Mistral-DNA-v1-1.6B-hg38 / trainer_state.json
RaphaelMourad's picture
Upload 9 files
f35ec84 verified
{
"best_metric": 5.67610502243042,
"best_model_checkpoint": "./results/models/mistral-dna/checkpoint-326520",
"epoch": 19.0,
"eval_steps": 500,
"global_step": 344660,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.027563395810363836,
"grad_norm": 0.2275390625,
"learning_rate": 0.0009994487320837927,
"loss": 6.911,
"step": 500
},
{
"epoch": 0.05512679162072767,
"grad_norm": 0.5078125,
"learning_rate": 0.0009988974641675853,
"loss": 6.4675,
"step": 1000
},
{
"epoch": 0.08269018743109151,
"grad_norm": 1.53125,
"learning_rate": 0.0009983461962513782,
"loss": 6.3671,
"step": 1500
},
{
"epoch": 0.11025358324145534,
"grad_norm": 0.98046875,
"learning_rate": 0.0009977949283351709,
"loss": 6.3713,
"step": 2000
},
{
"epoch": 0.1378169790518192,
"grad_norm": 8.625,
"learning_rate": 0.0009972436604189637,
"loss": 6.3203,
"step": 2500
},
{
"epoch": 0.16538037486218302,
"grad_norm": 0.94140625,
"learning_rate": 0.0009966923925027564,
"loss": 6.2909,
"step": 3000
},
{
"epoch": 0.19294377067254687,
"grad_norm": 1.5078125,
"learning_rate": 0.000996141124586549,
"loss": 6.258,
"step": 3500
},
{
"epoch": 0.2205071664829107,
"grad_norm": 1.78125,
"learning_rate": 0.000995589856670342,
"loss": 6.229,
"step": 4000
},
{
"epoch": 0.24807056229327454,
"grad_norm": 1.015625,
"learning_rate": 0.0009950385887541346,
"loss": 6.1963,
"step": 4500
},
{
"epoch": 0.2756339581036384,
"grad_norm": 0.85546875,
"learning_rate": 0.0009944873208379273,
"loss": 6.164,
"step": 5000
},
{
"epoch": 0.3031973539140022,
"grad_norm": 1.4921875,
"learning_rate": 0.00099393605292172,
"loss": 6.182,
"step": 5500
},
{
"epoch": 0.33076074972436603,
"grad_norm": 2.265625,
"learning_rate": 0.0009933847850055126,
"loss": 6.1642,
"step": 6000
},
{
"epoch": 0.35832414553472985,
"grad_norm": 1.28125,
"learning_rate": 0.0009928335170893054,
"loss": 6.1384,
"step": 6500
},
{
"epoch": 0.38588754134509373,
"grad_norm": 2.453125,
"learning_rate": 0.000992282249173098,
"loss": 6.1192,
"step": 7000
},
{
"epoch": 0.41345093715545755,
"grad_norm": 2.53125,
"learning_rate": 0.000991730981256891,
"loss": 6.118,
"step": 7500
},
{
"epoch": 0.4410143329658214,
"grad_norm": 2.484375,
"learning_rate": 0.0009911797133406836,
"loss": 6.1237,
"step": 8000
},
{
"epoch": 0.4685777287761852,
"grad_norm": 0.93359375,
"learning_rate": 0.0009906284454244763,
"loss": 6.1096,
"step": 8500
},
{
"epoch": 0.4961411245865491,
"grad_norm": 0.9765625,
"learning_rate": 0.0009900771775082692,
"loss": 6.0873,
"step": 9000
},
{
"epoch": 0.523704520396913,
"grad_norm": 1.0078125,
"learning_rate": 0.0009895259095920618,
"loss": 6.0941,
"step": 9500
},
{
"epoch": 0.5512679162072768,
"grad_norm": 1.1015625,
"learning_rate": 0.0009889746416758545,
"loss": 6.0842,
"step": 10000
},
{
"epoch": 0.5788313120176406,
"grad_norm": 1.390625,
"learning_rate": 0.0009884233737596471,
"loss": 6.0843,
"step": 10500
},
{
"epoch": 0.6063947078280044,
"grad_norm": 1.1953125,
"learning_rate": 0.0009878721058434398,
"loss": 6.0626,
"step": 11000
},
{
"epoch": 0.6339581036383682,
"grad_norm": 1.984375,
"learning_rate": 0.0009873208379272327,
"loss": 6.0823,
"step": 11500
},
{
"epoch": 0.6615214994487321,
"grad_norm": 1.078125,
"learning_rate": 0.0009867695700110253,
"loss": 6.0745,
"step": 12000
},
{
"epoch": 0.6890848952590959,
"grad_norm": 1.0859375,
"learning_rate": 0.0009862183020948182,
"loss": 6.0307,
"step": 12500
},
{
"epoch": 0.7166482910694597,
"grad_norm": 1.265625,
"learning_rate": 0.0009856670341786109,
"loss": 6.0327,
"step": 13000
},
{
"epoch": 0.7442116868798236,
"grad_norm": 1.03125,
"learning_rate": 0.0009851157662624035,
"loss": 6.0547,
"step": 13500
},
{
"epoch": 0.7717750826901875,
"grad_norm": 0.87890625,
"learning_rate": 0.0009845644983461964,
"loss": 6.0374,
"step": 14000
},
{
"epoch": 0.7993384785005513,
"grad_norm": 1.390625,
"learning_rate": 0.000984013230429989,
"loss": 6.029,
"step": 14500
},
{
"epoch": 0.8269018743109151,
"grad_norm": 1.1796875,
"learning_rate": 0.0009834619625137817,
"loss": 6.0243,
"step": 15000
},
{
"epoch": 0.8544652701212789,
"grad_norm": 1.5703125,
"learning_rate": 0.0009829106945975744,
"loss": 5.9914,
"step": 15500
},
{
"epoch": 0.8820286659316428,
"grad_norm": 1.0390625,
"learning_rate": 0.000982359426681367,
"loss": 6.0179,
"step": 16000
},
{
"epoch": 0.9095920617420066,
"grad_norm": 1.5,
"learning_rate": 0.00098180815876516,
"loss": 6.0157,
"step": 16500
},
{
"epoch": 0.9371554575523704,
"grad_norm": 1.0625,
"learning_rate": 0.0009812568908489526,
"loss": 6.0221,
"step": 17000
},
{
"epoch": 0.9647188533627343,
"grad_norm": 1.03125,
"learning_rate": 0.0009807056229327454,
"loss": 6.0173,
"step": 17500
},
{
"epoch": 0.9922822491730982,
"grad_norm": 0.89453125,
"learning_rate": 0.000980154355016538,
"loss": 5.9947,
"step": 18000
},
{
"epoch": 1.0,
"eval_loss": 5.929446220397949,
"eval_runtime": 3.5789,
"eval_samples_per_second": 81.309,
"eval_steps_per_second": 5.309,
"step": 18140
},
{
"epoch": 1.0198456449834619,
"grad_norm": 1.171875,
"learning_rate": 0.0009796030871003308,
"loss": 5.998,
"step": 18500
},
{
"epoch": 1.0474090407938257,
"grad_norm": 10.0,
"learning_rate": 0.0009790518191841234,
"loss": 6.0043,
"step": 19000
},
{
"epoch": 1.0749724366041897,
"grad_norm": 1.078125,
"learning_rate": 0.0009785005512679163,
"loss": 5.9952,
"step": 19500
},
{
"epoch": 1.1025358324145536,
"grad_norm": 1.8984375,
"learning_rate": 0.000977949283351709,
"loss": 5.9804,
"step": 20000
},
{
"epoch": 1.1300992282249174,
"grad_norm": 2.234375,
"learning_rate": 0.0009773980154355016,
"loss": 5.9935,
"step": 20500
},
{
"epoch": 1.1576626240352812,
"grad_norm": 1.234375,
"learning_rate": 0.0009768467475192943,
"loss": 5.9866,
"step": 21000
},
{
"epoch": 1.185226019845645,
"grad_norm": 1.109375,
"learning_rate": 0.000976295479603087,
"loss": 5.9887,
"step": 21500
},
{
"epoch": 1.2127894156560088,
"grad_norm": 2.046875,
"learning_rate": 0.0009757442116868799,
"loss": 5.9695,
"step": 22000
},
{
"epoch": 1.2403528114663727,
"grad_norm": 0.91796875,
"learning_rate": 0.0009751929437706726,
"loss": 5.9573,
"step": 22500
},
{
"epoch": 1.2679162072767365,
"grad_norm": 12.75,
"learning_rate": 0.0009746416758544653,
"loss": 5.9796,
"step": 23000
},
{
"epoch": 1.2954796030871003,
"grad_norm": 1.28125,
"learning_rate": 0.000974090407938258,
"loss": 5.9909,
"step": 23500
},
{
"epoch": 1.3230429988974641,
"grad_norm": 1.53125,
"learning_rate": 0.0009735391400220506,
"loss": 5.9719,
"step": 24000
},
{
"epoch": 1.350606394707828,
"grad_norm": 0.89453125,
"learning_rate": 0.0009729878721058435,
"loss": 5.9726,
"step": 24500
},
{
"epoch": 1.3781697905181918,
"grad_norm": 2.578125,
"learning_rate": 0.0009724366041896362,
"loss": 5.9742,
"step": 25000
},
{
"epoch": 1.4057331863285556,
"grad_norm": 1.15625,
"learning_rate": 0.0009718853362734289,
"loss": 5.9722,
"step": 25500
},
{
"epoch": 1.4332965821389196,
"grad_norm": 1.3125,
"learning_rate": 0.0009713340683572216,
"loss": 5.9578,
"step": 26000
},
{
"epoch": 1.4608599779492835,
"grad_norm": 1.453125,
"learning_rate": 0.0009707828004410143,
"loss": 5.9473,
"step": 26500
},
{
"epoch": 1.4884233737596473,
"grad_norm": 1.390625,
"learning_rate": 0.0009702315325248071,
"loss": 5.955,
"step": 27000
},
{
"epoch": 1.515986769570011,
"grad_norm": 1.3359375,
"learning_rate": 0.0009696802646085998,
"loss": 5.9419,
"step": 27500
},
{
"epoch": 1.543550165380375,
"grad_norm": 1.640625,
"learning_rate": 0.0009691289966923926,
"loss": 5.9387,
"step": 28000
},
{
"epoch": 1.5711135611907387,
"grad_norm": 1.6015625,
"learning_rate": 0.0009685777287761852,
"loss": 5.95,
"step": 28500
},
{
"epoch": 1.5986769570011026,
"grad_norm": 1.3203125,
"learning_rate": 0.0009680264608599779,
"loss": 5.9469,
"step": 29000
},
{
"epoch": 1.6262403528114664,
"grad_norm": 4.90625,
"learning_rate": 0.0009674751929437707,
"loss": 5.9324,
"step": 29500
},
{
"epoch": 1.6538037486218302,
"grad_norm": 1.4765625,
"learning_rate": 0.0009669239250275634,
"loss": 5.9238,
"step": 30000
},
{
"epoch": 1.681367144432194,
"grad_norm": 1.265625,
"learning_rate": 0.0009663726571113562,
"loss": 5.9536,
"step": 30500
},
{
"epoch": 1.7089305402425579,
"grad_norm": 1.1875,
"learning_rate": 0.0009658213891951488,
"loss": 5.9408,
"step": 31000
},
{
"epoch": 1.7364939360529217,
"grad_norm": 1.734375,
"learning_rate": 0.0009652701212789415,
"loss": 5.9553,
"step": 31500
},
{
"epoch": 1.7640573318632855,
"grad_norm": 0.84765625,
"learning_rate": 0.0009647188533627344,
"loss": 5.9385,
"step": 32000
},
{
"epoch": 1.7916207276736493,
"grad_norm": 1.3671875,
"learning_rate": 0.000964167585446527,
"loss": 5.9371,
"step": 32500
},
{
"epoch": 1.8191841234840131,
"grad_norm": 1.421875,
"learning_rate": 0.0009636163175303198,
"loss": 5.9171,
"step": 33000
},
{
"epoch": 1.846747519294377,
"grad_norm": 1.875,
"learning_rate": 0.0009630650496141124,
"loss": 5.9314,
"step": 33500
},
{
"epoch": 1.8743109151047408,
"grad_norm": 0.8359375,
"learning_rate": 0.0009625137816979052,
"loss": 5.951,
"step": 34000
},
{
"epoch": 1.9018743109151046,
"grad_norm": 1.390625,
