loss": 0.7412109375,
"step": 578
},
{
"epoch": 4.16546762589928,
"grad_norm": 0.052314918488264084,
"learning_rate": 3.305490922229874e-05,
"loss": 0.716796875,
"step": 579
},
{
"epoch": 4.172661870503597,
"grad_norm": 0.05323723331093788,
"learning_rate": 3.2838143438731704e-05,
"loss": 0.75537109375,
"step": 580
},
{
"epoch": 4.179856115107913,
"grad_norm": 0.054106373339891434,
"learning_rate": 3.2623054071308855e-05,
"loss": 0.70458984375,
"step": 581
},
{
"epoch": 4.18705035971223,
"grad_norm": 0.05198446288704872,
"learning_rate": 3.240964579305522e-05,
"loss": 0.7236328125,
"step": 582
},
{
"epoch": 4.194244604316546,
"grad_norm": 0.053653303533792496,
"learning_rate": 3.2197923240472574e-05,
"loss": 0.716796875,
"step": 583
},
{
"epoch": 4.201438848920863,
"grad_norm": 0.05069001764059067,
"learning_rate": 3.198789101343861e-05,
"loss": 0.7197265625,
"step": 584
},
{
"epoch": 4.2086330935251794,
"grad_norm": 0.05460018292069435,
"learning_rate": 3.1779553675107134e-05,
"loss": 0.80029296875,
"step": 585
},
{
"epoch": 4.215827338129497,
"grad_norm": 0.051281604915857315,
"learning_rate": 3.157291575180877e-05,
"loss": 0.74658203125,
"step": 586
},
{
"epoch": 4.223021582733813,
"grad_norm": 0.05118497088551521,
"learning_rate": 3.136798173295275e-05,
"loss": 0.77392578125,
"step": 587
},
{
"epoch": 4.23021582733813,
"grad_norm": 0.05297469347715378,
"learning_rate": 3.116475607092935e-05,
"loss": 0.73388671875,
"step": 588
},
{
"epoch": 4.237410071942446,
"grad_norm": 0.050522178411483765,
"learning_rate": 3.096324318101308e-05,
"loss": 0.7587890625,
"step": 589
},
{
"epoch": 4.244604316546763,
"grad_norm": 0.04883132502436638,
"learning_rate": 3.076344744126685e-05,
"loss": 0.6790771484375,
"step": 590
},
{
"epoch": 4.251798561151079,
"grad_norm": 0.05249188467860222,
"learning_rate": 3.056537319244683e-05,
"loss": 0.76171875,
"step": 591
},
{
"epoch": 4.258992805755396,
"grad_norm": 0.04979240894317627,
"learning_rate": 3.0369024737908093e-05,
"loss": 0.77880859375,
"step": 592
},
{
"epoch": 4.266187050359712,
"grad_norm": 0.05447956174612045,
"learning_rate": 3.0174406343511186e-05,
"loss": 0.72998046875,
"step": 593
},
{
"epoch": 4.273381294964029,
"grad_norm": 0.051062773913145065,
"learning_rate": 2.9981522237529425e-05,
"loss": 0.78662109375,
"step": 594
},
{
"epoch": 4.280575539568345,
"grad_norm": 0.05364208668470383,
"learning_rate": 2.9790376610557e-05,
"loss": 0.7529296875,
"step": 595
},
{
"epoch": 4.287769784172662,
"grad_norm": 0.05287604779005051,
"learning_rate": 2.9600973615417994e-05,
"loss": 0.71533203125,
"step": 596
},
{
"epoch": 4.294964028776978,
"grad_norm": 0.05403478816151619,
"learning_rate": 2.94133173670761e-05,
"loss": 0.77294921875,
"step": 597
},
{
"epoch": 4.302158273381295,
"grad_norm": 0.05350170284509659,
"learning_rate": 2.9227411942545257e-05,
"loss": 0.677734375,
"step": 598
},
{
"epoch": 4.309352517985611,
"grad_norm": 0.05625879764556885,
"learning_rate": 2.9043261380801036e-05,
"loss": 0.7431640625,
"step": 599
},
{
"epoch": 4.316546762589928,
"grad_norm": 0.05229846388101578,
"learning_rate": 2.8860869682692955e-05,
"loss": 0.73779296875,
"step": 600
},
{
"epoch": 4.323741007194244,
"grad_norm": 0.052753571420907974,
"learning_rate": 2.8680240810857467e-05,
"loss": 0.7099609375,
"step": 601
},
{
"epoch": 4.330935251798561,
"grad_norm": 0.05504533648490906,
"learning_rate": 2.8501378689631953e-05,
