akhilfau's picture
Upload folder using huggingface_hub
0c410d4 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.0,
"eval_steps": 500,
"global_step": 32000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.025,
"grad_norm": 0.20501533150672913,
"learning_rate": 0.000499987952239832,
"loss": 1.3493,
"step": 100
},
{
"epoch": 0.05,
"grad_norm": 0.17424988746643066,
"learning_rate": 0.0004999518101205162,
"loss": 1.1647,
"step": 200
},
{
"epoch": 0.075,
"grad_norm": 0.24931852519512177,
"learning_rate": 0.0004998915771255053,
"loss": 1.1393,
"step": 300
},
{
"epoch": 0.1,
"grad_norm": 0.2063228040933609,
"learning_rate": 0.0004998072590601808,
"loss": 1.1057,
"step": 400
},
{
"epoch": 0.125,
"grad_norm": 0.23096567392349243,
"learning_rate": 0.0004996988640512931,
"loss": 1.1329,
"step": 500
},
{
"epoch": 0.15,
"grad_norm": 0.19355718791484833,
"learning_rate": 0.000499566402546179,
"loss": 1.1168,
"step": 600
},
{
"epoch": 0.175,
"grad_norm": 0.2221299558877945,
"learning_rate": 0.0004994098873117539,
"loss": 1.1316,
"step": 700
},
{
"epoch": 0.2,
"grad_norm": 0.2073143720626831,
"learning_rate": 0.000499229333433282,
"loss": 1.1141,
"step": 800
},
{
"epoch": 0.225,
"grad_norm": 0.21791169047355652,
"learning_rate": 0.0004990247583129218,
"loss": 1.1274,
"step": 900
},
{
"epoch": 0.25,
"grad_norm": 0.21467778086662292,
"learning_rate": 0.0004987961816680492,
"loss": 1.0698,
"step": 1000
},
{
"epoch": 0.275,
"grad_norm": 0.2048187404870987,
"learning_rate": 0.0004985436255293571,
"loss": 1.0928,
"step": 1100
},
{
"epoch": 0.3,
"grad_norm": 0.21932852268218994,
"learning_rate": 0.0004982671142387316,
"loss": 1.0906,
"step": 1200
},
{
"epoch": 0.325,
"grad_norm": 0.2301362156867981,
"learning_rate": 0.0004979666744469065,
"loss": 1.0949,
"step": 1300
},
{
"epoch": 0.35,
"grad_norm": 0.2186669409275055,
"learning_rate": 0.0004976423351108943,
"loss": 1.0857,
"step": 1400
},
{
"epoch": 0.375,
"grad_norm": 0.19886991381645203,
"learning_rate": 0.0004972941274911952,
"loss": 1.0642,
"step": 1500
},
{
"epoch": 0.4,
"grad_norm": 0.23275479674339294,
"learning_rate": 0.0004969220851487844,
"loss": 1.0718,
"step": 1600
},
{
"epoch": 0.425,
"grad_norm": 0.21335655450820923,
"learning_rate": 0.0004965262439418772,
"loss": 1.082,
"step": 1700
},
{
"epoch": 0.45,
"grad_norm": 0.2357306331396103,
"learning_rate": 0.0004961066420224729,
"loss": 1.0937,
"step": 1800
},
{
"epoch": 0.475,
"grad_norm": 0.23492847383022308,
"learning_rate": 0.000495663319832678,
"loss": 1.0846,
"step": 1900
},
{
"epoch": 0.5,
"grad_norm": 0.2015356421470642,
"learning_rate": 0.0004951963201008077,
"loss": 1.0829,
"step": 2000
},
{
"epoch": 0.525,
"grad_norm": 0.24353289604187012,
"learning_rate": 0.0004947056878372681,
"loss": 1.0688,
"step": 2100
},
{
"epoch": 0.55,
"grad_norm": 0.27955085039138794,
"learning_rate": 0.0004941914703302181,
"loss": 1.0644,
"step": 2200
},
{
"epoch": 0.575,
"grad_norm": 0.24444086849689484,
"learning_rate": 0.0004936537171410112,
"loss": 1.0946,
"step": 2300
},
{
"epoch": 0.6,
"grad_norm": 0.22312547266483307,
"learning_rate": 0.0004930924800994192,
"loss": 1.0636,
"step": 2400
},
{
"epoch": 0.625,
"grad_norm": 0.22395829856395721,
"learning_rate": 0.000492507813298636,
"loss": 1.0858,
"step": 2500
},
{
"epoch": 0.65,
"grad_norm": 0.2249772697687149,
"learning_rate": 0.0004918997730900649,
"loss": 1.0885,
"step": 2600
},
{
"epoch": 0.675,
"grad_norm": 0.22566111385822296,
"learning_rate": 0.0004912684180778869,
"loss": 1.0647,
"step": 2700
},
{
"epoch": 0.7,
"grad_norm": 0.256917804479599,
"learning_rate": 0.0004906138091134118,
"loss": 1.0484,
"step": 2800
},
{
"epoch": 0.725,
"grad_norm": 0.2598745822906494,
"learning_rate": 0.0004899360092892143,
"loss": 1.063,
"step": 2900
},
{
"epoch": 0.75,
"grad_norm": 0.2576007843017578,
"learning_rate": 0.0004892350839330522,
"loss": 1.0585,
"step": 3000
},
{
"epoch": 0.775,
"grad_norm": 0.2577688992023468,
"learning_rate": 0.0004885111006015701,
"loss": 1.0452,
"step": 3100
},
{
"epoch": 0.8,
"grad_norm": 0.2334214746952057,
"learning_rate": 0.0004877641290737884,
"loss": 1.0473,
"step": 3200
},
{
"epoch": 0.825,
"grad_norm": 0.2869343161582947,
"learning_rate": 0.0004869942413443776,
"loss": 1.0412,
"step": 3300
},
{
"epoch": 0.85,
"grad_norm": 0.26476991176605225,
"learning_rate": 0.00048620151161671955,
"loss": 1.064,
"step": 3400
},
{
"epoch": 0.875,
"grad_norm": 0.2549433708190918,
"learning_rate": 0.0004853860162957552,
"loss": 1.0557,
"step": 3500
},
{
"epoch": 0.9,
"grad_norm": 0.26020538806915283,
"learning_rate": 0.0004845478339806211,
"loss": 1.0424,
"step": 3600
},
{
"epoch": 0.925,
"grad_norm": 0.2770324945449829,
"learning_rate": 0.0004836870454570731,
"loss": 1.0552,
"step": 3700
},
{
"epoch": 0.95,
"grad_norm": 0.2561758756637573,
"learning_rate": 0.00048280373368970086,
"loss": 1.0336,
"step": 3800
},
{
"epoch": 0.975,
"grad_norm": 0.25469744205474854,
"learning_rate": 0.000481897983813931,
"loss": 1.06,
"step": 3900
},
{
"epoch": 1.0,
"grad_norm": 0.2685888707637787,
"learning_rate": 0.0004809698831278217,
"loss": 1.0151,
"step": 4000
},
{
"epoch": 1.0,
"eval_loss": 1.0406872034072876,