"learning_rate": 0.000961962513781698,
"loss": 5.9276,
"step": 34500
},
{
"epoch": 1.9294377067254684,
"grad_norm": 1.1796875,
"learning_rate": 0.0009614112458654906,
"loss": 5.9392,
"step": 35000
},
{
"epoch": 1.9570011025358323,
"grad_norm": 0.52734375,
"learning_rate": 0.0009608599779492834,
"loss": 5.9271,
"step": 35500
},
{
"epoch": 1.9845644983461963,
"grad_norm": 4.8125,
"learning_rate": 0.0009603087100330761,
"loss": 5.9204,
"step": 36000
},
{
"epoch": 2.0,
"eval_loss": 5.8477325439453125,
"eval_runtime": 3.5523,
"eval_samples_per_second": 81.919,
"eval_steps_per_second": 5.349,
"step": 36280
},
{
"epoch": 2.01212789415656,
"grad_norm": 1.0625,
"learning_rate": 0.0009597574421168688,
"loss": 5.9157,
"step": 36500
},
{
"epoch": 2.0396912899669237,
"grad_norm": 1.109375,
"learning_rate": 0.0009592061742006616,
"loss": 5.931,
"step": 37000
},
{
"epoch": 2.0672546857772875,
"grad_norm": 1.7265625,
"learning_rate": 0.0009586549062844542,
"loss": 5.9114,
"step": 37500
},
{
"epoch": 2.0948180815876514,
"grad_norm": 1.40625,
"learning_rate": 0.000958103638368247,
"loss": 5.9024,
"step": 38000
},
{
"epoch": 2.1223814773980156,
"grad_norm": 1.078125,
"learning_rate": 0.0009575523704520397,
"loss": 5.9296,
"step": 38500
},
{
"epoch": 2.1499448732083795,
"grad_norm": 0.640625,
"learning_rate": 0.0009570011025358324,
"loss": 5.9374,
"step": 39000
},
{
"epoch": 2.1775082690187433,
"grad_norm": 0.98046875,
"learning_rate": 0.0009564498346196252,
"loss": 5.9184,
"step": 39500
},
{
"epoch": 2.205071664829107,
"grad_norm": 1.3828125,
"learning_rate": 0.0009558985667034179,
"loss": 5.896,
"step": 40000
},
{
"epoch": 2.232635060639471,
"grad_norm": 0.8984375,
"learning_rate": 0.0009553472987872106,
"loss": 5.9052,
"step": 40500
},
{
"epoch": 2.2601984564498347,
"grad_norm": 1.7734375,
"learning_rate": 0.0009547960308710033,
"loss": 5.9184,
"step": 41000
},
{
"epoch": 2.2877618522601986,
"grad_norm": 1.3125,
"learning_rate": 0.0009542447629547961,
"loss": 5.8971,
"step": 41500
},
{
"epoch": 2.3153252480705624,
"grad_norm": 1.265625,
"learning_rate": 0.0009536934950385888,
"loss": 5.9281,
"step": 42000
},
{
"epoch": 2.342888643880926,
"grad_norm": 1.203125,
"learning_rate": 0.0009531422271223815,
"loss": 5.8906,
"step": 42500
},
{
"epoch": 2.37045203969129,
"grad_norm": 0.9296875,
"learning_rate": 0.0009525909592061742,
"loss": 5.8993,
"step": 43000
},
{
"epoch": 2.398015435501654,
"grad_norm": 2.421875,
"learning_rate": 0.0009520396912899669,
"loss": 5.9032,
"step": 43500
},
{
"epoch": 2.4255788313120177,
"grad_norm": 1.0,
"learning_rate": 0.0009514884233737597,
"loss": 5.8909,
"step": 44000
},
{
"epoch": 2.4531422271223815,
"grad_norm": 1.1875,
"learning_rate": 0.0009509371554575524,
"loss": 5.9002,
"step": 44500
},
{
"epoch": 2.4807056229327453,
"grad_norm": 0.79296875,
"learning_rate": 0.0009503858875413451,
"loss": 5.882,
"step": 45000
},
{
"epoch": 2.508269018743109,
"grad_norm": 2.3125,
"learning_rate": 0.0009498346196251379,
"loss": 5.8949,
"step": 45500
},
{
"epoch": 2.535832414553473,
"grad_norm": 1.0859375,
"learning_rate": 0.0009492833517089305,
"loss": 5.8871,
"step": 46000
},
{
"epoch": 2.563395810363837,
"grad_norm": 0.70703125,
"learning_rate": 0.0009487320837927233,
"loss": 5.9061,
"step": 46500
},
{
"epoch": 2.5909592061742006,
"grad_norm": 1.1328125,
"learning_rate": 0.000948180815876516,
"loss": 5.8935,
"step": 47000
},
{
"epoch": 2.6185226019845644,
"grad_norm": 0.65234375,
"learning_rate": 0.0009476295479603087,
"loss": 5.8811,
"step": 47500
},
{
"epoch": 2.6460859977949283,
"grad_norm": 0.79296875,
"learning_rate": 0.0009470782800441015,
"loss": 5.8933,
"step": 48000
},
{
"epoch": 2.673649393605292,
"grad_norm": 0.91015625,
"learning_rate": 0.0009465270121278941,
"loss": 5.8882,
"step": 48500
},
{
"epoch": 2.701212789415656,
"grad_norm": 0.97265625,
"learning_rate": 0.0009459757442116869,
"loss": 5.8635,
"step": 49000
},
{
"epoch": 2.7287761852260197,
"grad_norm": 1.015625,
"learning_rate": 0.0009454244762954797,
"loss": 5.888,
"step": 49500
},
{
"epoch": 2.7563395810363835,
"grad_norm": 0.8984375,
"learning_rate": 0.0009448732083792723,
"loss": 5.8789,
"step": 50000
},
{
"epoch": 2.7839029768467474,
"grad_norm": 0.66796875,
"learning_rate": 0.0009443219404630651,
"loss": 5.8909,
"step": 50500
},
{
"epoch": 2.811466372657111,
"grad_norm": 1.6171875,
"learning_rate": 0.0009437706725468577,
"loss": 5.8678,
"step": 51000
},
{
"epoch": 2.8390297684674755,
"grad_norm": 3.53125,
"learning_rate": 0.0009432194046306505,
"loss": 5.8754,
"step": 51500
},
{
"epoch": 2.8665931642778393,
"grad_norm": 0.71875,
"learning_rate": 0.0009426681367144433,
"loss": 5.8766,
"step": 52000
},
{
"epoch": 2.894156560088203,
"grad_norm": 0.6953125,
"learning_rate": 0.0009421168687982359,
"loss": 5.886,
"step": 52500
},
{
"epoch": 2.921719955898567,
"grad_norm": 0.87890625,
"learning_rate": 0.0009415656008820287,
"loss": 5.8551,
"step": 53000
},
{
"epoch": 2.9492833517089307,
"grad_norm": 0.875,
"learning_rate": 0.0009410143329658214,
"loss": 5.8986,
"step": 53500
},
{
"epoch": 2.9768467475192946,
"grad_norm": 1.609375,
"learning_rate": 0.0009404630650496141,
"loss": 5.891,
"step": 54000
},
{
"epoch": 3.0,
"eval_loss": 5.803347587585449,
"eval_runtime": 3.5792,
"eval_samples_per_second": 81.304,
"eval_steps_per_second": 5.308,
"step": 54420
},
{
"epoch": 3.0044101433296584,
"grad_norm": 0.6484375,
"learning_rate": 0.0009399117971334069,
"loss": 5.8926,
"step": 54500
},
{
"epoch": 3.031973539140022,
"grad_norm": 14.875,
"learning_rate": 0.0009393605292171997,
"loss": 5.8568,
"step": 55000
},
{
"epoch": 3.059536934950386,
"grad_norm": 0.58203125,
"learning_rate": 0.0009388092613009923,
"loss": 5.8754,
"step": 55500
},
{
"epoch": 3.08710033076075,
"grad_norm": 0.79296875,
"learning_rate": 0.000938257993384785,
"loss": 5.8574,
"step": 56000
},
{
"epoch": 3.1146637265711137,
"grad_norm": 1.2265625,
"learning_rate": 0.0009377067254685777,
"loss": 5.8662,
"step": 56500
},
{
"epoch": 3.1422271223814775,
"grad_norm": 0.640625,
"learning_rate": 0.0009371554575523704,
"loss": 5.8519,
"step": 57000
},
{
"epoch": 3.1697905181918413,
"grad_norm": 0.6171875,
"learning_rate": 0.0009366041896361633,
"loss": 5.8509,
"step": 57500
},
{
"epoch": 3.197353914002205,
"grad_norm": 0.74609375,
"learning_rate": 0.0009360529217199559,
"loss": 5.8836,
"step": 58000
},
{
"epoch": 3.224917309812569,
"grad_norm": 0.7109375,
"learning_rate": 0.0009355016538037486,
"loss": 5.8643,
"step": 58500
},
{
"epoch": 3.252480705622933,
"grad_norm": 1.1640625,
"learning_rate": 0.0009349503858875414,
"loss": 5.8799,
"step": 59000
},
{
"epoch": 3.2800441014332966,
"grad_norm": 0.84375,
"learning_rate": 0.000934399117971334,
"loss": 5.866,
"step": 59500
},
{
"epoch": 3.3076074972436604,
"grad_norm": 0.93359375,
"learning_rate": 0.0009338478500551269,
"loss": 5.8548,
"step": 60000
},
{
"epoch": 3.3351708930540243,
"grad_norm": 0.609375,
"learning_rate": 0.0009332965821389196,
"loss": 5.8507,
"step": 60500
},
{
"epoch": 3.362734288864388,
"grad_norm": 1.578125,
"learning_rate": 0.0009327453142227122,
"loss": 5.8459,
"step": 61000
},
{
"epoch": 3.390297684674752,
"grad_norm": 0.93359375,
"learning_rate": 0.000932194046306505,
"loss": 5.8494,
"step": 61500
},
{
"epoch": 3.4178610804851157,
"grad_norm": 0.78515625,
"learning_rate": 0.0009316427783902976,
"loss": 5.873,
"step": 62000
},
{
"epoch": 3.4454244762954795,
"grad_norm": 1.3515625,
"learning_rate": 0.0009310915104740905,
"loss": 5.8589,
"step": 62500
},
{
"epoch": 3.4729878721058434,
"grad_norm": 0.8671875,
"learning_rate": 0.0009305402425578832,
"loss": 5.8487,
"step": 63000
},
{
"epoch": 3.500551267916207,
"grad_norm": 1.5546875,
"learning_rate": 0.0009299889746416758,
"loss": 5.8644,
"step": 63500
},
{
"epoch": 3.528114663726571,
"grad_norm": 0.765625,
"learning_rate": 0.0009294377067254686,
"loss": 5.8487,
"step": 64000
},
{
"epoch": 3.555678059536935,
"grad_norm": 0.6328125,
"learning_rate": 0.0009288864388092612,
"loss": 5.8694,
"step": 64500
},
{
"epoch": 3.5832414553472987,
"grad_norm": 1.03125,
"learning_rate": 0.0009283351708930541,
"loss": 5.8628,
"step": 65000
},
{
"epoch": 3.6108048511576625,
"grad_norm": 0.68359375,
"learning_rate": 0.0009277839029768468,
"loss": 5.8573,
"step": 65500
},
{
"epoch": 3.6383682469680263,
"grad_norm": 0.90625,
"learning_rate": 0.0009272326350606394,
"loss": 5.8417,
"step": 66000
},
{
"epoch": 3.66593164277839,
"grad_norm": 1.6015625,
"learning_rate": 0.0009266813671444322,
"loss": 5.8485,
"step": 66500
},
{
"epoch": 3.693495038588754,
"grad_norm": 0.75,
"learning_rate": 0.0009261300992282249,
"loss": 5.8443,
"step": 67000
},
{
"epoch": 3.7210584343991178,
"grad_norm": 0.859375,
"learning_rate": 0.0009255788313120177,
"loss": 5.841,
"step": 67500
},
{
"epoch": 3.7486218302094816,
"grad_norm": 0.6875,
"learning_rate": 0.0009250275633958104,
"loss": 5.835,
"step": 68000
},
{
"epoch": 3.7761852260198454,
"grad_norm": 0.96484375,
"learning_rate": 0.0009244762954796031,
"loss": 5.8575,
"step": 68500
},
{
"epoch": 3.8037486218302092,
"grad_norm": 1.1796875,
"learning_rate": 0.0009239250275633958,
"loss": 5.8631,