"loss": 0.75048828125,
"step": 602
},
{
"epoch": 4.338129496402877,
"grad_norm": 0.05058334395289421,
"learning_rate": 2.8324287204969387e-05,
"loss": 0.77783203125,
"step": 603
},
{
"epoch": 4.345323741007194,
"grad_norm": 0.05247846245765686,
"learning_rate": 2.8148970204353992e-05,
"loss": 0.6416015625,
"step": 604
},
{
"epoch": 4.35251798561151,
"grad_norm": 0.05337994918227196,
"learning_rate": 2.797543149671757e-05,
"loss": 0.72802734375,
"step": 605
},
{
"epoch": 4.359712230215827,
"grad_norm": 0.054547443985939026,
"learning_rate": 2.780367485235677e-05,
"loss": 0.71435546875,
"step": 606
},
{
"epoch": 4.366906474820144,
"grad_norm": 0.054399874061346054,
"learning_rate": 2.7633704002851252e-05,
"loss": 0.72314453125,
"step": 607
},
{
"epoch": 4.374100719424461,
"grad_norm": 0.05170078203082085,
"learning_rate": 2.746552264098251e-05,
"loss": 0.75244140625,
"step": 608
},
{
"epoch": 4.381294964028777,
"grad_norm": 0.04778819531202316,
"learning_rate": 2.7299134420653665e-05,
"loss": 0.677978515625,
"step": 609
},
{
"epoch": 4.388489208633094,
"grad_norm": 0.0491393581032753,
"learning_rate": 2.713454295681016e-05,
"loss": 0.65087890625,
"step": 610
},
{
"epoch": 4.39568345323741,
"grad_norm": 0.0522012785077095,
"learning_rate": 2.6971751825361065e-05,
"loss": 0.74462890625,
"step": 611
},
{
"epoch": 4.402877697841727,
"grad_norm": 0.04799595847725868,
"learning_rate": 2.681076456310157e-05,
"loss": 0.6298828125,
"step": 612
},
{
"epoch": 4.410071942446043,
"grad_norm": 0.054174259305000305,
"learning_rate": 2.6651584667636038e-05,
"loss": 0.67626953125,
"step": 613
},
{
"epoch": 4.41726618705036,
"grad_norm": 0.05027070641517639,
"learning_rate": 2.6494215597302012e-05,
"loss": 0.71533203125,
"step": 614
},
{
"epoch": 4.424460431654676,
"grad_norm": 0.04885563254356384,
"learning_rate": 2.6338660771095125e-05,
"loss": 0.783203125,
"step": 615
},
{
"epoch": 4.431654676258993,
"grad_norm": 0.0508473739027977,
"learning_rate": 2.618492356859479e-05,
"loss": 0.71337890625,
"step": 616
},
{
"epoch": 4.438848920863309,
"grad_norm": 0.05053354427218437,
"learning_rate": 2.603300732989078e-05,
"loss": 0.78076171875,
"step": 617
},
{
"epoch": 4.446043165467626,
"grad_norm": 0.052582401782274246,
"learning_rate": 2.588291535551068e-05,
"loss": 0.72412109375,
"step": 618
},
{
"epoch": 4.453237410071942,
"grad_norm": 0.0530349537730217,
"learning_rate": 2.573465090634813e-05,
"loss": 0.74462890625,
"step": 619
},
{
"epoch": 4.460431654676259,
"grad_norm": 0.05255937948822975,
"learning_rate": 2.558821720359204e-05,
"loss": 0.720703125,
"step": 620
},
{
"epoch": 4.467625899280575,
"grad_norm": 0.058697544038295746,
"learning_rate": 2.5443617428656603e-05,
"loss": 0.716796875,
"step": 621
},
{
"epoch": 4.474820143884892,
"grad_norm": 0.05128984525799751,
"learning_rate": 2.530085472311208e-05,
"loss": 0.73095703125,
"step": 622
},
{
"epoch": 4.482014388489208,
"grad_norm": 0.049633316695690155,
"learning_rate": 2.5159932188616687e-05,
"loss": 0.61444091796875,
"step": 623
},
{
"epoch": 4.489208633093525,
"grad_norm": 0.050551820546388626,
"learning_rate": 2.502085288684911e-05,
"loss": 0.787109375,
"step": 624
},
{
"epoch": 4.496402877697841,
"grad_norm": 0.05205032601952553,
"learning_rate": 2.488361983944201e-05,
"loss": 0.74609375,
"step": 625
},
{
"epoch": 4.503597122302159,
"grad_norm": 0.05488746985793114,