"eval_runtime": 152.4194,
"eval_samples_per_second": 26.243,
"eval_steps_per_second": 6.561,
"step": 4000
},
{
"epoch": 1.025,
"grad_norm": 0.28361451625823975,
"learning_rate": 0.00048001952108364876,
"loss": 1.0277,
"step": 4100
},
{
"epoch": 1.05,
"grad_norm": 0.26193392276763916,
"learning_rate": 0.00047904698927928404,
"loss": 1.0187,
"step": 4200
},
{
"epoch": 1.075,
"grad_norm": 0.2700245678424835,
"learning_rate": 0.0004780523814493669,
"loss": 1.0325,
"step": 4300
},
{
"epoch": 1.1,
"grad_norm": 0.2610750198364258,
"learning_rate": 0.00047703579345627036,
"loss": 1.0182,
"step": 4400
},
{
"epoch": 1.125,
"grad_norm": 0.2965630888938904,
"learning_rate": 0.0004759973232808609,
"loss": 1.0105,
"step": 4500
},
{
"epoch": 1.15,
"grad_norm": 0.25167468190193176,
"learning_rate": 0.0004749370710130554,
"loss": 1.0404,
"step": 4600
},
{
"epoch": 1.175,
"grad_norm": 0.26605212688446045,
"learning_rate": 0.0004738551388421742,
"loss": 1.0291,
"step": 4700
},
{
"epoch": 1.2,
"grad_norm": 0.25520554184913635,
"learning_rate": 0.00047275163104709196,
"loss": 1.019,
"step": 4800
},
{
"epoch": 1.225,
"grad_norm": 0.26057741045951843,
"learning_rate": 0.00047162665398618666,
"loss": 1.0309,
"step": 4900
},
{
"epoch": 1.25,
"grad_norm": 0.2987058758735657,
"learning_rate": 0.00047048031608708875,
"loss": 1.0127,
"step": 5000
},
{
"epoch": 1.275,
"grad_norm": 0.2619779706001282,
"learning_rate": 0.00046931272783623106,
"loss": 1.0191,
"step": 5100
},
{
"epoch": 1.3,
"grad_norm": 0.27090466022491455,
"learning_rate": 0.0004681240017681993,
"loss": 1.0416,
"step": 5200
},
{
"epoch": 1.325,
"grad_norm": 0.24344772100448608,
"learning_rate": 0.00046691425245488607,
"loss": 1.0075,
"step": 5300
},
{
"epoch": 1.35,
"grad_norm": 0.2597128450870514,
"learning_rate": 0.00046568359649444796,
"loss": 1.0147,
"step": 5400
},
{
"epoch": 1.375,
"grad_norm": 0.3321911692619324,
"learning_rate": 0.00046443215250006805,
"loss": 1.0277,
"step": 5500
},
{
"epoch": 1.4,
"grad_norm": 0.2736588716506958,
"learning_rate": 0.00046316004108852305,
"loss": 1.041,
"step": 5600
},
{
"epoch": 1.425,
"grad_norm": 0.30011600255966187,
"learning_rate": 0.0004618673848685586,
"loss": 1.006,
"step": 5700
},
{
"epoch": 1.45,
"grad_norm": 0.27296823263168335,
"learning_rate": 0.0004605543084290716,
"loss": 1.0207,
"step": 5800
},
{
"epoch": 1.475,
"grad_norm": 0.2965295910835266,
"learning_rate": 0.0004592209383271023,
"loss": 1.0306,
"step": 5900
},
{
"epoch": 1.5,
"grad_norm": 0.27299028635025024,
"learning_rate": 0.00045786740307563633,
"loss": 1.0296,
"step": 6000
},
{
"epoch": 1.525,
"grad_norm": 0.2956341803073883,
"learning_rate": 0.0004564938331312183,
"loss": 0.9965,
"step": 6100
},
{
"epoch": 1.55,
"grad_norm": 0.2554098665714264,
"learning_rate": 0.0004551003608813784,
"loss": 1.0232,
"step": 6200
},
{
"epoch": 1.575,
"grad_norm": 0.2712690234184265,
"learning_rate": 0.00045368712063187237,
"loss": 1.02,
"step": 6300
},
{
"epoch": 1.6,
"grad_norm": 0.31331920623779297,
"learning_rate": 0.0004522542485937369,
"loss": 0.971,
"step": 6400
},
{
"epoch": 1.625,
"grad_norm": 0.3378168046474457,
"learning_rate": 0.0004508018828701612,
"loss": 1.0017,
"step": 6500
},
{
"epoch": 1.65,
"grad_norm": 0.3126436471939087,
"learning_rate": 0.0004493301634431768,
"loss": 0.9969,
"step": 6600
},
{
"epoch": 1.675,
"grad_norm": 0.2890426218509674,
"learning_rate": 0.00044783923216016507,
"loss": 1.0082,
"step": 6700
},
{
"epoch": 1.7,
"grad_norm": 0.3303642272949219,
"learning_rate": 0.0004463292327201862,
"loss": 0.9989,
"step": 6800
},
{
"epoch": 1.725,
"grad_norm": 0.3025239408016205,
"learning_rate": 0.00044480031066012916,
"loss": 1.0305,
"step": 6900
},
{
"epoch": 1.75,
"grad_norm": 0.2934839725494385,
"learning_rate": 0.0004432526133406842,
"loss": 1.0003,
"step": 7000
},
{
"epoch": 1.775,
"grad_norm": 0.31030675768852234,
"learning_rate": 0.00044168628993214036,
"loss": 0.982,
"step": 7100
},
{
"epoch": 1.8,
"grad_norm": 0.30027347803115845,
"learning_rate": 0.0004401014914000078,
"loss": 0.9825,
"step": 7200
},
{
"epoch": 1.825,
"grad_norm": 0.2832087278366089,
"learning_rate": 0.00043849837049046735,
"loss": 1.007,
"step": 7300
},
{
"epoch": 1.85,
"grad_norm": 0.30503541231155396,
"learning_rate": 0.00043687708171564923,
"loss": 1.0023,
"step": 7400
},
{
"epoch": 1.875,
"grad_norm": 0.30458569526672363,
"learning_rate": 0.0004352377813387398,
"loss": 1.0006,
"step": 7500
},
{
"epoch": 1.9,
"grad_norm": 0.3471212089061737,
"learning_rate": 0.0004335806273589214,
"loss": 1.0239,
"step": 7600
},
{
"epoch": 1.925,
"grad_norm": 0.29310837388038635,
"learning_rate": 0.00043190577949614375,
"loss": 1.0129,
"step": 7700
},
{
"epoch": 1.95,
"grad_norm": 0.294300377368927,
"learning_rate": 0.0004302133991757297,
"loss": 0.9956,
"step": 7800
},
{
"epoch": 1.975,
"grad_norm": 0.3151143193244934,
"learning_rate": 0.00042850364951281707,
"loss": 1.0224,
"step": 7900
},
{
"epoch": 2.0,
"grad_norm": 0.3241264820098877,
"learning_rate": 0.00042677669529663686,
"loss": 1.0234,
"step": 8000
},
{
"epoch": 2.0,
"eval_loss": 1.0086950063705444,
"eval_runtime": 152.329,