"step": 69000
},
{
"epoch": 3.831312017640573,
"grad_norm": 0.7578125,
"learning_rate": 0.0009233737596471885,
"loss": 5.8509,
"step": 69500
},
{
"epoch": 3.8588754134509373,
"grad_norm": 0.5703125,
"learning_rate": 0.0009228224917309814,
"loss": 5.847,
"step": 70000
},
{
"epoch": 3.886438809261301,
"grad_norm": 0.76171875,
"learning_rate": 0.000922271223814774,
"loss": 5.8587,
"step": 70500
},
{
"epoch": 3.914002205071665,
"grad_norm": 0.51171875,
"learning_rate": 0.0009217199558985667,
"loss": 5.8451,
"step": 71000
},
{
"epoch": 3.941565600882029,
"grad_norm": 0.41015625,
"learning_rate": 0.0009211686879823594,
"loss": 5.8521,
"step": 71500
},
{
"epoch": 3.9691289966923926,
"grad_norm": 0.8671875,
"learning_rate": 0.0009206174200661521,
"loss": 5.8407,
"step": 72000
},
{
"epoch": 3.9966923925027564,
"grad_norm": 0.75390625,
"learning_rate": 0.000920066152149945,
"loss": 5.8205,
"step": 72500
},
{
"epoch": 4.0,
"eval_loss": 5.774289608001709,
"eval_runtime": 3.5097,
"eval_samples_per_second": 82.912,
"eval_steps_per_second": 5.414,
"step": 72560
},
{
"epoch": 4.02425578831312,
"grad_norm": 0.79296875,
"learning_rate": 0.0009195148842337376,
"loss": 5.8396,
"step": 73000
},
{
"epoch": 4.051819184123484,
"grad_norm": 1.5,
"learning_rate": 0.0009189636163175303,
"loss": 5.8453,
"step": 73500
},
{
"epoch": 4.0793825799338475,
"grad_norm": 0.58203125,
"learning_rate": 0.000918412348401323,
"loss": 5.8365,
"step": 74000
},
{
"epoch": 4.106945975744211,
"grad_norm": 0.55078125,
"learning_rate": 0.0009178610804851157,
"loss": 5.8304,
"step": 74500
},
{
"epoch": 4.134509371554575,
"grad_norm": 0.77734375,
"learning_rate": 0.0009173098125689086,
"loss": 5.8235,
"step": 75000
},
{
"epoch": 4.16207276736494,
"grad_norm": 0.78515625,
"learning_rate": 0.0009167585446527012,
"loss": 5.8591,
"step": 75500
},
{
"epoch": 4.189636163175303,
"grad_norm": 2.515625,
"learning_rate": 0.000916207276736494,
"loss": 5.8466,
"step": 76000
},
{
"epoch": 4.2171995589856675,
"grad_norm": 0.5703125,
"learning_rate": 0.0009156560088202867,
"loss": 5.8329,
"step": 76500
},
{
"epoch": 4.244762954796031,
"grad_norm": 0.55078125,
"learning_rate": 0.0009151047409040793,
"loss": 5.8334,
"step": 77000
},
{
"epoch": 4.272326350606395,
"grad_norm": 1.0859375,
"learning_rate": 0.0009145534729878722,
"loss": 5.8243,
"step": 77500
},
{
"epoch": 4.299889746416759,
"grad_norm": 0.75,
"learning_rate": 0.0009140022050716649,
"loss": 5.8238,
"step": 78000
},
{
"epoch": 4.327453142227123,
"grad_norm": 1.90625,
"learning_rate": 0.0009134509371554576,
"loss": 5.8285,
"step": 78500
},
{
"epoch": 4.355016538037487,
"grad_norm": 0.58984375,
"learning_rate": 0.0009128996692392503,
"loss": 5.838,
"step": 79000
},
{
"epoch": 4.38257993384785,
"grad_norm": 0.6015625,
"learning_rate": 0.0009123484013230429,
"loss": 5.8347,
"step": 79500
},
{
"epoch": 4.410143329658214,
"grad_norm": 0.75,
"learning_rate": 0.0009117971334068358,
"loss": 5.832,
"step": 80000
},
{
"epoch": 4.437706725468578,
"grad_norm": 0.46484375,
"learning_rate": 0.0009112458654906285,
"loss": 5.841,
"step": 80500
},
{
"epoch": 4.465270121278942,
"grad_norm": 0.87890625,
"learning_rate": 0.0009106945975744212,
"loss": 5.8299,
"step": 81000
},
{
"epoch": 4.492833517089306,
"grad_norm": 1.265625,
"learning_rate": 0.0009101433296582139,
"loss": 5.8212,
"step": 81500
},
{
"epoch": 4.5203969128996695,
"grad_norm": 0.6328125,
"learning_rate": 0.0009095920617420066,
"loss": 5.8406,
"step": 82000
},
{
"epoch": 4.547960308710033,
"grad_norm": 0.69140625,
"learning_rate": 0.0009090407938257994,
"loss": 5.8292,
"step": 82500
},
{
"epoch": 4.575523704520397,
"grad_norm": 0.66015625,
"learning_rate": 0.0009084895259095921,
"loss": 5.8295,
"step": 83000
},
{
"epoch": 4.603087100330761,
"grad_norm": 0.7109375,
"learning_rate": 0.0009079382579933849,
"loss": 5.8325,
"step": 83500
},
{
"epoch": 4.630650496141125,
"grad_norm": 0.484375,
"learning_rate": 0.0009073869900771775,
"loss": 5.8038,
"step": 84000
},
{
"epoch": 4.658213891951489,
"grad_norm": 0.6171875,
"learning_rate": 0.0009068357221609702,
"loss": 5.8389,
"step": 84500
},
{
"epoch": 4.685777287761852,
"grad_norm": 3.375,
"learning_rate": 0.000906284454244763,
"loss": 5.829,
"step": 85000
},
{
"epoch": 4.713340683572216,
"grad_norm": 0.55859375,
"learning_rate": 0.0009057331863285557,
"loss": 5.8178,
"step": 85500
},
{
"epoch": 4.74090407938258,
"grad_norm": 0.8515625,
"learning_rate": 0.0009051819184123485,
"loss": 5.8195,
"step": 86000
},
{
"epoch": 4.768467475192944,
"grad_norm": 0.6171875,
"learning_rate": 0.0009046306504961411,
"loss": 5.8204,
"step": 86500
},
{
"epoch": 4.796030871003308,
"grad_norm": 0.9296875,
"learning_rate": 0.0009040793825799338,
"loss": 5.7925,
"step": 87000
},
{
"epoch": 4.8235942668136715,
"grad_norm": 0.419921875,
"learning_rate": 0.0009035281146637267,
"loss": 5.8219,
"step": 87500
},
{
"epoch": 4.851157662624035,
"grad_norm": 0.466796875,
"learning_rate": 0.0009029768467475193,
"loss": 5.8183,
"step": 88000
},
{
"epoch": 4.878721058434399,
"grad_norm": 0.8515625,
"learning_rate": 0.0009024255788313121,
"loss": 5.8106,
"step": 88500
},
{
"epoch": 4.906284454244763,
"grad_norm": 0.546875,
"learning_rate": 0.0009018743109151047,
"loss": 5.8082,
"step": 89000
},
{
"epoch": 4.933847850055127,
"grad_norm": 0.921875,
"learning_rate": 0.0009013230429988974,
"loss": 5.8191,
"step": 89500
},
{
"epoch": 4.961411245865491,
"grad_norm": 0.76953125,
"learning_rate": 0.0009007717750826903,
"loss": 5.8146,
"step": 90000
},
{
"epoch": 4.9889746416758545,
"grad_norm": 1.0234375,
"learning_rate": 0.0009002205071664829,
"loss": 5.834,
"step": 90500
},
{
"epoch": 5.0,
"eval_loss": 5.750288486480713,
"eval_runtime": 3.4633,
"eval_samples_per_second": 84.024,
"eval_steps_per_second": 5.486,
"step": 90700
},
{
"epoch": 5.016538037486218,
"grad_norm": 0.5546875,
"learning_rate": 0.0008996692392502757,
"loss": 5.7809,
"step": 91000
},
{
"epoch": 5.044101433296582,
"grad_norm": 0.5390625,
"learning_rate": 0.0008991179713340684,
"loss": 5.8308,
"step": 91500
},
{
"epoch": 5.071664829106946,
"grad_norm": 0.60546875,
"learning_rate": 0.000898566703417861,
"loss": 5.7961,
"step": 92000
},
{
"epoch": 5.09922822491731,
"grad_norm": 0.53515625,
"learning_rate": 0.0008980154355016539,
"loss": 5.787,
"step": 92500
},
{
"epoch": 5.126791620727674,
"grad_norm": 0.55859375,
"learning_rate": 0.0008974641675854465,
"loss": 5.8046,
"step": 93000
},
{
"epoch": 5.154355016538037,
"grad_norm": 0.859375,
"learning_rate": 0.0008969128996692393,
"loss": 5.8129,
"step": 93500
},
{
"epoch": 5.181918412348401,
"grad_norm": 0.66796875,
"learning_rate": 0.000896361631753032,
"loss": 5.7921,
"step": 94000
},
{
"epoch": 5.209481808158765,
"grad_norm": 0.470703125,
"learning_rate": 0.0008958103638368246,
"loss": 5.8238,
"step": 94500
},
{
"epoch": 5.237045203969129,
"grad_norm": 0.94921875,
"learning_rate": 0.0008952590959206174,
"loss": 5.8191,
"step": 95000
},
{
"epoch": 5.264608599779493,
"grad_norm": 0.546875,
"learning_rate": 0.0008947078280044102,
"loss": 5.8169,
"step": 95500
},
{
"epoch": 5.2921719955898565,
"grad_norm": 0.44140625,
"learning_rate": 0.0008941565600882029,
"loss": 5.8309,
"step": 96000
},
{
"epoch": 5.31973539140022,
"grad_norm": 0.484375,
"learning_rate": 0.0008936052921719956,
"loss": 5.7999,
"step": 96500
},
{
"epoch": 5.347298787210584,
"grad_norm": 0.5390625,
"learning_rate": 0.0008930540242557882,
"loss": 5.8098,
"step": 97000
},
{
"epoch": 5.374862183020948,
"grad_norm": 0.484375,
"learning_rate": 0.000892502756339581,
"loss": 5.799,
"step": 97500
},
{
"epoch": 5.402425578831312,
"grad_norm": 1.3671875,
"learning_rate": 0.0008919514884233738,
"loss": 5.7938,
"step": 98000
},
{
"epoch": 5.429988974641676,
"grad_norm": 0.6875,
"learning_rate": 0.0008914002205071665,
"loss": 5.8295,
"step": 98500
},
{
"epoch": 5.4575523704520394,
"grad_norm": 0.58203125,
"learning_rate": 0.0008908489525909592,
"loss": 5.803,
"step": 99000
},
{
"epoch": 5.485115766262403,
"grad_norm": 0.515625,
"learning_rate": 0.000890297684674752,
"loss": 5.7955,
"step": 99500
},
{
"epoch": 5.512679162072767,
"grad_norm": 0.5703125,
"learning_rate": 0.0008897464167585446,
"loss": 5.8132,
"step": 100000
},
{
"epoch": 5.540242557883131,
"grad_norm": 0.83203125,
"learning_rate": 0.0008891951488423374,
"loss": 5.8069,
"step": 100500
},
{
"epoch": 5.567805953693495,
"grad_norm": 0.703125,
"learning_rate": 0.0008886438809261302,
"loss": 5.7817,
"step": 101000
},
{
"epoch": 5.595369349503859,
"grad_norm": 2.3125,
"learning_rate": 0.0008880926130099228,
"loss": 5.8091,
"step": 101500
},
{
"epoch": 5.622932745314222,
"grad_norm": 1.2265625,
"learning_rate": 0.0008875413450937156,
"loss": 5.8136,
"step": 102000
},
{
"epoch": 5.650496141124586,
"grad_norm": 0.55859375,
"learning_rate": 0.0008869900771775082,
"loss": 5.7865,
"step": 102500
},
{
"epoch": 5.67805953693495,
"grad_norm": 0.45703125,
"learning_rate": 0.000886438809261301,
"loss": 5.8017,
"step": 103000
},
{
"epoch": 5.705622932745314,
"grad_norm": 0.69140625,
"learning_rate": 0.0008858875413450938,
"loss": 5.7965,
"step": 103500
},
{
"epoch": 5.733186328555679,