"learning_rate": 2.4748236027916413e-05,
"loss": 0.68408203125,
"step": 626
},
{
"epoch": 4.510791366906475,
"grad_norm": 0.05285046622157097,
"learning_rate": 2.461470439361686e-05,
"loss": 0.7158203125,
"step": 627
},
{
"epoch": 4.517985611510792,
"grad_norm": 0.04785111919045448,
"learning_rate": 2.448302783764758e-05,
"loss": 0.623626708984375,
"step": 628
},
{
"epoch": 4.525179856115108,
"grad_norm": 0.05188073590397835,
"learning_rate": 2.435320922080942e-05,
"loss": 0.7373046875,
"step": 629
},
{
"epoch": 4.532374100719425,
"grad_norm": 0.05069158226251602,
"learning_rate": 2.4225251363537687e-05,
"loss": 0.74560546875,
"step": 630
},
{
"epoch": 4.539568345323741,
"grad_norm": 0.05008401721715927,
"learning_rate": 2.4099157045840888e-05,
"loss": 0.74951171875,
"step": 631
},
{
"epoch": 4.546762589928058,
"grad_norm": 0.05251746624708176,
"learning_rate": 2.397492900724031e-05,
"loss": 0.736328125,
"step": 632
},
{
"epoch": 4.553956834532374,
"grad_norm": 0.053564026951789856,
"learning_rate": 2.3852569946710573e-05,
"loss": 0.6982421875,
"step": 633
},
{
"epoch": 4.561151079136691,
"grad_norm": 0.05176601931452751,
"learning_rate": 2.3732082522620877e-05,
"loss": 0.69140625,
"step": 634
},
{
"epoch": 4.568345323741007,
"grad_norm": 0.05212892219424248,
"learning_rate": 2.3613469352677315e-05,
"loss": 0.69580078125,
"step": 635
},
{
"epoch": 4.575539568345324,
"grad_norm": 0.05525335669517517,
"learning_rate": 2.349673301386602e-05,
"loss": 0.72265625,
"step": 636
},
{
"epoch": 4.58273381294964,
"grad_norm": 0.05233904346823692,
"learning_rate": 2.3381876042397114e-05,
"loss": 0.71435546875,
"step": 637
},
{
"epoch": 4.589928057553957,
"grad_norm": 0.05244535952806473,
"learning_rate": 2.3268900933649683e-05,
"loss": 0.71533203125,
"step": 638
},
{
"epoch": 4.597122302158273,
"grad_norm": 0.05539185181260109,
"learning_rate": 2.3157810142117473e-05,
"loss": 0.775390625,
"step": 639
},
{
"epoch": 4.60431654676259,
"grad_norm": 0.05139709636569023,
"learning_rate": 2.304860608135565e-05,
"loss": 0.73974609375,
"step": 640
},
{
"epoch": 4.611510791366906,
"grad_norm": 0.050320859998464584,
"learning_rate": 2.2941291123928298e-05,
"loss": 0.681640625,
"step": 641
},
{
"epoch": 4.618705035971223,
"grad_norm": 0.047281209379434586,
"learning_rate": 2.283586760135693e-05,
"loss": 0.66949462890625,
"step": 642
},
{
"epoch": 4.625899280575539,
"grad_norm": 0.051026154309511185,
"learning_rate": 2.2732337804069763e-05,
"loss": 0.76416015625,
"step": 643
},
{
"epoch": 4.633093525179856,
"grad_norm": 0.05396101251244545,
"learning_rate": 2.263070398135203e-05,
"loss": 0.7685546875,
"step": 644
},
{
"epoch": 4.640287769784173,
"grad_norm": 0.057470086961984634,
"learning_rate": 2.2530968341297066e-05,
"loss": 0.71240234375,
"step": 645
},
{
"epoch": 4.647482014388489,
"grad_norm": 0.05303116887807846,
"learning_rate": 2.2433133050758355e-05,
"loss": 0.775390625,
"step": 646
},
{
"epoch": 4.654676258992806,
"grad_norm": 0.05158863589167595,
"learning_rate": 2.2337200235302426e-05,
"loss": 0.729248046875,
"step": 647
},
{
"epoch": 4.661870503597123,
"grad_norm": 0.050347328186035156,
"learning_rate": 2.224317197916269e-05,
"loss": 0.7587890625,
"step": 648
},
{
"epoch": 4.669064748201439,
"grad_norm": 0.0516074076294899,
"learning_rate": 2.2151050325194206e-05,
"loss": 0.74658203125,
"step": 649
},
{
"epoch": 4.676258992805756,
"grad_norm": 0.05186400189995766,