"eval_samples_per_second": 26.259,
"eval_steps_per_second": 6.565,
"step": 8000
},
{
"epoch": 2.025,
"grad_norm": 0.3218720853328705,
"learning_rate": 0.0004250327029746309,
"loss": 1.0029,
"step": 8100
},
{
"epoch": 2.05,
"grad_norm": 0.31330084800720215,
"learning_rate": 0.000423271840636409,
"loss": 0.9844,
"step": 8200
},
{
"epoch": 2.075,
"grad_norm": 0.30206719040870667,
"learning_rate": 0.00042149427799754817,
"loss": 0.989,
"step": 8300
},
{
"epoch": 2.1,
"grad_norm": 0.303648978471756,
"learning_rate": 0.00041970018638323546,
"loss": 0.9543,
"step": 8400
},
{
"epoch": 2.125,
"grad_norm": 0.317037433385849,
"learning_rate": 0.00041788973871175465,
"loss": 0.9945,
"step": 8500
},
{
"epoch": 2.15,
"grad_norm": 0.3210434913635254,
"learning_rate": 0.00041606310947782046,
"loss": 0.988,
"step": 8600
},
{
"epoch": 2.175,
"grad_norm": 0.33763307332992554,
"learning_rate": 0.00041422047473576033,
"loss": 1.0066,
"step": 8700
},
{
"epoch": 2.2,
"grad_norm": 0.30534419417381287,
"learning_rate": 0.0004123620120825459,
"loss": 1.0033,
"step": 8800
},
{
"epoch": 2.225,
"grad_norm": 0.3363495171070099,
"learning_rate": 0.00041048790064067577,
"loss": 0.993,
"step": 8900
},
{
"epoch": 2.25,
"grad_norm": 0.2920531928539276,
"learning_rate": 0.0004085983210409114,
"loss": 0.9844,
"step": 9000
},
{
"epoch": 2.275,
"grad_norm": 0.33446577191352844,
"learning_rate": 0.0004066934554048674,
"loss": 0.9846,
"step": 9100
},
{
"epoch": 2.3,
"grad_norm": 0.33012858033180237,
"learning_rate": 0.00040477348732745853,
"loss": 0.9858,
"step": 9200
},
{
"epoch": 2.325,
"grad_norm": 0.3301050364971161,
"learning_rate": 0.0004028386018592041,
"loss": 0.9787,
"step": 9300
},
{
"epoch": 2.35,
"grad_norm": 0.3368571400642395,
"learning_rate": 0.0004008889854883929,
"loss": 0.9912,
"step": 9400
},
{
"epoch": 2.375,
"grad_norm": 0.285281777381897,
"learning_rate": 0.0003989248261231084,
"loss": 0.9655,
"step": 9500
},
{
"epoch": 2.4,
"grad_norm": 0.36711010336875916,
"learning_rate": 0.0003969463130731183,
"loss": 0.9753,
"step": 9600
},
{
"epoch": 2.425,
"grad_norm": 0.28881680965423584,
"learning_rate": 0.00039495363703162843,
"loss": 0.978,
"step": 9700
},
{
"epoch": 2.45,
"grad_norm": 0.3270690441131592,
"learning_rate": 0.000392946990056903,
"loss": 1.0242,
"step": 9800
},
{
"epoch": 2.475,
"grad_norm": 0.3338991105556488,
"learning_rate": 0.00039092656555375416,
"loss": 1.0066,
"step": 9900
},
{
"epoch": 2.5,
"grad_norm": 0.34082475304603577,
"learning_rate": 0.00038889255825490053,
"loss": 0.9781,
"step": 10000
},
{
"epoch": 2.525,
"grad_norm": 0.34000107645988464,
"learning_rate": 0.0003868451642021992,
"loss": 0.9745,
"step": 10100
},
{
"epoch": 2.55,
"grad_norm": 0.3570154309272766,
"learning_rate": 0.0003847845807277501,
"loss": 0.9759,
"step": 10200
},
{
"epoch": 2.575,
"grad_norm": 0.33699771761894226,
"learning_rate": 0.0003827110064348773,
"loss": 0.9882,
"step": 10300
},
{
"epoch": 2.6,
"grad_norm": 0.29268336296081543,
"learning_rate": 0.0003806246411789872,
"loss": 0.9745,
"step": 10400
},
{
"epoch": 2.625,
"grad_norm": 0.3088798224925995,
"learning_rate": 0.0003785256860483054,
"loss": 0.9501,
"step": 10500
},
{
"epoch": 2.65,
"grad_norm": 0.34749528765678406,
"learning_rate": 0.0003764143433444962,
"loss": 0.9702,
"step": 10600
},
{
"epoch": 2.675,
"grad_norm": 0.33005061745643616,
"learning_rate": 0.0003742908165631636,
"loss": 0.987,
"step": 10700
},
{
"epoch": 2.7,
"grad_norm": 0.3165997266769409,
"learning_rate": 0.0003721553103742388,
"loss": 1.0125,
"step": 10800
},
{
"epoch": 2.725,
"grad_norm": 0.3213465213775635,
"learning_rate": 0.0003700080306022528,
"loss": 0.9613,
"step": 10900
},
{
"epoch": 2.75,
"grad_norm": 0.33442971110343933,
"learning_rate": 0.0003678491842064995,
"loss": 0.9825,
"step": 11000
},
{
"epoch": 2.775,
"grad_norm": 0.2766638994216919,
"learning_rate": 0.00036567897926108756,
"loss": 0.9473,
"step": 11100
},
{
"epoch": 2.8,
"grad_norm": 0.3419225215911865,
"learning_rate": 0.00036349762493488667,
"loss": 0.9462,
"step": 11200
},
{
"epoch": 2.825,
"grad_norm": 0.3595256209373474,
"learning_rate": 0.0003613053314713671,
"loss": 0.9879,
"step": 11300
},
{
"epoch": 2.85,
"grad_norm": 0.3483733534812927,
"learning_rate": 0.0003591023101683355,
"loss": 0.9997,
"step": 11400
},
{
"epoch": 2.875,
"grad_norm": 0.32273510098457336,
"learning_rate": 0.0003568887733575705,
"loss": 1.0057,
"step": 11500
},
{
"epoch": 2.9,
"grad_norm": 0.31241312623023987,
"learning_rate": 0.00035466493438435703,
"loss": 0.9675,
"step": 11600
},
{
"epoch": 2.925,
"grad_norm": 0.37985849380493164,
"learning_rate": 0.0003524310075869239,
"loss": 0.9927,
"step": 11700
},
{
"epoch": 2.95,
"grad_norm": 0.33704909682273865,
"learning_rate": 0.0003501872082757852,
"loss": 0.9779,
"step": 11800
},
{
"epoch": 2.975,
"grad_norm": 0.4041268229484558,
"learning_rate": 0.000347933752712989,
"loss": 0.9739,
"step": 11900
},
{
"epoch": 3.0,
"grad_norm": 0.3415277302265167,
"learning_rate": 0.0003456708580912725,
"loss": 0.9995,
"step": 12000
},
{
"epoch": 3.0,
"eval_loss": 0.9921265244483948,
"eval_runtime": 153.1095,
"eval_samples_per_second": 26.125,