"grad_norm": 0.68359375,
"learning_rate": 0.0008853362734288864,
"loss": 5.8133,
"step": 104000
},
{
"epoch": 5.7607497243660415,
"grad_norm": 0.49609375,
"learning_rate": 0.0008847850055126792,
"loss": 5.7881,
"step": 104500
},
{
"epoch": 5.788313120176406,
"grad_norm": 0.5234375,
"learning_rate": 0.0008842337375964719,
"loss": 5.7775,
"step": 105000
},
{
"epoch": 5.815876515986769,
"grad_norm": 0.59765625,
"learning_rate": 0.0008836824696802646,
"loss": 5.8153,
"step": 105500
},
{
"epoch": 5.843439911797134,
"grad_norm": 0.51953125,
"learning_rate": 0.0008831312017640574,
"loss": 5.8193,
"step": 106000
},
{
"epoch": 5.871003307607497,
"grad_norm": 0.5546875,
"learning_rate": 0.00088257993384785,
"loss": 5.7903,
"step": 106500
},
{
"epoch": 5.8985667034178615,
"grad_norm": 0.390625,
"learning_rate": 0.0008820286659316428,
"loss": 5.8197,
"step": 107000
},
{
"epoch": 5.926130099228224,
"grad_norm": 0.44921875,
"learning_rate": 0.0008814773980154355,
"loss": 5.8029,
"step": 107500
},
{
"epoch": 5.953693495038589,
"grad_norm": 0.443359375,
"learning_rate": 0.0008809261300992282,
"loss": 5.8085,
"step": 108000
},
{
"epoch": 5.981256890848953,
"grad_norm": 0.5078125,
"learning_rate": 0.000880374862183021,
"loss": 5.7913,
"step": 108500
},
{
"epoch": 6.0,
"eval_loss": 5.734777927398682,
"eval_runtime": 3.5058,
"eval_samples_per_second": 83.005,
"eval_steps_per_second": 5.42,
"step": 108840
},
{
"epoch": 6.008820286659317,
"grad_norm": 0.51953125,
"learning_rate": 0.0008798235942668137,
"loss": 5.7969,
"step": 109000
},
{
"epoch": 6.036383682469681,
"grad_norm": 0.86328125,
"learning_rate": 0.0008792723263506064,
"loss": 5.798,
"step": 109500
},
{
"epoch": 6.063947078280044,
"grad_norm": 0.6796875,
"learning_rate": 0.0008787210584343991,
"loss": 5.8031,
"step": 110000
},
{
"epoch": 6.091510474090408,
"grad_norm": 0.61328125,
"learning_rate": 0.0008781697905181919,
"loss": 5.7775,
"step": 110500
},
{
"epoch": 6.119073869900772,
"grad_norm": 0.79296875,
"learning_rate": 0.0008776185226019846,
"loss": 5.7736,
"step": 111000
},
{
"epoch": 6.146637265711136,
"grad_norm": 0.482421875,
"learning_rate": 0.0008770672546857773,
"loss": 5.7873,
"step": 111500
},
{
"epoch": 6.1742006615215,
"grad_norm": 0.498046875,
"learning_rate": 0.00087651598676957,
"loss": 5.7928,
"step": 112000
},
{
"epoch": 6.2017640573318635,
"grad_norm": 0.51171875,
"learning_rate": 0.0008759647188533627,
"loss": 5.7961,
"step": 112500
},
{
"epoch": 6.229327453142227,
"grad_norm": 0.60546875,
"learning_rate": 0.0008754134509371555,
"loss": 5.7866,
"step": 113000
},
{
"epoch": 6.256890848952591,
"grad_norm": 0.58984375,
"learning_rate": 0.0008748621830209482,
"loss": 5.7872,
"step": 113500
},
{
"epoch": 6.284454244762955,
"grad_norm": 0.57421875,
"learning_rate": 0.0008743109151047409,
"loss": 5.803,
"step": 114000
},
{
"epoch": 6.312017640573319,
"grad_norm": 0.453125,
"learning_rate": 0.0008737596471885337,
"loss": 5.8078,
"step": 114500
},
{
"epoch": 6.339581036383683,
"grad_norm": 0.431640625,
"learning_rate": 0.0008732083792723263,
"loss": 5.7968,
"step": 115000
},
{
"epoch": 6.3671444321940465,
"grad_norm": 0.5078125,
"learning_rate": 0.0008726571113561191,
"loss": 5.785,
"step": 115500
},
{
"epoch": 6.39470782800441,
"grad_norm": 0.49609375,
"learning_rate": 0.0008721058434399119,
"loss": 5.7898,
"step": 116000
},
{
"epoch": 6.422271223814774,
"grad_norm": 0.43359375,
"learning_rate": 0.0008715545755237045,
"loss": 5.802,
"step": 116500
},
{
"epoch": 6.449834619625138,
"grad_norm": 0.51171875,
"learning_rate": 0.0008710033076074973,
"loss": 5.7907,
"step": 117000
},
{
"epoch": 6.477398015435502,
"grad_norm": 0.875,
"learning_rate": 0.0008704520396912899,
"loss": 5.7899,
"step": 117500
},
{
"epoch": 6.504961411245866,
"grad_norm": 0.6171875,
"learning_rate": 0.0008699007717750828,
"loss": 5.7908,
"step": 118000
},
{
"epoch": 6.532524807056229,
"grad_norm": 0.396484375,
"learning_rate": 0.0008693495038588755,
"loss": 5.808,
"step": 118500
},
{
"epoch": 6.560088202866593,
"grad_norm": 0.6171875,
"learning_rate": 0.0008687982359426681,
"loss": 5.7799,
"step": 119000
},
{
"epoch": 6.587651598676957,
"grad_norm": 1.0078125,
"learning_rate": 0.0008682469680264609,
"loss": 5.7839,
"step": 119500
},
{
"epoch": 6.615214994487321,
"grad_norm": 1.53125,
"learning_rate": 0.0008676957001102535,
"loss": 5.7823,
"step": 120000
},
{
"epoch": 6.642778390297685,
"grad_norm": 0.37890625,
"learning_rate": 0.0008671444321940464,
"loss": 5.7844,
"step": 120500
},
{
"epoch": 6.6703417861080485,
"grad_norm": 0.82421875,
"learning_rate": 0.0008665931642778391,
"loss": 5.7917,
"step": 121000
},
{
"epoch": 6.697905181918412,
"grad_norm": 0.6640625,
"learning_rate": 0.0008660418963616317,
"loss": 5.8034,
"step": 121500
},
{
"epoch": 6.725468577728776,
"grad_norm": 0.39453125,
"learning_rate": 0.0008654906284454245,
"loss": 5.7769,
"step": 122000
},
{
"epoch": 6.75303197353914,
"grad_norm": 0.490234375,
"learning_rate": 0.0008649393605292172,
"loss": 5.7911,
"step": 122500
},
{
"epoch": 6.780595369349504,
"grad_norm": 0.5078125,
"learning_rate": 0.00086438809261301,
"loss": 5.7873,
"step": 123000
},
{
"epoch": 6.808158765159868,
"grad_norm": 0.76171875,
"learning_rate": 0.0008638368246968027,
"loss": 5.7845,
"step": 123500
},
{
"epoch": 6.835722160970231,
"grad_norm": 0.353515625,
"learning_rate": 0.0008632855567805954,
"loss": 5.8045,
"step": 124000
},
{
"epoch": 6.863285556780595,
"grad_norm": 0.470703125,
"learning_rate": 0.0008627342888643881,
"loss": 5.7967,
"step": 124500
},
{
"epoch": 6.890848952590959,
"grad_norm": 0.6171875,
"learning_rate": 0.0008621830209481808,
"loss": 5.7611,
"step": 125000
},
{
"epoch": 6.918412348401323,
"grad_norm": 0.498046875,
"learning_rate": 0.0008616317530319737,
"loss": 5.7735,
"step": 125500
},
{
"epoch": 6.945975744211687,
"grad_norm": 0.396484375,
"learning_rate": 0.0008610804851157663,
"loss": 5.7777,
"step": 126000
},
{
"epoch": 6.9735391400220506,
"grad_norm": 0.6484375,
"learning_rate": 0.000860529217199559,
"loss": 5.7793,
"step": 126500
},
{
"epoch": 7.0,
"eval_loss": 5.720947742462158,
"eval_runtime": 3.4558,
"eval_samples_per_second": 84.206,
"eval_steps_per_second": 5.498,
"step": 126980
},
{
"epoch": 7.001102535832414,
"grad_norm": 0.98828125,
"learning_rate": 0.0008599779492833517,
"loss": 5.7761,
"step": 127000
},
{
"epoch": 7.028665931642778,
"grad_norm": 0.63671875,
"learning_rate": 0.0008594266813671444,
"loss": 5.7634,
"step": 127500
},
{
"epoch": 7.056229327453142,
"grad_norm": 0.380859375,
"learning_rate": 0.0008588754134509373,
"loss": 5.7837,
"step": 128000
},
{
"epoch": 7.083792723263506,
"grad_norm": 0.515625,
"learning_rate": 0.0008583241455347299,
"loss": 5.7759,
"step": 128500
},
{
"epoch": 7.11135611907387,
"grad_norm": 0.75390625,
"learning_rate": 0.0008577728776185226,
"loss": 5.7737,
"step": 129000
},
{
"epoch": 7.1389195148842335,
"grad_norm": 0.7109375,
"learning_rate": 0.0008572216097023154,
"loss": 5.7793,
"step": 129500
},
{
"epoch": 7.166482910694597,
"grad_norm": 0.53125,
"learning_rate": 0.000856670341786108,
"loss": 5.8033,
"step": 130000
},
{
"epoch": 7.194046306504961,
"grad_norm": 1.09375,
"learning_rate": 0.0008561190738699009,
"loss": 5.7663,
"step": 130500
},
{
"epoch": 7.221609702315325,
"grad_norm": 0.482421875,
"learning_rate": 0.0008555678059536935,
"loss": 5.7625,
"step": 131000
},
{
"epoch": 7.249173098125689,
"grad_norm": 0.39453125,
"learning_rate": 0.0008550165380374862,
"loss": 5.8,
"step": 131500
},
{
"epoch": 7.276736493936053,
"grad_norm": 0.412109375,
"learning_rate": 0.000854465270121279,
"loss": 5.7776,
"step": 132000
},
{
"epoch": 7.304299889746416,
"grad_norm": 0.95703125,
"learning_rate": 0.0008539140022050716,
"loss": 5.7849,
"step": 132500
},
{
"epoch": 7.33186328555678,
"grad_norm": 0.4609375,
"learning_rate": 0.0008533627342888644,
"loss": 5.7772,
"step": 133000
},
{
"epoch": 7.359426681367144,
"grad_norm": 0.412109375,
"learning_rate": 0.0008528114663726572,
"loss": 5.761,
"step": 133500
},
{
"epoch": 7.386990077177508,
"grad_norm": 0.52734375,
"learning_rate": 0.0008522601984564498,
"loss": 5.7731,
"step": 134000
},
{
"epoch": 7.414553472987872,
"grad_norm": 0.6328125,
"learning_rate": 0.0008517089305402426,
"loss": 5.7644,
"step": 134500
},
{
"epoch": 7.4421168687982355,
"grad_norm": 1.125,
"learning_rate": 0.0008511576626240352,
"loss": 5.761,
"step": 135000
},
{
"epoch": 7.4696802646086,
"grad_norm": 0.416015625,
"learning_rate": 0.000850606394707828,
"loss": 5.7774,
"step": 135500
},
{
"epoch": 7.497243660418963,
"grad_norm": 0.326171875,
"learning_rate": 0.0008500551267916208,
"loss": 5.7838,
"step": 136000
},
{
"epoch": 7.524807056229328,
"grad_norm": 0.41796875,
"learning_rate": 0.0008495038588754134,
"loss": 5.7687,
"step": 136500
},
{
"epoch": 7.552370452039691,
"grad_norm": 0.435546875,
"learning_rate": 0.0008489525909592062,
"loss": 5.7818,
"step": 137000
},
{
"epoch": 7.5799338478500555,
"grad_norm": 1.0703125,
"learning_rate": 0.0008484013230429989,
"loss": 5.7693,
"step": 137500
},
{
"epoch": 7.607497243660419,
"grad_norm": 0.5390625,
"learning_rate": 0.0008478500551267916,