"learning_rate": 2.2060837274829196e-05,
"loss": 0.71337890625,
"step": 650
},
{
"epoch": 4.683453237410072,
"grad_norm": 0.04709075763821602,
"learning_rate": 2.197253478803367e-05,
"loss": 0.640472412109375,
"step": 651
},
{
"epoch": 4.690647482014389,
"grad_norm": 0.05202441290020943,
"learning_rate": 2.1886144783264733e-05,
"loss": 0.740234375,
"step": 652
},
{
"epoch": 4.697841726618705,
"grad_norm": 0.052339646965265274,
"learning_rate": 2.1801669137429016e-05,
"loss": 0.71240234375,
"step": 653
},
{
"epoch": 4.705035971223022,
"grad_norm": 0.05486401915550232,
"learning_rate": 2.171910968584182e-05,
"loss": 0.755859375,
"step": 654
},
{
"epoch": 4.712230215827338,
"grad_norm": 0.04742782562971115,
"learning_rate": 2.1638468222187274e-05,
"loss": 0.669921875,
"step": 655
},
{
"epoch": 4.719424460431655,
"grad_norm": 0.052510373294353485,
"learning_rate": 2.1559746498479366e-05,
"loss": 0.76025390625,
"step": 656
},
{
"epoch": 4.726618705035971,
"grad_norm": 0.05129651352763176,
"learning_rate": 2.1482946225023853e-05,
"loss": 0.67919921875,
"step": 657
},
{
"epoch": 4.733812949640288,
"grad_norm": 0.05407492816448212,
"learning_rate": 2.1408069070381148e-05,
"loss": 0.74169921875,
"step": 658
},
{
"epoch": 4.741007194244604,
"grad_norm": 0.05486985296010971,
"learning_rate": 2.1335116661330022e-05,
"loss": 0.6787109375,
"step": 659
},
{
"epoch": 4.748201438848921,
"grad_norm": 0.054227206856012344,
"learning_rate": 2.1264090582832307e-05,
"loss": 0.75048828125,
"step": 660
},
{
"epoch": 4.755395683453237,
"grad_norm": 0.05136020481586456,
"learning_rate": 2.1194992377998408e-05,
"loss": 0.69775390625,
"step": 661
},
{
"epoch": 4.762589928057554,
"grad_norm": 0.050531502813100815,
"learning_rate": 2.1127823548053814e-05,
"loss": 0.666015625,
"step": 662
},
{
"epoch": 4.76978417266187,
"grad_norm": 0.05272015929222107,
"learning_rate": 2.1062585552306478e-05,
"loss": 0.75439453125,
"step": 663
},
{
"epoch": 4.7769784172661875,
"grad_norm": 0.05362412706017494,
"learning_rate": 2.0999279808115117e-05,
"loss": 0.7568359375,
"step": 664
},
{
"epoch": 4.784172661870503,
"grad_norm": 0.05568424612283707,
"learning_rate": 2.0937907690858392e-05,
"loss": 0.75634765625,
"step": 665
},
{
"epoch": 4.7913669064748206,
"grad_norm": 0.055312927812337875,
"learning_rate": 2.0878470533905058e-05,
"loss": 0.7333984375,
"step": 666
},
{
"epoch": 4.798561151079137,
"grad_norm": 0.07465150207281113,
"learning_rate": 2.082096962858497e-05,
"loss": 0.6962890625,
"step": 667
},
{
"epoch": 4.805755395683454,
"grad_norm": 0.05409865081310272,
"learning_rate": 2.0765406224161048e-05,
"loss": 0.72607421875,
"step": 668
},
{
"epoch": 4.81294964028777,
"grad_norm": 0.054045382887125015,
"learning_rate": 2.0711781527802125e-05,
"loss": 0.7607421875,
"step": 669
},
{
"epoch": 4.820143884892087,
"grad_norm": 0.05289534479379654,
"learning_rate": 2.066009670455671e-05,
"loss": 0.72998046875,
"step": 670
},
{
"epoch": 4.827338129496403,
"grad_norm": 0.05547667667269707,
"learning_rate": 2.061035287732771e-05,
"loss": 0.70654296875,
"step": 671
},
{
"epoch": 4.83453237410072,
"grad_norm": 0.05358997732400894,
"learning_rate": 2.0562551126847996e-05,
"loss": 0.7783203125,
"step": 672
},
{
"epoch": 4.841726618705036,
"grad_norm": 0.0539671815931797,
"learning_rate": 2.0516692491656935e-05,
"loss": 0.76513671875,
"step": 673
},
{
"epoch": 4.848920863309353,