"eval_steps_per_second": 6.531,
"step": 12000
},
{
"epoch": 3.025,
"grad_norm": 0.3260078430175781,
"learning_rate": 0.0003433987425131291,
"loss": 0.969,
"step": 12100
},
{
"epoch": 3.05,
"grad_norm": 0.3035444915294647,
"learning_rate": 0.0003411176249697875,
"loss": 0.9636,
"step": 12200
},
{
"epoch": 3.075,
"grad_norm": 0.3195238411426544,
"learning_rate": 0.00033882772532010404,
"loss": 0.9522,
"step": 12300
},
{
"epoch": 3.1,
"grad_norm": 0.33937081694602966,
"learning_rate": 0.0003365292642693733,
"loss": 0.9425,
"step": 12400
},
{
"epoch": 3.125,
"grad_norm": 0.37307849526405334,
"learning_rate": 0.00033422246334805503,
"loss": 0.9683,
"step": 12500
},
{
"epoch": 3.15,
"grad_norm": 0.3180018365383148,
"learning_rate": 0.0003319075448904234,
"loss": 0.9761,
"step": 12600
},
{
"epoch": 3.175,
"grad_norm": 0.3785949647426605,
"learning_rate": 0.00032958473201313745,
"loss": 0.9748,
"step": 12700
},
{
"epoch": 3.2,
"grad_norm": 0.3146439790725708,
"learning_rate": 0.00032725424859373687,
"loss": 0.9657,
"step": 12800
},
{
"epoch": 3.225,
"grad_norm": 0.3667052686214447,
"learning_rate": 0.00032491631924906416,
"loss": 0.9685,
"step": 12900
},
{
"epoch": 3.25,
"grad_norm": 0.34998300671577454,
"learning_rate": 0.00032257116931361555,
"loss": 0.9821,
"step": 13000
},
{
"epoch": 3.275,
"grad_norm": 0.34160691499710083,
"learning_rate": 0.00032021902481782304,
"loss": 0.9536,
"step": 13100
},
{
"epoch": 3.3,
"grad_norm": 0.35554495453834534,
"learning_rate": 0.00031786011246626855,
"loss": 0.9626,
"step": 13200
},
{
"epoch": 3.325,
"grad_norm": 0.373349666595459,
"learning_rate": 0.0003154946596158343,
"loss": 0.9926,
"step": 13300
},
{
"epoch": 3.35,
"grad_norm": 0.38320091366767883,
"learning_rate": 0.0003131228942537895,
"loss": 0.9787,
"step": 13400
},
{
"epoch": 3.375,
"grad_norm": 0.3836865723133087,
"learning_rate": 0.000310745044975816,
"loss": 0.9583,
"step": 13500
},
{
"epoch": 3.4,
"grad_norm": 0.3358447551727295,
"learning_rate": 0.0003083613409639764,
"loss": 0.953,
"step": 13600
},
{
"epoch": 3.425,
"grad_norm": 0.3501192629337311,
"learning_rate": 0.00030597201196462466,
"loss": 0.9346,
"step": 13700
},
{
"epoch": 3.45,
"grad_norm": 0.3595263957977295,
"learning_rate": 0.00030357728826626266,
"loss": 0.9656,
"step": 13800
},
{
"epoch": 3.475,
"grad_norm": 0.3395259380340576,
"learning_rate": 0.00030117740067734495,
"loss": 0.9835,
"step": 13900
},
{
"epoch": 3.5,
"grad_norm": 0.36751946806907654,
"learning_rate": 0.0002987725805040321,
"loss": 0.9465,
"step": 14000
},
{
"epoch": 3.525,
"grad_norm": 0.348893404006958,
"learning_rate": 0.0002963630595278977,
"loss": 0.9564,
"step": 14100
},
{
"epoch": 3.55,
"grad_norm": 0.39346957206726074,
"learning_rate": 0.0002939490699835887,
"loss": 0.9508,
"step": 14200
},
{
"epoch": 3.575,
"grad_norm": 0.33249151706695557,
"learning_rate": 0.00029153084453644135,
"loss": 0.9757,
"step": 14300
},
{
"epoch": 3.6,
"grad_norm": 0.3582550585269928,
"learning_rate": 0.00028910861626005774,
"loss": 0.9552,
"step": 14400
},
{
"epoch": 3.625,
"grad_norm": 0.3562643229961395,
"learning_rate": 0.00028668261861384045,
"loss": 0.95,
"step": 14500
},
{
"epoch": 3.65,
"grad_norm": 0.3955428898334503,
"learning_rate": 0.00028425308542049207,
"loss": 0.9699,
"step": 14600
},
{
"epoch": 3.675,
"grad_norm": 0.38744592666625977,
"learning_rate": 0.0002818202508434783,
"loss": 0.9838,
"step": 14700
},
{
"epoch": 3.7,
"grad_norm": 0.404632031917572,
"learning_rate": 0.00027938434936445943,
"loss": 0.9589,
"step": 14800
},
{
"epoch": 3.725,
"grad_norm": 0.36033356189727783,
"learning_rate": 0.00027694561576068985,
"loss": 0.973,
"step": 14900
},
{
"epoch": 3.75,
"grad_norm": 0.3457838296890259,
"learning_rate": 0.0002745042850823902,
"loss": 0.9801,
"step": 15000
},
{
"epoch": 3.775,
"grad_norm": 0.35734304785728455,
"learning_rate": 0.00027206059263009243,
"loss": 0.9469,
"step": 15100
},
{
"epoch": 3.8,
"grad_norm": 0.3542312681674957,
"learning_rate": 0.00026961477393196127,
"loss": 0.9336,
"step": 15200
},
{
"epoch": 3.825,
"grad_norm": 0.3671669065952301,
"learning_rate": 0.0002671670647210934,
"loss": 0.9793,
"step": 15300
},
{
"epoch": 3.85,
"grad_norm": 0.357881098985672,
"learning_rate": 0.00026471770091279724,
"loss": 0.9544,
"step": 15400
},
{
"epoch": 3.875,
"grad_norm": 0.31071895360946655,
"learning_rate": 0.00026226691858185456,
"loss": 0.9656,
"step": 15500
},
{
"epoch": 3.9,
"grad_norm": 0.34388652443885803,
"learning_rate": 0.00025981495393976716,
"loss": 0.96,
"step": 15600
},
{
"epoch": 3.925,
"grad_norm": 0.3791946768760681,
"learning_rate": 0.00025736204331199084,
"loss": 0.9797,
"step": 15700
},
{
"epoch": 3.95,
"grad_norm": 0.3630838096141815,
"learning_rate": 0.00025490842311515704,
"loss": 0.9592,
"step": 15800
},
{
"epoch": 3.975,
"grad_norm": 0.3712921440601349,
"learning_rate": 0.0002524543298342875,
"loss": 0.9731,
"step": 15900
},
{
"epoch": 4.0,
"grad_norm": 0.4159054756164551,
"learning_rate": 0.00025,
"loss": 0.9528,
"step": 16000
},
{
"epoch": 4.0,
"eval_loss": 0.9823833107948303,
"eval_runtime": 152.8782,
"eval_samples_per_second": 26.165,
"eval_steps_per_second": 6.541,