"loss": 5.7745,
"step": 138000
},
{
"epoch": 7.635060639470783,
"grad_norm": 0.578125,
"learning_rate": 0.0008472987872105844,
"loss": 5.7658,
"step": 138500
},
{
"epoch": 7.662624035281147,
"grad_norm": 0.609375,
"learning_rate": 0.000846747519294377,
"loss": 5.7618,
"step": 139000
},
{
"epoch": 7.690187431091511,
"grad_norm": 0.451171875,
"learning_rate": 0.0008461962513781698,
"loss": 5.7692,
"step": 139500
},
{
"epoch": 7.717750826901875,
"grad_norm": 0.447265625,
"learning_rate": 0.0008456449834619625,
"loss": 5.7893,
"step": 140000
},
{
"epoch": 7.7453142227122385,
"grad_norm": 0.5546875,
"learning_rate": 0.0008450937155457552,
"loss": 5.7833,
"step": 140500
},
{
"epoch": 7.772877618522602,
"grad_norm": 0.59765625,
"learning_rate": 0.000844542447629548,
"loss": 5.7728,
"step": 141000
},
{
"epoch": 7.800441014332966,
"grad_norm": 0.431640625,
"learning_rate": 0.0008439911797133408,
"loss": 5.7854,
"step": 141500
},
{
"epoch": 7.82800441014333,
"grad_norm": 0.462890625,
"learning_rate": 0.0008434399117971334,
"loss": 5.7749,
"step": 142000
},
{
"epoch": 7.855567805953694,
"grad_norm": 0.5,
"learning_rate": 0.0008428886438809261,
"loss": 5.7706,
"step": 142500
},
{
"epoch": 7.883131201764058,
"grad_norm": 0.37890625,
"learning_rate": 0.0008423373759647189,
"loss": 5.7673,
"step": 143000
},
{
"epoch": 7.910694597574421,
"grad_norm": 0.474609375,
"learning_rate": 0.0008417861080485116,
"loss": 5.7834,
"step": 143500
},
{
"epoch": 7.938257993384785,
"grad_norm": 0.46875,
"learning_rate": 0.0008412348401323044,
"loss": 5.7748,
"step": 144000
},
{
"epoch": 7.965821389195149,
"grad_norm": 0.93359375,
"learning_rate": 0.000840683572216097,
"loss": 5.7908,
"step": 144500
},
{
"epoch": 7.993384785005513,
"grad_norm": 0.53515625,
"learning_rate": 0.0008401323042998897,
"loss": 5.7698,
"step": 145000
},
{
"epoch": 8.0,
"eval_loss": 5.71162223815918,
"eval_runtime": 3.4422,
"eval_samples_per_second": 84.54,
"eval_steps_per_second": 5.52,
"step": 145120
},
{
"epoch": 8.020948180815877,
"grad_norm": 0.490234375,
"learning_rate": 0.0008395810363836825,
"loss": 5.7724,
"step": 145500
},
{
"epoch": 8.04851157662624,
"grad_norm": 0.62109375,
"learning_rate": 0.0008390297684674752,
"loss": 5.7663,
"step": 146000
},
{
"epoch": 8.076074972436604,
"grad_norm": 0.6796875,
"learning_rate": 0.000838478500551268,
"loss": 5.7685,
"step": 146500
},
{
"epoch": 8.103638368246967,
"grad_norm": 0.8359375,
"learning_rate": 0.0008379272326350607,
"loss": 5.7875,
"step": 147000
},
{
"epoch": 8.131201764057332,
"grad_norm": 1.3515625,
"learning_rate": 0.0008373759647188533,
"loss": 5.7763,
"step": 147500
},
{
"epoch": 8.158765159867695,
"grad_norm": 0.416015625,
"learning_rate": 0.0008368246968026461,
"loss": 5.7662,
"step": 148000
},
{
"epoch": 8.18632855567806,
"grad_norm": 0.51953125,
"learning_rate": 0.0008362734288864388,
"loss": 5.7624,
"step": 148500
},
{
"epoch": 8.213891951488423,
"grad_norm": 0.515625,
"learning_rate": 0.0008357221609702316,
"loss": 5.7667,
"step": 149000
},
{
"epoch": 8.241455347298787,
"grad_norm": 0.431640625,
"learning_rate": 0.0008351708930540243,
"loss": 5.7788,
"step": 149500
},
{
"epoch": 8.26901874310915,
"grad_norm": 0.3984375,
"learning_rate": 0.0008346196251378169,
"loss": 5.7647,
"step": 150000
},
{
"epoch": 8.296582138919515,
"grad_norm": 0.71484375,
"learning_rate": 0.0008340683572216097,
"loss": 5.7819,
"step": 150500
},
{
"epoch": 8.32414553472988,
"grad_norm": 0.37109375,
"learning_rate": 0.0008335170893054025,
"loss": 5.7612,
"step": 151000
},
{
"epoch": 8.351708930540243,
"grad_norm": 0.88671875,
"learning_rate": 0.0008329658213891952,
"loss": 5.7775,
"step": 151500
},
{
"epoch": 8.379272326350605,
"grad_norm": 0.46875,
"learning_rate": 0.0008324145534729879,
"loss": 5.7565,
"step": 152000
},
{
"epoch": 8.40683572216097,
"grad_norm": 0.5859375,
"learning_rate": 0.0008318632855567805,
"loss": 5.7515,
"step": 152500
},
{
"epoch": 8.434399117971335,
"grad_norm": 0.609375,
"learning_rate": 0.0008313120176405733,
"loss": 5.7639,
"step": 153000
},
{
"epoch": 8.461962513781698,
"grad_norm": 0.40234375,
"learning_rate": 0.0008307607497243661,
"loss": 5.7595,
"step": 153500
},
{
"epoch": 8.489525909592063,
"grad_norm": 0.416015625,
"learning_rate": 0.0008302094818081588,
"loss": 5.7484,
"step": 154000
},
{
"epoch": 8.517089305402425,
"grad_norm": 0.8671875,
"learning_rate": 0.0008296582138919515,
"loss": 5.7783,
"step": 154500
},
{
"epoch": 8.54465270121279,
"grad_norm": 0.3984375,
"learning_rate": 0.0008291069459757442,
"loss": 5.7618,
"step": 155000
},
{
"epoch": 8.572216097023153,
"grad_norm": 0.55859375,
"learning_rate": 0.0008285556780595369,
"loss": 5.7686,
"step": 155500
},
{
"epoch": 8.599779492833518,
"grad_norm": 0.54296875,
"learning_rate": 0.0008280044101433297,
"loss": 5.7739,
"step": 156000
},
{
"epoch": 8.62734288864388,
"grad_norm": 0.5,
"learning_rate": 0.0008274531422271225,
"loss": 5.7731,
"step": 156500
},
{
"epoch": 8.654906284454245,
"grad_norm": 0.50390625,
"learning_rate": 0.0008269018743109151,
"loss": 5.7755,
"step": 157000
},
{
"epoch": 8.682469680264608,
"grad_norm": 0.40234375,
"learning_rate": 0.0008263506063947078,
"loss": 5.7607,
"step": 157500
},
{
"epoch": 8.710033076074973,
"grad_norm": 0.41015625,
"learning_rate": 0.0008257993384785005,
"loss": 5.7848,
"step": 158000
},
{
"epoch": 8.737596471885336,
"grad_norm": 0.49609375,
"learning_rate": 0.0008252480705622933,
"loss": 5.7626,
"step": 158500
},
{
"epoch": 8.7651598676957,
"grad_norm": 0.44140625,
"learning_rate": 0.0008246968026460861,
"loss": 5.7732,
"step": 159000
},
{
"epoch": 8.792723263506064,
"grad_norm": 0.494140625,
"learning_rate": 0.0008241455347298787,
"loss": 5.7488,
"step": 159500
},
{
"epoch": 8.820286659316428,
"grad_norm": 0.55078125,
"learning_rate": 0.0008235942668136714,
"loss": 5.7689,
"step": 160000
},
{
"epoch": 8.847850055126791,
"grad_norm": 0.765625,
"learning_rate": 0.0008230429988974642,
"loss": 5.7707,
"step": 160500
},
{
"epoch": 8.875413450937156,
"grad_norm": 0.41796875,
"learning_rate": 0.0008224917309812569,
"loss": 5.7448,
"step": 161000
},
{
"epoch": 8.902976846747519,
"grad_norm": 0.4453125,
"learning_rate": 0.0008219404630650497,
"loss": 5.7603,
"step": 161500
},
{
"epoch": 8.930540242557884,
"grad_norm": 0.369140625,
"learning_rate": 0.0008213891951488423,
"loss": 5.7592,
"step": 162000
},
{
"epoch": 8.958103638368247,
"grad_norm": 0.73828125,
"learning_rate": 0.0008208379272326351,
"loss": 5.7537,
"step": 162500
},
{
"epoch": 8.985667034178611,
"grad_norm": 0.359375,
"learning_rate": 0.0008202866593164278,
"loss": 5.758,
"step": 163000
},
{
"epoch": 9.0,
"eval_loss": 5.707642078399658,
"eval_runtime": 3.4079,
"eval_samples_per_second": 85.389,
"eval_steps_per_second": 5.575,
"step": 163260
},
{
"epoch": 9.013230429988974,
"grad_norm": 0.328125,
"learning_rate": 0.0008197353914002205,
"loss": 5.7547,
"step": 163500
},
{
"epoch": 9.040793825799339,
"grad_norm": 0.427734375,
"learning_rate": 0.0008191841234840133,
"loss": 5.7489,
"step": 164000
},
{
"epoch": 9.068357221609702,
"grad_norm": 0.69921875,
"learning_rate": 0.000818632855567806,
"loss": 5.7536,
"step": 164500
},
{
"epoch": 9.095920617420067,
"grad_norm": 0.3515625,
"learning_rate": 0.0008180815876515987,
"loss": 5.7599,
"step": 165000
},
{
"epoch": 9.12348401323043,
"grad_norm": 0.51171875,
"learning_rate": 0.0008175303197353914,
"loss": 5.7676,
"step": 165500
},
{
"epoch": 9.151047409040794,
"grad_norm": 0.56640625,
"learning_rate": 0.0008169790518191842,
"loss": 5.7523,
"step": 166000
},
{
"epoch": 9.178610804851157,
"grad_norm": 0.369140625,
"learning_rate": 0.0008164277839029769,
"loss": 5.7702,
"step": 166500
},
{
"epoch": 9.206174200661522,
"grad_norm": 0.376953125,
"learning_rate": 0.0008158765159867696,
"loss": 5.7238,
"step": 167000
},
{
"epoch": 9.233737596471885,
"grad_norm": 0.34765625,
"learning_rate": 0.0008153252480705623,
"loss": 5.7696,
"step": 167500
},
{
"epoch": 9.26130099228225,
"grad_norm": 0.48828125,
"learning_rate": 0.000814773980154355,
"loss": 5.7566,
"step": 168000
},
{
"epoch": 9.288864388092613,
"grad_norm": 0.439453125,
"learning_rate": 0.0008142227122381478,
"loss": 5.7403,
"step": 168500
},
{
"epoch": 9.316427783902977,
"grad_norm": 0.404296875,
"learning_rate": 0.0008136714443219405,
"loss": 5.752,
"step": 169000
},
{
"epoch": 9.34399117971334,
"grad_norm": 0.3984375,
"learning_rate": 0.0008131201764057332,
"loss": 5.753,
"step": 169500
},
{
"epoch": 9.371554575523705,
"grad_norm": 0.486328125,
"learning_rate": 0.000812568908489526,
"loss": 5.7681,
"step": 170000
},
{
"epoch": 9.399117971334068,
"grad_norm": 0.357421875,
"learning_rate": 0.0008120176405733186,
"loss": 5.7472,
"step": 170500
},
{
"epoch": 9.426681367144432,
"grad_norm": 0.51953125,
"learning_rate": 0.0008114663726571113,
"loss": 5.7753,
"step": 171000
},
{
"epoch": 9.454244762954795,
"grad_norm": 0.380859375,
"learning_rate": 0.0008109151047409042,
"loss": 5.7646,
"step": 171500
},
{
"epoch": 9.48180815876516,
"grad_norm": 0.439453125,
"learning_rate": 0.0008103638368246968,
"loss": 5.7771,
"step": 172000
},
{
"epoch": 9.509371554575523,
"grad_norm": 0.3671875,