"grad_norm": 0.047293100506067276,
"learning_rate": 2.0472777968077844e-05,
"loss": 0.6424713134765625,
"step": 674
},
{
"epoch": 4.856115107913669,
"grad_norm": 0.05361802130937576,
"learning_rate": 2.0430808510196333e-05,
"loss": 0.63623046875,
"step": 675
},
{
"epoch": 4.863309352517986,
"grad_norm": 0.0557270348072052,
"learning_rate": 2.0390785029839545e-05,
"loss": 0.70458984375,
"step": 676
},
{
"epoch": 4.870503597122302,
"grad_norm": 0.05307677015662193,
"learning_rate": 2.0352708396556405e-05,
"loss": 0.7236328125,
"step": 677
},
{
"epoch": 4.877697841726619,
"grad_norm": 0.05302033945918083,
"learning_rate": 2.0316579437598695e-05,
"loss": 0.7275390625,
"step": 678
},
{
"epoch": 4.884892086330935,
"grad_norm": 0.05203063786029816,
"learning_rate": 2.0282398937903064e-05,
"loss": 0.718505859375,
"step": 679
},
{
"epoch": 4.892086330935252,
"grad_norm": 0.05210476368665695,
"learning_rate": 2.0250167640074004e-05,
"loss": 0.7626953125,
"step": 680
},
{
"epoch": 4.899280575539568,
"grad_norm": 0.05047106742858887,
"learning_rate": 2.021988624436772e-05,
"loss": 0.75390625,
"step": 681
},
{
"epoch": 4.906474820143885,
"grad_norm": 0.05173734202980995,
"learning_rate": 2.0191555408676892e-05,
"loss": 0.6614990234375,
"step": 682
},
{
"epoch": 4.913669064748201,
"grad_norm": 0.045575015246868134,
"learning_rate": 2.0165175748516395e-05,
"loss": 0.596954345703125,
"step": 683
},
{
"epoch": 4.920863309352518,
"grad_norm": 0.054150424897670746,
"learning_rate": 2.014074783700991e-05,
"loss": 0.703125,
"step": 684
},
{
"epoch": 4.928057553956835,
"grad_norm": 0.05526477098464966,
"learning_rate": 2.0118272204877504e-05,
"loss": 0.70068359375,
"step": 685
},
{
"epoch": 4.935251798561151,
"grad_norm": 0.054716844111680984,
"learning_rate": 2.009774934042407e-05,
"loss": 0.708740234375,
"step": 686
},
{
"epoch": 4.942446043165468,
"grad_norm": 0.0508871003985405,
"learning_rate": 2.0079179689528758e-05,
"loss": 0.68701171875,
"step": 687
},
{
"epoch": 4.9496402877697845,
"grad_norm": 0.053397320210933685,
"learning_rate": 2.0062563655635206e-05,
"loss": 0.69873046875,
"step": 688
},
{
"epoch": 4.956834532374101,
"grad_norm": 0.055672161281108856,
"learning_rate": 2.0047901599742886e-05,
"loss": 0.69775390625,
"step": 689
},
{
"epoch": 4.9640287769784175,
"grad_norm": 0.052525658160448074,
"learning_rate": 2.0035193840399153e-05,
"loss": 0.7001953125,
"step": 690
},
{
"epoch": 4.971223021582734,
"grad_norm": 0.0548984594643116,
"learning_rate": 2.0024440653692426e-05,
"loss": 0.716796875,
"step": 691
},
{
"epoch": 4.9784172661870505,
"grad_norm": 0.05292995646595955,
"learning_rate": 2.00156422732461e-05,
"loss": 0.76904296875,
"step": 692
},
{
"epoch": 4.985611510791367,
"grad_norm": 0.05397019162774086,
"learning_rate": 2.0008798890213506e-05,
"loss": 0.7373046875,
"step": 693
},
{
"epoch": 4.9928057553956835,
"grad_norm": 0.05884130671620369,
"learning_rate": 2.00039106532738e-05,
"loss": 0.73876953125,
"step": 694
},
{
"epoch": 5.0,
"grad_norm": 0.06566242128610611,
"learning_rate": 2.0000977668628646e-05,
"loss": 0.580322265625,
"step": 695
},
{
"epoch": 5.0,
"eval_loss": 0.822265625,
"eval_runtime": 2.161,
"eval_samples_per_second": 3.239,
"eval_steps_per_second": 0.463,
"step": 695
}
],
"logging_steps": 1.0,
"max_steps": 695,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.095561060526588e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}