"step": 16000
},
{
"epoch": 4.025,
"grad_norm": 0.39106351137161255,
"learning_rate": 0.0002475456701657126,
"loss": 0.9814,
"step": 16100
},
{
"epoch": 4.05,
"grad_norm": 0.36192214488983154,
"learning_rate": 0.00024509157688484297,
"loss": 0.9369,
"step": 16200
},
{
"epoch": 4.075,
"grad_norm": 0.3404277563095093,
"learning_rate": 0.0002426379566880092,
"loss": 0.9501,
"step": 16300
},
{
"epoch": 4.1,
"grad_norm": 0.3791425824165344,
"learning_rate": 0.00024018504606023293,
"loss": 0.9336,
"step": 16400
},
{
"epoch": 4.125,
"grad_norm": 0.4009718894958496,
"learning_rate": 0.0002377330814181455,
"loss": 0.9487,
"step": 16500
},
{
"epoch": 4.15,
"grad_norm": 0.37880653142929077,
"learning_rate": 0.00023528229908720272,
"loss": 0.9542,
"step": 16600
},
{
"epoch": 4.175,
"grad_norm": 0.3936653733253479,
"learning_rate": 0.00023283293527890658,
"loss": 0.9388,
"step": 16700
},
{
"epoch": 4.2,
"grad_norm": 0.33316799998283386,
"learning_rate": 0.0002303852260680388,
"loss": 0.943,
"step": 16800
},
{
"epoch": 4.225,
"grad_norm": 0.3236179053783417,
"learning_rate": 0.00022793940736990766,
"loss": 0.9044,
"step": 16900
},
{
"epoch": 4.25,
"grad_norm": 0.3429449200630188,
"learning_rate": 0.00022549571491760985,
"loss": 0.9624,
"step": 17000
},
{
"epoch": 4.275,
"grad_norm": 0.35557985305786133,
"learning_rate": 0.00022305438423931017,
"loss": 0.9226,
"step": 17100
},
{
"epoch": 4.3,
"grad_norm": 1.0042773485183716,
"learning_rate": 0.00022061565063554063,
"loss": 0.9472,
"step": 17200
},
{
"epoch": 4.325,
"grad_norm": 0.3724925220012665,
"learning_rate": 0.00021817974915652172,
"loss": 0.947,
"step": 17300
},
{
"epoch": 4.35,
"grad_norm": 0.3926277756690979,
"learning_rate": 0.00021574691457950805,
"loss": 0.9478,
"step": 17400
},
{
"epoch": 4.375,
"grad_norm": 0.38053977489471436,
"learning_rate": 0.00021331738138615958,
"loss": 0.9801,
"step": 17500
},
{
"epoch": 4.4,
"grad_norm": 0.36115145683288574,
"learning_rate": 0.00021089138373994224,
"loss": 0.9619,
"step": 17600
},
{
"epoch": 4.425,
"grad_norm": 0.35729482769966125,
"learning_rate": 0.0002084691554635587,
"loss": 0.9549,
"step": 17700
},
{
"epoch": 4.45,
"grad_norm": 0.3762321174144745,
"learning_rate": 0.00020605093001641137,
"loss": 0.9359,
"step": 17800
},
{
"epoch": 4.475,
"grad_norm": 0.3317940831184387,
"learning_rate": 0.00020363694047210228,
"loss": 0.9571,
"step": 17900
},
{
"epoch": 4.5,
"grad_norm": 0.3733656406402588,
"learning_rate": 0.00020122741949596797,
"loss": 0.9409,
"step": 18000
},
{
"epoch": 4.525,
"grad_norm": 0.3790251612663269,
"learning_rate": 0.00019882259932265512,
"loss": 0.9768,
"step": 18100
},
{
"epoch": 4.55,
"grad_norm": 0.37900087237358093,
"learning_rate": 0.00019642271173373735,
"loss": 0.9208,
"step": 18200
},
{
"epoch": 4.575,
"grad_norm": 0.34171342849731445,
"learning_rate": 0.00019402798803537538,
"loss": 0.9831,
"step": 18300
},
{
"epoch": 4.6,
"grad_norm": 0.39172932505607605,
"learning_rate": 0.00019163865903602372,
"loss": 0.941,
"step": 18400
},
{
"epoch": 4.625,
"grad_norm": 0.36279597878456116,
"learning_rate": 0.00018925495502418406,
"loss": 0.9511,
"step": 18500
},
{
"epoch": 4.65,
"grad_norm": 0.35040661692619324,
"learning_rate": 0.00018687710574621051,
"loss": 0.9713,
"step": 18600
},
{
"epoch": 4.675,
"grad_norm": 0.35176095366477966,
"learning_rate": 0.00018450534038416566,
"loss": 0.9227,
"step": 18700
},
{
"epoch": 4.7,
"grad_norm": 0.41925740242004395,
"learning_rate": 0.00018213988753373146,
"loss": 0.9454,
"step": 18800
},
{
"epoch": 4.725,
"grad_norm": 0.4147469699382782,
"learning_rate": 0.00017978097518217702,
"loss": 0.9783,
"step": 18900
},
{
"epoch": 4.75,
"grad_norm": 0.364629864692688,
"learning_rate": 0.00017742883068638446,
"loss": 0.963,
"step": 19000
},
{
"epoch": 4.775,
"grad_norm": 0.39363783597946167,
"learning_rate": 0.00017508368075093582,
"loss": 0.9175,
"step": 19100
},
{
"epoch": 4.8,
"grad_norm": 0.39291703701019287,
"learning_rate": 0.00017274575140626317,
"loss": 0.9616,
"step": 19200
},
{
"epoch": 4.825,
"grad_norm": 0.3810083866119385,
"learning_rate": 0.0001704152679868626,
"loss": 0.9754,
"step": 19300
},
{
"epoch": 4.85,
"grad_norm": 0.36352667212486267,
"learning_rate": 0.00016809245510957666,
"loss": 0.953,
"step": 19400
},
{
"epoch": 4.875,
"grad_norm": 0.31296002864837646,
"learning_rate": 0.000165777536651945,
"loss": 0.9478,
"step": 19500
},
{
"epoch": 4.9,
"grad_norm": 0.4004424214363098,
"learning_rate": 0.0001634707357306267,
"loss": 0.9508,
"step": 19600
},
{
"epoch": 4.925,
"grad_norm": 0.3690031170845032,
"learning_rate": 0.00016117227467989602,
"loss": 0.9456,
"step": 19700
},
{
"epoch": 4.95,
"grad_norm": 0.3946553170681,
"learning_rate": 0.0001588823750302126,
"loss": 0.95,
"step": 19800
},
{
"epoch": 4.975,
"grad_norm": 0.39817288517951965,
"learning_rate": 0.00015660125748687094,
"loss": 0.9431,
"step": 19900
},
{
"epoch": 5.0,
"grad_norm": 0.37246620655059814,
"learning_rate": 0.00015432914190872756,
"loss": 0.9353,
"step": 20000
},
{
"epoch": 5.0,
"eval_loss": 0.9754775762557983,
"eval_runtime": 152.4185,
"eval_samples_per_second": 26.244,
"eval_steps_per_second": 6.561,