"learning_rate": 0.0008098125689084896,
"loss": 5.7628,
"step": 172500
},
{
"epoch": 9.536934950385888,
"grad_norm": 0.349609375,
"learning_rate": 0.0008092613009922822,
"loss": 5.7618,
"step": 173000
},
{
"epoch": 9.56449834619625,
"grad_norm": 0.427734375,
"learning_rate": 0.0008087100330760749,
"loss": 5.7626,
"step": 173500
},
{
"epoch": 9.592061742006615,
"grad_norm": 0.546875,
"learning_rate": 0.0008081587651598678,
"loss": 5.7592,
"step": 174000
},
{
"epoch": 9.619625137816978,
"grad_norm": 0.9609375,
"learning_rate": 0.0008076074972436604,
"loss": 5.7822,
"step": 174500
},
{
"epoch": 9.647188533627343,
"grad_norm": 0.40234375,
"learning_rate": 0.0008070562293274532,
"loss": 5.7712,
"step": 175000
},
{
"epoch": 9.674751929437706,
"grad_norm": 0.44140625,
"learning_rate": 0.0008065049614112459,
"loss": 5.7641,
"step": 175500
},
{
"epoch": 9.70231532524807,
"grad_norm": 0.609375,
"learning_rate": 0.0008059536934950385,
"loss": 5.7498,
"step": 176000
},
{
"epoch": 9.729878721058434,
"grad_norm": 0.609375,
"learning_rate": 0.0008054024255788314,
"loss": 5.7343,
"step": 176500
},
{
"epoch": 9.757442116868798,
"grad_norm": 0.3671875,
"learning_rate": 0.000804851157662624,
"loss": 5.7558,
"step": 177000
},
{
"epoch": 9.785005512679161,
"grad_norm": 0.369140625,
"learning_rate": 0.0008042998897464168,
"loss": 5.7295,
"step": 177500
},
{
"epoch": 9.812568908489526,
"grad_norm": 0.55859375,
"learning_rate": 0.0008037486218302095,
"loss": 5.7506,
"step": 178000
},
{
"epoch": 9.840132304299889,
"grad_norm": 0.447265625,
"learning_rate": 0.0008031973539140021,
"loss": 5.7619,
"step": 178500
},
{
"epoch": 9.867695700110254,
"grad_norm": 0.859375,
"learning_rate": 0.000802646085997795,
"loss": 5.7847,
"step": 179000
},
{
"epoch": 9.895259095920617,
"grad_norm": 0.384765625,
"learning_rate": 0.0008020948180815877,
"loss": 5.7624,
"step": 179500
},
{
"epoch": 9.922822491730981,
"grad_norm": 0.390625,
"learning_rate": 0.0008015435501653804,
"loss": 5.7732,
"step": 180000
},
{
"epoch": 9.950385887541344,
"grad_norm": 0.34375,
"learning_rate": 0.0008009922822491731,
"loss": 5.7425,
"step": 180500
},
{
"epoch": 9.977949283351709,
"grad_norm": 0.45703125,
"learning_rate": 0.0008004410143329657,
"loss": 5.7658,
"step": 181000
},
{
"epoch": 10.0,
"eval_loss": 5.698179244995117,
"eval_runtime": 3.4017,
"eval_samples_per_second": 85.545,
"eval_steps_per_second": 5.585,
"step": 181400
},
{
"epoch": 10.005512679162074,
"grad_norm": 0.357421875,
"learning_rate": 0.0007998897464167586,
"loss": 5.754,
"step": 181500
},
{
"epoch": 10.033076074972437,
"grad_norm": 0.462890625,
"learning_rate": 0.0007993384785005513,
"loss": 5.7548,
"step": 182000
},
{
"epoch": 10.060639470782801,
"grad_norm": 0.353515625,
"learning_rate": 0.000798787210584344,
"loss": 5.7513,
"step": 182500
},
{
"epoch": 10.088202866593164,
"grad_norm": 0.375,
"learning_rate": 0.0007982359426681367,
"loss": 5.7397,
"step": 183000
},
{
"epoch": 10.115766262403529,
"grad_norm": 0.57421875,
"learning_rate": 0.0007976846747519294,
"loss": 5.7576,
"step": 183500
},
{
"epoch": 10.143329658213892,
"grad_norm": 0.345703125,
"learning_rate": 0.0007971334068357222,
"loss": 5.7683,
"step": 184000
},
{
"epoch": 10.170893054024257,
"grad_norm": 0.65234375,
"learning_rate": 0.0007965821389195149,
"loss": 5.7573,
"step": 184500
},
{
"epoch": 10.19845644983462,
"grad_norm": 0.486328125,
"learning_rate": 0.0007960308710033077,
"loss": 5.7413,
"step": 185000
},
{
"epoch": 10.226019845644984,
"grad_norm": 0.419921875,
"learning_rate": 0.0007954796030871003,
"loss": 5.7609,
"step": 185500
},
{
"epoch": 10.253583241455347,
"grad_norm": 0.875,
"learning_rate": 0.0007949283351708931,
"loss": 5.7462,
"step": 186000
},
{
"epoch": 10.281146637265712,
"grad_norm": 0.5,
"learning_rate": 0.0007943770672546858,
"loss": 5.7551,
"step": 186500
},
{
"epoch": 10.308710033076075,
"grad_norm": 0.349609375,
"learning_rate": 0.0007938257993384785,
"loss": 5.7674,
"step": 187000
},
{
"epoch": 10.33627342888644,
"grad_norm": 0.421875,
"learning_rate": 0.0007932745314222713,
"loss": 5.7599,
"step": 187500
},
{
"epoch": 10.363836824696802,
"grad_norm": 0.341796875,
"learning_rate": 0.0007927232635060639,
"loss": 5.7496,
"step": 188000
},
{
"epoch": 10.391400220507167,
"grad_norm": 0.388671875,
"learning_rate": 0.0007921719955898567,
"loss": 5.7392,
"step": 188500
},
{
"epoch": 10.41896361631753,
"grad_norm": 0.5078125,
"learning_rate": 0.0007916207276736495,
"loss": 5.7736,
"step": 189000
},
{
"epoch": 10.446527012127895,
"grad_norm": 0.51171875,
"learning_rate": 0.0007910694597574421,
"loss": 5.7394,
"step": 189500
},
{
"epoch": 10.474090407938258,
"grad_norm": 0.392578125,
"learning_rate": 0.0007905181918412349,
"loss": 5.7425,
"step": 190000
},
{
"epoch": 10.501653803748622,
"grad_norm": 0.39453125,
"learning_rate": 0.0007899669239250275,
"loss": 5.7564,
"step": 190500
},
{
"epoch": 10.529217199558985,
"grad_norm": 0.373046875,
"learning_rate": 0.0007894156560088203,
"loss": 5.7643,
"step": 191000
},
{
"epoch": 10.55678059536935,
"grad_norm": 0.357421875,
"learning_rate": 0.0007888643880926131,
"loss": 5.7533,
"step": 191500
},
{
"epoch": 10.584343991179713,
"grad_norm": 0.478515625,
"learning_rate": 0.0007883131201764057,
"loss": 5.7359,
"step": 192000
},
{
"epoch": 10.611907386990078,
"grad_norm": 0.357421875,
"learning_rate": 0.0007877618522601985,
"loss": 5.7601,
"step": 192500
},
{
"epoch": 10.63947078280044,
"grad_norm": 0.310546875,
"learning_rate": 0.0007872105843439912,
"loss": 5.7627,
"step": 193000
},
{
"epoch": 10.667034178610805,
"grad_norm": 0.3515625,
"learning_rate": 0.0007866593164277839,
"loss": 5.7579,
"step": 193500
},
{
"epoch": 10.694597574421168,
"grad_norm": 0.431640625,
"learning_rate": 0.0007861080485115767,
"loss": 5.7502,
"step": 194000
},
{
"epoch": 10.722160970231533,
"grad_norm": 0.40625,
"learning_rate": 0.0007855567805953693,
"loss": 5.7542,
"step": 194500
},
{
"epoch": 10.749724366041896,
"grad_norm": 0.451171875,
"learning_rate": 0.0007850055126791621,
"loss": 5.7384,
"step": 195000
},
{
"epoch": 10.77728776185226,
"grad_norm": 0.37890625,
"learning_rate": 0.0007844542447629548,
"loss": 5.7489,
"step": 195500
},
{
"epoch": 10.804851157662624,
"grad_norm": 0.359375,
"learning_rate": 0.0007839029768467475,
"loss": 5.7698,
"step": 196000
},
{
"epoch": 10.832414553472988,
"grad_norm": 0.357421875,
"learning_rate": 0.0007833517089305403,
"loss": 5.7565,
"step": 196500
},
{
"epoch": 10.859977949283351,
"grad_norm": 0.3203125,
"learning_rate": 0.000782800441014333,
"loss": 5.7514,
"step": 197000
},
{
"epoch": 10.887541345093716,
"grad_norm": 0.36328125,
"learning_rate": 0.0007822491730981257,
"loss": 5.7497,
"step": 197500
},
{
"epoch": 10.915104740904079,
"grad_norm": 0.5859375,
"learning_rate": 0.0007816979051819184,
"loss": 5.7485,
"step": 198000
},
{
"epoch": 10.942668136714444,
"grad_norm": 0.4609375,
"learning_rate": 0.0007811466372657112,
"loss": 5.7435,
"step": 198500
},
{
"epoch": 10.970231532524807,
"grad_norm": 0.357421875,
"learning_rate": 0.0007805953693495039,
"loss": 5.7511,
"step": 199000
},
{
"epoch": 10.997794928335171,
"grad_norm": 0.47265625,
"learning_rate": 0.0007800441014332966,
"loss": 5.7397,
"step": 199500
},
{
"epoch": 11.0,
"eval_loss": 5.6925530433654785,
"eval_runtime": 3.473,
"eval_samples_per_second": 83.788,
"eval_steps_per_second": 5.471,
"step": 199540
},
{
"epoch": 11.025358324145534,
"grad_norm": 0.39453125,
"learning_rate": 0.0007794928335170893,
"loss": 5.7422,
"step": 200000
},
{
"epoch": 11.052921719955899,
"grad_norm": 1.4609375,
"learning_rate": 0.000778941565600882,
"loss": 5.733,
"step": 200500
},
{
"epoch": 11.080485115766262,
"grad_norm": 0.38671875,
"learning_rate": 0.0007783902976846748,
"loss": 5.7357,
"step": 201000
},
{
"epoch": 11.108048511576627,
"grad_norm": 0.4375,
"learning_rate": 0.0007778390297684675,
"loss": 5.7599,
"step": 201500
},
{
"epoch": 11.13561190738699,
"grad_norm": 0.36328125,
"learning_rate": 0.0007772877618522602,
"loss": 5.7505,
"step": 202000
},
{
"epoch": 11.163175303197354,
"grad_norm": 1.0859375,
"learning_rate": 0.000776736493936053,
"loss": 5.7602,
"step": 202500
},
{
"epoch": 11.190738699007717,
"grad_norm": 0.427734375,
"learning_rate": 0.0007761852260198456,
"loss": 5.7426,
"step": 203000
},
{
"epoch": 11.218302094818082,
"grad_norm": 0.37109375,
"learning_rate": 0.0007756339581036384,
"loss": 5.751,
"step": 203500
},
{
"epoch": 11.245865490628445,
"grad_norm": 0.419921875,
"learning_rate": 0.0007750826901874311,
"loss": 5.7675,
"step": 204000
},
{
"epoch": 11.27342888643881,
"grad_norm": 0.38671875,
"learning_rate": 0.0007745314222712239,
"loss": 5.7414,
"step": 204500
},
{
"epoch": 11.300992282249172,
"grad_norm": 0.421875,
"learning_rate": 0.0007739801543550166,
"loss": 5.7601,
"step": 205000
},
{
"epoch": 11.328555678059537,
"grad_norm": 0.376953125,
"learning_rate": 0.0007734288864388092,
"loss": 5.7351,
"step": 205500
},
{
"epoch": 11.3561190738699,
"grad_norm": 0.328125,
"learning_rate": 0.000772877618522602,
"loss": 5.7413,
"step": 206000
},
{
"epoch": 11.383682469680265,
"grad_norm": 0.53515625,
"learning_rate": 0.0007723263506063948,
"loss": 5.7493,
"step": 206500
},
{
"epoch": 11.411245865490628,
"grad_norm": 0.44140625,
"learning_rate": 0.0007717750826901875,
"loss": 5.7704,
"step": 207000
},
{
"epoch": 11.438809261300992,
"grad_norm": 0.5234375,
"learning_rate": 0.0007712238147739802,
"loss": 5.747,
"step": 207500
},
{
"epoch": 11.466372657111355,
"grad_norm": 0.5,
"learning_rate": 0.0007706725468577728,
"loss": 5.744,
"step": 208000
},
{
"epoch": 11.49393605292172,
"grad_norm": 0.494140625,
"learning_rate": 0.0007701212789415656,
"loss": 5.7392,
"step": 208500
},
{
"epoch": 11.521499448732083,
"grad_norm": 0.3046875,
"learning_rate": 0.0007695700110253583,
"loss": 5.7407,
"step": 209000
},
{
"epoch": 11.549062844542448,
"grad_norm": 0.3203125,
"learning_rate": 0.0007690187431091511,
"loss": 5.7333,
"step": 209500
},
{
"epoch": 11.576626240352812,
"grad_norm": 0.4609375,
"learning_rate": 0.0007684674751929438,
"loss": 5.743,
"step": 210000
},
{
"epoch": 11.604189636163175,
"grad_norm": 0.40234375,
"learning_rate": 0.0007679162072767365,
"loss": 5.7642,
"step": 210500
},
{
"epoch": 11.631753031973538,
"grad_norm": 0.5703125,
"learning_rate": 0.0007673649393605292,
"loss": 5.7351,
"step": 211000
},
{
"epoch": 11.659316427783903,
"grad_norm": 0.455078125,
"learning_rate": 0.0007668136714443219,
"loss": 5.7701,
"step": 211500
},
{
"epoch": 11.686879823594268,
"grad_norm": 0.28515625,
"learning_rate": 0.0007662624035281148,
"loss": 5.7295,
"step": 212000
},
{
"epoch": 11.71444321940463,
"grad_norm": 0.32421875,
"learning_rate": 0.0007657111356119074,
"loss": 5.7499,
"step": 212500
},
{
"epoch": 11.742006615214994,
"grad_norm": 0.3046875,
"learning_rate": 0.0007651598676957001,
"loss": 5.7722,
"step": 213000
},
{
"epoch": 11.769570011025358,
"grad_norm": 0.369140625,
"learning_rate": 0.0007646085997794928,
"loss": 5.7446,
"step": 213500
},
{
"epoch": 11.797133406835723,
"grad_norm": 0.345703125,
"learning_rate": 0.0007640573318632855,
"loss": 5.7524,
"step": 214000
},
{
"epoch": 11.824696802646086,
"grad_norm": 0.419921875,
"learning_rate": 0.0007635060639470784,
"loss": 5.7592,
"step": 214500
},
{
"epoch": 11.85226019845645,
"grad_norm": 0.42578125,
"learning_rate": 0.000762954796030871,
"loss": 5.7532,
"step": 215000
},
{
"epoch": 11.879823594266814,
"grad_norm": 0.3359375,
"learning_rate": 0.0007624035281146637,
"loss": 5.7412,
"step": 215500
},
{
"epoch": 11.907386990077178,
"grad_norm": 0.4453125,
"learning_rate": 0.0007618522601984565,
"loss": 5.7421,
"step": 216000
},
{
"epoch": 11.934950385887541,
"grad_norm": 0.41796875,
"learning_rate": 0.0007613009922822491,
"loss": 5.7383,
"step": 216500
},
{
"epoch": 11.962513781697906,
"grad_norm": 0.341796875,
"learning_rate": 0.000760749724366042,
"loss": 5.7447,
"step": 217000
},
{
"epoch": 11.990077177508269,
"grad_norm": 0.427734375,
"learning_rate": 0.0007601984564498347,
"loss": 5.7552,
"step": 217500
},
{
"epoch": 12.0,
"eval_loss": 5.68997859954834,
"eval_runtime": 3.4588,
"eval_samples_per_second": 84.133,
"eval_steps_per_second": 5.493,
"step": 217680
},
{
"epoch": 12.017640573318634,
"grad_norm": 0.345703125,
"learning_rate": 0.0007596471885336273,
"loss": 5.7476,
"step": 218000
},
{
"epoch": 12.045203969128996,
"grad_norm": 0.447265625,
"learning_rate": 0.0007590959206174201,
"loss": 5.7503,
"step": 218500
},
{
"epoch": 12.072767364939361,
"grad_norm": 0.423828125,
"learning_rate": 0.0007585446527012127,
"loss": 5.7334,
"step": 219000
},
{
"epoch": 12.100330760749724,
"grad_norm": 0.328125,
"learning_rate": 0.0007579933847850056,
"loss": 5.7367,
"step": 219500
},
{
"epoch": 12.127894156560089,
"grad_norm": 0.486328125,
"learning_rate": 0.0007574421168687983,
"loss": 5.7288,
"step": 220000
},
{
"epoch": 12.155457552370452,
"grad_norm": 0.470703125,
"learning_rate": 0.0007568908489525909,
"loss": 5.752,
"step": 220500
},
{
"epoch": 12.183020948180816,
"grad_norm": 0.322265625,
"learning_rate": 0.0007563395810363837,
"loss": 5.7276,
"step": 221000
},
{
"epoch": 12.21058434399118,
"grad_norm": 0.40625,
"learning_rate": 0.0007557883131201763,
"loss": 5.732,
"step": 221500
},
{
"epoch": 12.238147739801544,
"grad_norm": 0.375,
"learning_rate": 0.0007552370452039692,
"loss": 5.7643,
"step": 222000
},
{
"epoch": 12.265711135611907,
"grad_norm": 0.37890625,
"learning_rate": 0.0007546857772877619,
"loss": 5.7374,
"step": 222500
},
{
"epoch": 12.293274531422272,
"grad_norm": 0.421875,
"learning_rate": 0.0007541345093715545,
"loss": 5.7423,
"step": 223000
},
{
"epoch": 12.320837927232635,
"grad_norm": 0.37890625,
"learning_rate": 0.0007535832414553473,
"loss": 5.7593,
"step": 223500
},
{
"epoch": 12.348401323043,
"grad_norm": 0.484375,
"learning_rate": 0.00075303197353914,
"loss": 5.7556,
"step": 224000
},
{
"epoch": 12.375964718853362,
"grad_norm": 0.66015625,
"learning_rate": 0.0007524807056229328,
"loss": 5.7512,
"step": 224500
},
{
"epoch": 12.403528114663727,
"grad_norm": 0.345703125,
"learning_rate": 0.0007519294377067255,
"loss": 5.7309,
"step": 225000
},
{
"epoch": 12.43109151047409,
"grad_norm": 0.3515625,
"learning_rate": 0.0007513781697905182,
"loss": 5.7577,
"step": 225500
},
{
"epoch": 12.458654906284455,
"grad_norm": 0.32421875,
"learning_rate": 0.0007508269018743109,
"loss": 5.7341,
"step": 226000
},
{
"epoch": 12.486218302094818,
"grad_norm": 0.3515625,
"learning_rate": 0.0007502756339581036,
"loss": 5.7458,
"step": 226500
},
{
"epoch": 12.513781697905182,
"grad_norm": 0.48046875,
"learning_rate": 0.0007497243660418965,
"loss": 5.7408,
"step": 227000
},
{
"epoch": 12.541345093715545,
"grad_norm": 0.5625,
"learning_rate": 0.0007491730981256891,
"loss": 5.7453,
"step": 227500
},
{
"epoch": 12.56890848952591,
"grad_norm": 0.42578125,
"learning_rate": 0.0007486218302094819,
"loss": 5.7414,
"step": 228000
},
{
"epoch": 12.596471885336273,
"grad_norm": 0.40234375,
"learning_rate": 0.0007480705622932745,
"loss": 5.7766,
"step": 228500
},
{
"epoch": 12.624035281146638,
"grad_norm": 0.4453125,
"learning_rate": 0.0007475192943770672,
"loss": 5.7368,
"step": 229000
},
{
"epoch": 12.651598676957,
"grad_norm": 0.5859375,
"learning_rate": 0.0007469680264608601,
"loss": 5.7412,
"step": 229500
},
{
"epoch": 12.679162072767365,
"grad_norm": 0.6640625,
"learning_rate": 0.0007464167585446527,
"loss": 5.7527,
"step": 230000
},
{
"epoch": 12.706725468577728,
"grad_norm": 0.33984375,
"learning_rate": 0.0007458654906284455,
"loss": 5.7399,
"step": 230500
},
{
"epoch": 12.734288864388093,
"grad_norm": 0.34765625,
"learning_rate": 0.0007453142227122382,
"loss": 5.7555,
"step": 231000
},
{
"epoch": 12.761852260198456,
"grad_norm": 0.443359375,
"learning_rate": 0.0007447629547960308,
"loss": 5.7398,
"step": 231500
},
{
"epoch": 12.78941565600882,
"grad_norm": 0.38671875,
"learning_rate": 0.0007442116868798237,
"loss": 5.737,
"step": 232000
},
{
"epoch": 12.816979051819184,
"grad_norm": 6.21875,
"learning_rate": 0.0007436604189636163,
"loss": 5.7539,
"step": 232500
},
{
"epoch": 12.844542447629548,
"grad_norm": 0.60546875,
"learning_rate": 0.0007431091510474091,
"loss": 5.7506,
"step": 233000
},
{
"epoch": 12.872105843439911,
"grad_norm": 0.4296875,
"learning_rate": 0.0007425578831312018,
"loss": 5.7503,
"step": 233500
},
{
"epoch": 12.899669239250276,
"grad_norm": 0.34765625,
"learning_rate": 0.0007420066152149944,
"loss": 5.7505,
"step": 234000
},
{
"epoch": 12.927232635060639,
"grad_norm": 0.34375,
"learning_rate": 0.0007414553472987873,
"loss": 5.7385,
"step": 234500
},
{
"epoch": 12.954796030871004,
"grad_norm": 0.419921875,
"learning_rate": 0.00074090407938258,
"loss": 5.737,
"step": 235000
},
{
"epoch": 12.982359426681366,
"grad_norm": 0.451171875,
"learning_rate": 0.0007403528114663727,
"loss": 5.755,
"step": 235500
},
{
"epoch": 13.0,
"eval_loss": 5.689921855926514,
"eval_runtime": 3.4572,
"eval_samples_per_second": 84.171,
"eval_steps_per_second": 5.496,
"step": 235820
},
{
"epoch": 13.009922822491731,
"grad_norm": 0.45703125,
"learning_rate": 0.0007398015435501654,
"loss": 5.7438,
"step": 236000
},
{
"epoch": 13.037486218302094,
"grad_norm": 0.458984375,
"learning_rate": 0.000739250275633958,
"loss": 5.7433,
"step": 236500
},
{
"epoch": 13.065049614112459,
"grad_norm": 0.37109375,
"learning_rate": 0.0007386990077177509,
"loss": 5.7426,
"step": 237000
},
{
"epoch": 13.092613009922822,
"grad_norm": 0.486328125,
"learning_rate": 0.0007381477398015436,
"loss": 5.7621,
"step": 237500
},
{
"epoch": 13.120176405733186,
"grad_norm": 0.65234375,
"learning_rate": 0.0007375964718853363,
"loss": 5.722,
"step": 238000
},
{
"epoch": 13.14773980154355,
"grad_norm": 0.47265625,
"learning_rate": 0.000737045203969129,
"loss": 5.7348,
"step": 238500
},
{
"epoch": 13.175303197353914,
"grad_norm": 0.98046875,
"learning_rate": 0.0007364939360529217,
"loss": 5.7326,
"step": 239000
},
{
"epoch": 13.202866593164277,
"grad_norm": 0.53125,
"learning_rate": 0.0007359426681367145,
"loss": 5.747,
"step": 239500
},
{
"epoch": 13.230429988974642,
"grad_norm": 0.3046875,
"learning_rate": 0.0007353914002205072,
"loss": 5.7548,
"step": 240000
},
{
"epoch": 13.257993384785005,
"grad_norm": 0.404296875,
"learning_rate": 0.0007348401323043,