"step": 20000
},
{
"epoch": 5.025,
"grad_norm": 0.36520034074783325,
"learning_rate": 0.000152066247287011,
"loss": 0.9377,
"step": 20100
},
{
"epoch": 5.05,
"grad_norm": 0.3535405397415161,
"learning_rate": 0.00014981279172421482,
"loss": 0.9414,
"step": 20200
},
{
"epoch": 5.075,
"grad_norm": 0.35102036595344543,
"learning_rate": 0.00014756899241307614,
"loss": 0.9164,
"step": 20300
},
{
"epoch": 5.1,
"grad_norm": 0.3539367616176605,
"learning_rate": 0.00014533506561564306,
"loss": 0.9187,
"step": 20400
},
{
"epoch": 5.125,
"grad_norm": 0.347476601600647,
"learning_rate": 0.00014311122664242953,
"loss": 0.9196,
"step": 20500
},
{
"epoch": 5.15,
"grad_norm": 0.3902195990085602,
"learning_rate": 0.00014089768983166444,
"loss": 0.9301,
"step": 20600
},
{
"epoch": 5.175,
"grad_norm": 0.3888334631919861,
"learning_rate": 0.000138694668528633,
"loss": 0.9241,
"step": 20700
},
{
"epoch": 5.2,
"grad_norm": 0.41042113304138184,
"learning_rate": 0.00013650237506511331,
"loss": 0.9504,
"step": 20800
},
{
"epoch": 5.225,
"grad_norm": 0.3549586236476898,
"learning_rate": 0.0001343210207389125,
"loss": 0.955,
"step": 20900
},
{
"epoch": 5.25,
"grad_norm": 0.34020912647247314,
"learning_rate": 0.00013215081579350058,
"loss": 0.9471,
"step": 21000
},
{
"epoch": 5.275,
"grad_norm": 0.33093366026878357,
"learning_rate": 0.00012999196939774722,
"loss": 0.9351,
"step": 21100
},
{
"epoch": 5.3,
"grad_norm": 0.4015860855579376,
"learning_rate": 0.00012784468962576134,
"loss": 0.9491,
"step": 21200
},
{
"epoch": 5.325,
"grad_norm": 0.37603822350502014,
"learning_rate": 0.00012570918343683636,
"loss": 0.958,
"step": 21300
},
{
"epoch": 5.35,
"grad_norm": 0.39434927701950073,
"learning_rate": 0.0001235856566555039,
"loss": 0.94,
"step": 21400
},
{
"epoch": 5.375,
"grad_norm": 0.43162479996681213,
"learning_rate": 0.0001214743139516946,
"loss": 0.9291,
"step": 21500
},
{
"epoch": 5.4,
"grad_norm": 0.38297414779663086,
"learning_rate": 0.00011937535882101281,
"loss": 0.9494,
"step": 21600
},
{
"epoch": 5.425,
"grad_norm": 0.40226617455482483,
"learning_rate": 0.00011728899356512265,
"loss": 0.9067,
"step": 21700
},
{
"epoch": 5.45,
"grad_norm": 0.38879096508026123,
"learning_rate": 0.00011521541927224994,
"loss": 0.949,
"step": 21800
},
{
"epoch": 5.475,
"grad_norm": 0.33627960085868835,
"learning_rate": 0.00011315483579780094,
"loss": 0.9358,
"step": 21900
},
{
"epoch": 5.5,
"grad_norm": 0.4547683596611023,
"learning_rate": 0.00011110744174509952,
"loss": 0.9179,
"step": 22000
},
{
"epoch": 5.525,
"grad_norm": 0.3883083462715149,
"learning_rate": 0.00010907343444624579,
"loss": 0.9662,
"step": 22100
},
{
"epoch": 5.55,
"grad_norm": 0.4168870449066162,
"learning_rate": 0.00010705300994309697,
"loss": 0.9286,
"step": 22200
},
{
"epoch": 5.575,
"grad_norm": 0.3810732066631317,
"learning_rate": 0.00010504636296837161,
"loss": 0.9443,
"step": 22300
},
{
"epoch": 5.6,
"grad_norm": 0.40432223677635193,
"learning_rate": 0.00010305368692688174,
"loss": 0.9138,
"step": 22400
},
{
"epoch": 5.625,
"grad_norm": 0.3702322542667389,
"learning_rate": 0.00010107517387689166,
"loss": 0.9474,
"step": 22500
},
{
"epoch": 5.65,
"grad_norm": 0.40569931268692017,
"learning_rate": 9.911101451160715e-05,
"loss": 0.9645,
"step": 22600
},
{
"epoch": 5.675,
"grad_norm": 0.39476191997528076,
"learning_rate": 9.716139814079594e-05,
"loss": 0.9478,
"step": 22700
},
{
"epoch": 5.7,
"grad_norm": 0.347662091255188,
"learning_rate": 9.522651267254148e-05,
"loss": 0.9627,
"step": 22800
},
{
"epoch": 5.725,
"grad_norm": 0.36813852190971375,
"learning_rate": 9.330654459513265e-05,
"loss": 0.9328,
"step": 22900
},
{
"epoch": 5.75,
"grad_norm": 0.32601600885391235,
"learning_rate": 9.140167895908866e-05,
"loss": 0.9547,
"step": 23000
},
{
"epoch": 5.775,
"grad_norm": 0.40840694308280945,
"learning_rate": 8.951209935932425e-05,
"loss": 0.9113,
"step": 23100
},
{
"epoch": 5.8,
"grad_norm": 0.38472625613212585,
"learning_rate": 8.763798791745412e-05,
"loss": 0.9667,
"step": 23200
},
{
"epoch": 5.825,
"grad_norm": 0.37892642617225647,
"learning_rate": 8.577952526423969e-05,
"loss": 0.9241,
"step": 23300
},
{
"epoch": 5.85,
"grad_norm": 0.3874419927597046,
"learning_rate": 8.393689052217964e-05,
"loss": 0.9539,
"step": 23400
},
{
"epoch": 5.875,
"grad_norm": 0.37583285570144653,
"learning_rate": 8.211026128824539e-05,
"loss": 0.9411,
"step": 23500
},
{
"epoch": 5.9,
"grad_norm": 0.37817347049713135,
"learning_rate": 8.029981361676455e-05,
"loss": 0.9426,
"step": 23600
},
{
"epoch": 5.925,
"grad_norm": 0.32163432240486145,
"learning_rate": 7.850572200245185e-05,
"loss": 0.9512,
"step": 23700
},
{
"epoch": 5.95,
"grad_norm": 0.37549078464508057,
"learning_rate": 7.672815936359106e-05,
"loss": 0.9694,
"step": 23800
},
{
"epoch": 5.975,
"grad_norm": 0.43039214611053467,
"learning_rate": 7.496729702536912e-05,
"loss": 0.9191,
"step": 23900
},
{
"epoch": 6.0,
"grad_norm": 0.3925749361515045,
"learning_rate": 7.322330470336314e-05,
"loss": 0.9121,
"step": 24000
},
{
"epoch": 6.0,
"eval_loss": 0.9720398187637329,
"eval_runtime": 152.9557,
"eval_samples_per_second": 26.151,
"eval_steps_per_second": 6.538,
"step": 24000
},
{
"epoch": 6.025,
"grad_norm": 0.41935107111930847,
"learning_rate": 7.149635048718294e-05,
"loss": 0.9072,
"step": 24100
},
{
"epoch": 6.05,
"grad_norm": 0.4102177321910858,
"learning_rate": 6.97866008242703e-05,
"loss": 0.9105,
"step": 24200
},
{
"epoch": 6.075,
"grad_norm": 0.3717847168445587,
"learning_rate": 6.809422050385628e-05,
"loss": 0.9399,
"step": 24300
},
{
"epoch": 6.1,
"grad_norm": 0.3842828869819641,
"learning_rate": 6.641937264107867e-05,
"loss": 0.8992,
"step": 24400
},
{
"epoch": 6.125,
"grad_norm": 0.4051499366760254,
"learning_rate": 6.476221866126028e-05,
"loss": 0.9274,
"step": 24500
},
{
"epoch": 6.15,
"grad_norm": 0.4197865128517151,
"learning_rate": 6.312291828435076e-05,
"loss": 0.9646,
"step": 24600
},
{
"epoch": 6.175,
"grad_norm": 0.41968774795532227,
"learning_rate": 6.150162950953264e-05,
"loss": 0.9412,
"step": 24700
},
{
"epoch": 6.2,
"grad_norm": 0.40155336260795593,
"learning_rate": 5.989850859999227e-05,
"loss": 0.9627,
"step": 24800
},
{
"epoch": 6.225,
"grad_norm": 0.39962807297706604,
"learning_rate": 5.831371006785963e-05,
"loss": 0.9337,
"step": 24900
},
{
"epoch": 6.25,
"grad_norm": 0.4056980609893799,
"learning_rate": 5.6747386659315755e-05,
"loss": 0.9221,
"step": 25000
},
{
"epoch": 6.275,
"grad_norm": 0.4260208308696747,
"learning_rate": 5.519968933987082e-05,
"loss": 0.9359,
"step": 25100
},
{
"epoch": 6.3,
"grad_norm": 0.39483314752578735,
"learning_rate": 5.367076727981382e-05,
"loss": 0.9187,
"step": 25200
},
{
"epoch": 6.325,
"grad_norm": 0.43257468938827515,
"learning_rate": 5.216076783983492e-05,
"loss": 0.9701,
"step": 25300
},
{
"epoch": 6.35,
"grad_norm": 0.39114078879356384,
"learning_rate": 5.066983655682325e-05,
"loss": 0.9664,
"step": 25400
},
{
"epoch": 6.375,
"grad_norm": 0.39986172318458557,
"learning_rate": 4.919811712983879e-05,
"loss": 0.9345,
"step": 25500
},
{
"epoch": 6.4,
"grad_norm": 0.41802579164505005,
"learning_rate": 4.7745751406263163e-05,
"loss": 0.9192,
"step": 25600
},
{
"epoch": 6.425,
"grad_norm": 0.34528008103370667,
"learning_rate": 4.6312879368127645e-05,
"loss": 0.953,
"step": 25700
},
{
"epoch": 6.45,
"grad_norm": 0.418544739484787,
"learning_rate": 4.4899639118621604e-05,
"loss": 0.9121,
"step": 25800
},
{
"epoch": 6.475,
"grad_norm": 0.40490132570266724,
"learning_rate": 4.350616686878175e-05,
"loss": 0.9199,
"step": 25900
},
{
"epoch": 6.5,
"grad_norm": 0.4175280034542084,
"learning_rate": 4.213259692436367e-05,
"loss": 0.9304,
"step": 26000
},
{
"epoch": 6.525,
"grad_norm": 0.3687520921230316,
"learning_rate": 4.077906167289766e-05,
"loss": 0.953,
"step": 26100
},
{
"epoch": 6.55,
"grad_norm": 0.389283686876297,
"learning_rate": 3.944569157092839e-05,
"loss": 0.9278,
"step": 26200
},
{
"epoch": 6.575,
"grad_norm": 0.353508323431015,
"learning_rate": 3.8132615131441396e-05,
"loss": 0.9488,
"step": 26300
},
{
"epoch": 6.6,
"grad_norm": 0.3994731605052948,
"learning_rate": 3.6839958911476953e-05,
"loss": 0.8955,
"step": 26400
},
{
"epoch": 6.625,
"grad_norm": 0.37398815155029297,
"learning_rate": 3.5567847499932e-05,
"loss": 0.9453,
"step": 26500
},
{
"epoch": 6.65,
"grad_norm": 0.37087592482566833,
"learning_rate": 3.431640350555204e-05,
"loss": 0.9449,
"step": 26600
},
{
"epoch": 6.675,
"grad_norm": 0.3406459093093872,
"learning_rate": 3.308574754511404e-05,
"loss": 0.9143,
"step": 26700
},
{
"epoch": 6.7,
"grad_norm": 0.36757832765579224,
"learning_rate": 3.187599823180071e-05,
"loss": 0.935,
"step": 26800
},
{
"epoch": 6.725,
"grad_norm": 0.40823671221733093,
"learning_rate": 3.0687272163768986e-05,
"loss": 0.9181,
"step": 26900
},
{
"epoch": 6.75,
"grad_norm": 0.3942839801311493,
"learning_rate": 2.9519683912911265e-05,
"loss": 0.9219,
"step": 27000
},
{
"epoch": 6.775,
"grad_norm": 0.3952127695083618,
"learning_rate": 2.8373346013813417e-05,
"loss": 0.9001,
"step": 27100
},
{
"epoch": 6.8,
"grad_norm": 0.4122380018234253,
"learning_rate": 2.7248368952908055e-05,
"loss": 0.9266,
"step": 27200
},
{
"epoch": 6.825,
"grad_norm": 0.4118337631225586,
"learning_rate": 2.6144861157825773e-05,
"loss": 0.9364,
"step": 27300
},
{
"epoch": 6.85,
"grad_norm": 0.39552587270736694,
"learning_rate": 2.5062928986944677e-05,
"loss": 0.9226,
"step": 27400
},
{
"epoch": 6.875,
"grad_norm": 0.4226832687854767,
"learning_rate": 2.4002676719139166e-05,
"loss": 0.9394,
"step": 27500
},
{
"epoch": 6.9,
"grad_norm": 0.34474310278892517,
"learning_rate": 2.296420654372966e-05,
"loss": 0.9255,
"step": 27600
},
{
"epoch": 6.925,
"grad_norm": 0.4371466636657715,
"learning_rate": 2.1947618550633096e-05,
"loss": 0.9298,
"step": 27700
},
{
"epoch": 6.95,
"grad_norm": 0.4318234622478485,
"learning_rate": 2.0953010720716037e-05,
"loss": 0.9533,
"step": 27800
},
{
"epoch": 6.975,
"grad_norm": 0.38867416977882385,
"learning_rate": 1.9980478916351297e-05,
"loss": 0.9612,
"step": 27900
},
{
"epoch": 7.0,
"grad_norm": 0.38006094098091125,
"learning_rate": 1.9030116872178316e-05,
"loss": 0.9175,
"step": 28000
},
{
"epoch": 7.0,
"eval_loss": 0.9707372784614563,
"eval_runtime": 152.8648,
"eval_samples_per_second": 26.167,
"eval_steps_per_second": 6.542,
"step": 28000
},
{
"epoch": 7.025,
"grad_norm": 0.4155292510986328,
"learning_rate": 1.8102016186068992e-05,
"loss": 0.936,
"step": 28100
},
{
"epoch": 7.05,
"grad_norm": 0.3884825110435486,
"learning_rate": 1.719626631029911e-05,
"loss": 0.9398,
"step": 28200
},
{
"epoch": 7.075,
"grad_norm": 0.39031410217285156,
"learning_rate": 1.6312954542926888e-05,
"loss": 0.9056,
"step": 28300
},
{
"epoch": 7.1,
"grad_norm": 0.4356350004673004,
"learning_rate": 1.5452166019378987e-05,
"loss": 0.9178,
"step": 28400
},
{
"epoch": 7.125,
"grad_norm": 0.3904324769973755,
"learning_rate": 1.4613983704244827e-05,
"loss": 0.9067,
"step": 28500
},
{
"epoch": 7.15,
"grad_norm": 0.3213234543800354,
"learning_rate": 1.3798488383280488e-05,
"loss": 0.9436,
"step": 28600
},
{
"epoch": 7.175,
"grad_norm": 0.38800540566444397,
"learning_rate": 1.3005758655622424e-05,
"loss": 0.9131,
"step": 28700
},
{
"epoch": 7.2,
"grad_norm": 0.3734656870365143,
"learning_rate": 1.2235870926211617e-05,
"loss": 0.9466,
"step": 28800
},
{
"epoch": 7.225,
"grad_norm": 0.4088476002216339,
"learning_rate": 1.1488899398429897e-05,
"loss": 0.9444,
"step": 28900
},
{
"epoch": 7.25,
"grad_norm": 0.3788207471370697,
"learning_rate": 1.0764916066947795e-05,
"loss": 0.9015,
"step": 29000
},
{
"epoch": 7.275,
"grad_norm": 0.3710539638996124,
"learning_rate": 1.0063990710785648e-05,
"loss": 0.9356,
"step": 29100
},
{
"epoch": 7.3,
"grad_norm": 0.39175015687942505,
"learning_rate": 9.386190886588208e-06,
"loss": 0.9277,
"step": 29200
},
{
"epoch": 7.325,
"grad_norm": 0.39857038855552673,
"learning_rate": 8.731581922113152e-06,
"loss": 0.9597,
"step": 29300
},
{
"epoch": 7.35,
"grad_norm": 0.42670151591300964,
"learning_rate": 8.10022690993506e-06,
"loss": 0.9124,
"step": 29400
},
{
"epoch": 7.375,
"grad_norm": 0.37594255805015564,
"learning_rate": 7.4921867013640064e-06,
"loss": 0.9202,
"step": 29500
},
{
"epoch": 7.4,
"grad_norm": 0.34726592898368835,
"learning_rate": 6.907519900580861e-06,
"loss": 0.9462,
"step": 29600
},
{
"epoch": 7.425,
"grad_norm": 0.3583536744117737,
"learning_rate": 6.34628285898875e-06,
"loss": 0.9356,
"step": 29700
},
{
"epoch": 7.45,
"grad_norm": 0.40716230869293213,
"learning_rate": 5.808529669781903e-06,
"loss": 0.9204,
"step": 29800
},
{
"epoch": 7.475,
"grad_norm": 0.4574654698371887,
"learning_rate": 5.294312162731935e-06,
"loss": 0.9272,
"step": 29900
},
{
"epoch": 7.5,
"grad_norm": 0.41072556376457214,
"learning_rate": 4.803679899192393e-06,
"loss": 0.9181,
"step": 30000
},
{
"epoch": 7.525,
"grad_norm": 0.4989704191684723,
"learning_rate": 4.336680167322055e-06,
"loss": 0.9346,
"step": 30100
},
{
"epoch": 7.55,
"grad_norm": 0.4089345932006836,
"learning_rate": 3.893357977527101e-06,
"loss": 0.9392,
"step": 30200
},
{
"epoch": 7.575,
"grad_norm": 0.4189968407154083,
"learning_rate": 3.4737560581228343e-06,
"loss": 0.9338,
"step": 30300
},
{
"epoch": 7.6,
"grad_norm": 0.40372830629348755,
"learning_rate": 3.077914851215585e-06,
"loss": 0.9394,
"step": 30400
},
{
"epoch": 7.625,
"grad_norm": 0.3864797055721283,
"learning_rate": 2.7058725088047465e-06,
"loss": 0.9283,
"step": 30500
},
{
"epoch": 7.65,
"grad_norm": 0.4125591814517975,
"learning_rate": 2.357664889105687e-06,
"loss": 0.9731,
"step": 30600
},
{
"epoch": 7.675,
"grad_norm": 0.4122030436992645,
"learning_rate": 2.0333255530934903e-06,
"loss": 0.9257,
"step": 30700
},
{
"epoch": 7.7,
"grad_norm": 0.40973401069641113,
"learning_rate": 1.7328857612684267e-06,
"loss": 0.8964,
"step": 30800
},
{
"epoch": 7.725,
"grad_norm": 0.36363255977630615,
"learning_rate": 1.4563744706429517e-06,
"loss": 0.9012,
"step": 30900
},
{
"epoch": 7.75,
"grad_norm": 0.39668798446655273,
"learning_rate": 1.2038183319507957e-06,
"loss": 0.9399,
"step": 31000
},
{
"epoch": 7.775,
"grad_norm": 0.40102848410606384,
"learning_rate": 9.752416870782156e-07,
"loss": 0.9471,
"step": 31100
},
{
"epoch": 7.8,
"grad_norm": 0.43242618441581726,
"learning_rate": 7.70666566718009e-07,
"loss": 0.9289,
"step": 31200
},
{
"epoch": 7.825,
"grad_norm": 0.41685134172439575,
"learning_rate": 5.90112688246075e-07,
"loss": 0.9365,
"step": 31300
},
{
"epoch": 7.85,
"grad_norm": 0.36857473850250244,
"learning_rate": 4.335974538210441e-07,
"loss": 0.9324,
"step": 31400
},
{
"epoch": 7.875,
"grad_norm": 0.42975786328315735,
"learning_rate": 3.0113594870689873e-07,
"loss": 0.9379,
"step": 31500
},
{
"epoch": 7.9,
"grad_norm": 0.42332813143730164,
"learning_rate": 1.9274093981927476e-07,
"loss": 0.9453,
"step": 31600
},
{
"epoch": 7.925,
"grad_norm": 0.41806164383888245,
"learning_rate": 1.0842287449469579e-07,
"loss": 0.9055,
"step": 31700
},
{
"epoch": 7.95,
"grad_norm": 0.35621610283851624,
"learning_rate": 4.818987948379538e-08,
"loss": 0.8726,
"step": 31800
},
{
"epoch": 7.975,
"grad_norm": 0.43373915553092957,
"learning_rate": 1.2047760167999133e-08,
"loss": 0.946,
"step": 31900
},
{
"epoch": 8.0,
"grad_norm": 0.4070851504802704,
"learning_rate": 0.0,
"loss": 0.9197,
"step": 32000
}
],
"logging_steps": 100,
"max_steps": 32000,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.2123286020096e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}