"loss": 5.7422,
"step": 240500
},
{
"epoch": 13.28555678059537,
"grad_norm": 0.71875,
"learning_rate": 0.0007342888643880926,
"loss": 5.737,
"step": 241000
},
{
"epoch": 13.313120176405732,
"grad_norm": 0.453125,
"learning_rate": 0.0007337375964718853,
"loss": 5.7167,
"step": 241500
},
{
"epoch": 13.340683572216097,
"grad_norm": 0.30859375,
"learning_rate": 0.0007331863285556781,
"loss": 5.7299,
"step": 242000
},
{
"epoch": 13.368246968026462,
"grad_norm": 0.34375,
"learning_rate": 0.0007326350606394708,
"loss": 5.7564,
"step": 242500
},
{
"epoch": 13.395810363836825,
"grad_norm": 0.466796875,
"learning_rate": 0.0007320837927232636,
"loss": 5.7445,
"step": 243000
},
{
"epoch": 13.42337375964719,
"grad_norm": 0.412109375,
"learning_rate": 0.0007315325248070562,
"loss": 5.753,
"step": 243500
},
{
"epoch": 13.450937155457552,
"grad_norm": 0.380859375,
"learning_rate": 0.0007309812568908489,
"loss": 5.7441,
"step": 244000
},
{
"epoch": 13.478500551267917,
"grad_norm": 0.58203125,
"learning_rate": 0.0007304299889746418,
"loss": 5.7416,
"step": 244500
},
{
"epoch": 13.50606394707828,
"grad_norm": 0.3359375,
"learning_rate": 0.0007298787210584344,
"loss": 5.7404,
"step": 245000
},
{
"epoch": 13.533627342888645,
"grad_norm": 0.376953125,
"learning_rate": 0.0007293274531422272,
"loss": 5.7318,
"step": 245500
},
{
"epoch": 13.561190738699008,
"grad_norm": 0.431640625,
"learning_rate": 0.0007287761852260198,
"loss": 5.7366,
"step": 246000
},
{
"epoch": 13.588754134509372,
"grad_norm": 0.396484375,
"learning_rate": 0.0007282249173098125,
"loss": 5.7395,
"step": 246500
},
{
"epoch": 13.616317530319735,
"grad_norm": 0.41015625,
"learning_rate": 0.0007276736493936053,
"loss": 5.7366,
"step": 247000
},
{
"epoch": 13.6438809261301,
"grad_norm": 0.43359375,
"learning_rate": 0.000727122381477398,
"loss": 5.7624,
"step": 247500
},
{
"epoch": 13.671444321940463,
"grad_norm": 0.30859375,
"learning_rate": 0.0007265711135611908,
"loss": 5.751,
"step": 248000
},
{
"epoch": 13.699007717750828,
"grad_norm": 0.3828125,
"learning_rate": 0.0007260198456449835,
"loss": 5.7418,
"step": 248500
},
{
"epoch": 13.72657111356119,
"grad_norm": 0.3671875,
"learning_rate": 0.0007254685777287761,
"loss": 5.7474,
"step": 249000
},
{
"epoch": 13.754134509371555,
"grad_norm": 0.384765625,
"learning_rate": 0.0007249173098125689,
"loss": 5.7553,
"step": 249500
},
{
"epoch": 13.781697905181918,
"grad_norm": 0.375,
"learning_rate": 0.0007243660418963616,
"loss": 5.7491,
"step": 250000
},
{
"epoch": 13.809261300992283,
"grad_norm": 0.4140625,
"learning_rate": 0.0007238147739801544,
"loss": 5.7412,
"step": 250500
},
{
"epoch": 13.836824696802646,
"grad_norm": 0.357421875,
"learning_rate": 0.0007232635060639471,
"loss": 5.7366,
"step": 251000
},
{
"epoch": 13.86438809261301,
"grad_norm": 1.0078125,
"learning_rate": 0.0007227122381477398,
"loss": 5.7245,
"step": 251500
},
{
"epoch": 13.891951488423373,
"grad_norm": 0.328125,
"learning_rate": 0.0007221609702315325,
"loss": 5.7421,
"step": 252000
},
{
"epoch": 13.919514884233738,
"grad_norm": 0.94921875,
"learning_rate": 0.0007216097023153253,
"loss": 5.7628,
"step": 252500
},
{
"epoch": 13.947078280044101,
"grad_norm": 0.41015625,
"learning_rate": 0.000721058434399118,
"loss": 5.7538,
"step": 253000
},
{
"epoch": 13.974641675854466,
"grad_norm": 0.98828125,
"learning_rate": 0.0007205071664829107,
"loss": 5.7307,
"step": 253500
},
{
"epoch": 14.0,
"eval_loss": 5.6859917640686035,
"eval_runtime": 3.4223,
"eval_samples_per_second": 85.03,
"eval_steps_per_second": 5.552,
"step": 253960
},
{
"epoch": 14.002205071664829,
"grad_norm": 0.64453125,
"learning_rate": 0.0007199558985667035,
"loss": 5.7491,
"step": 254000
},
{
"epoch": 14.029768467475193,
"grad_norm": 0.376953125,
"learning_rate": 0.0007194046306504961,
"loss": 5.7406,
"step": 254500
},
{
"epoch": 14.057331863285556,
"grad_norm": 0.466796875,
"learning_rate": 0.0007188533627342889,
"loss": 5.7294,
"step": 255000
},
{
"epoch": 14.084895259095921,
"grad_norm": 0.75390625,
"learning_rate": 0.0007183020948180816,
"loss": 5.7418,
"step": 255500
},
{
"epoch": 14.112458654906284,
"grad_norm": 0.4296875,
"learning_rate": 0.0007177508269018743,
"loss": 5.7267,
"step": 256000
},
{
"epoch": 14.140022050716649,
"grad_norm": 0.498046875,
"learning_rate": 0.0007171995589856671,
"loss": 5.7439,
"step": 256500
},
{
"epoch": 14.167585446527012,
"grad_norm": 0.35546875,
"learning_rate": 0.0007166482910694597,
"loss": 5.7512,
"step": 257000
},
{
"epoch": 14.195148842337376,
"grad_norm": 0.365234375,
"learning_rate": 0.0007160970231532525,
"loss": 5.7419,
"step": 257500
},
{
"epoch": 14.22271223814774,
"grad_norm": 0.365234375,
"learning_rate": 0.0007155457552370453,
"loss": 5.7306,
"step": 258000
},
{
"epoch": 14.250275633958104,
"grad_norm": 0.8125,
"learning_rate": 0.0007149944873208379,
"loss": 5.7509,
"step": 258500
},
{
"epoch": 14.277839029768467,
"grad_norm": 0.58984375,
"learning_rate": 0.0007144432194046307,
"loss": 5.7601,
"step": 259000
},
{
"epoch": 14.305402425578832,
"grad_norm": 0.46484375,
"learning_rate": 0.0007138919514884233,
"loss": 5.7511,
"step": 259500
},
{
"epoch": 14.332965821389195,
"grad_norm": 0.388671875,
"learning_rate": 0.0007133406835722161,
"loss": 5.7343,
"step": 260000
},
{
"epoch": 14.36052921719956,
"grad_norm": 0.3203125,
"learning_rate": 0.0007127894156560089,
"loss": 5.7474,
"step": 260500
},
{
"epoch": 14.388092613009922,
"grad_norm": 0.38671875,
"learning_rate": 0.0007122381477398015,
"loss": 5.7431,
"step": 261000
},
{
"epoch": 14.415656008820287,
"grad_norm": 0.5234375,
"learning_rate": 0.0007116868798235943,
"loss": 5.7377,
"step": 261500
},
{
"epoch": 14.44321940463065,
"grad_norm": 0.369140625,
"learning_rate": 0.000711135611907387,
"loss": 5.7433,
"step": 262000
},
{
"epoch": 14.470782800441015,
"grad_norm": 0.95703125,
"learning_rate": 0.0007105843439911797,
"loss": 5.7341,
"step": 262500
},
{
"epoch": 14.498346196251378,
"grad_norm": 0.380859375,
"learning_rate": 0.0007100330760749725,
"loss": 5.7479,
"step": 263000
},
{
"epoch": 14.525909592061742,
"grad_norm": 0.42578125,
"learning_rate": 0.0007094818081587651,
"loss": 5.7299,
"step": 263500
},
{
"epoch": 14.553472987872105,
"grad_norm": 0.341796875,
"learning_rate": 0.0007089305402425579,
"loss": 5.7444,
"step": 264000
},
{
"epoch": 14.58103638368247,
"grad_norm": 0.376953125,
"learning_rate": 0.0007083792723263506,
"loss": 5.7349,
"step": 264500
},
{
"epoch": 14.608599779492833,
"grad_norm": 0.443359375,
"learning_rate": 0.0007078280044101433,
"loss": 5.736,
"step": 265000
},
{
"epoch": 14.636163175303198,
"grad_norm": 1.109375,
"learning_rate": 0.0007072767364939361,
"loss": 5.7253,
"step": 265500
},
{
"epoch": 14.66372657111356,
"grad_norm": 0.376953125,
"learning_rate": 0.0007067254685777288,
"loss": 5.7351,
"step": 266000
},
{
"epoch": 14.691289966923925,
"grad_norm": 0.5703125,
"learning_rate": 0.0007061742006615215,
"loss": 5.7491,
"step": 266500
},
{
"epoch": 14.718853362734288,
"grad_norm": 0.361328125,
"learning_rate": 0.0007056229327453142,
"loss": 5.7343,
"step": 267000
},
{
"epoch": 14.746416758544653,
"grad_norm": 0.376953125,
"learning_rate": 0.000705071664829107,
"loss": 5.7302,
"step": 267500
},
{
"epoch": 14.773980154355016,
"grad_norm": 0.359375,
"learning_rate": 0.0007045203969128997,
"loss": 5.7474,
"step": 268000
},
{
"epoch": 14.80154355016538,
"grad_norm": 0.46875,
"learning_rate": 0.0007039691289966924,
"loss": 5.73,
"step": 268500
},
{
"epoch": 14.829106945975743,
"grad_norm": 0.357421875,
"learning_rate": 0.0007034178610804851,
"loss": 5.737,
"step": 269000
},
{
"epoch": 14.856670341786108,
"grad_norm": 0.35546875,
"learning_rate": 0.0007028665931642778,
"loss": 5.7352,
"step": 269500
},
{
"epoch": 14.884233737596471,
"grad_norm": 0.49609375,
"learning_rate": 0.0007023153252480707,
"loss": 5.7386,
"step": 270000
},
{
"epoch": 14.911797133406836,
"grad_norm": 0.3828125,
"learning_rate": 0.0007017640573318633,
"loss": 5.7437,
"step": 270500
},
{
"epoch": 14.9393605292172,
"grad_norm": 0.328125,
"learning_rate": 0.000701212789415656,
"loss": 5.7477,
"step": 271000
},
{
"epoch": 14.966923925027563,
"grad_norm": 0.41015625,
"learning_rate": 0.0007006615214994488,
"loss": 5.7491,
"step": 271500
},
{
"epoch": 14.994487320837926,
"grad_norm": 0.314453125,
"learning_rate": 0.0007001102535832414,
"loss": 5.7383,
"step": 272000
},
{
"epoch": 15.0,
"eval_loss": 5.684328079223633,
"eval_runtime": 3.4544,
"eval_samples_per_second": 84.241,
"eval_steps_per_second": 5.5,
"step": 272100
},
{
"epoch": 15.022050716648291,
"grad_norm": 0.53515625,
"learning_rate": 0.0006995589856670343,
"loss": 5.7559,
"step": 272500
},
{
"epoch": 15.049614112458656,
"grad_norm": 0.337890625,
"learning_rate": 0.000699007717750827,
"loss": 5.7207,
"step": 273000
},
{
"epoch": 15.077177508269019,
"grad_norm": 0.46875,
"learning_rate": 0.0006984564498346196,
"loss": 5.7345,
"step": 273500
},
{
"epoch": 15.104740904079383,
"grad_norm": 0.365234375,
"learning_rate": 0.0006979051819184124,
"loss": 5.7125,
"step": 274000
},
{
"epoch": 15.132304299889746,
"grad_norm": 1.3671875,
"learning_rate": 0.000697353914002205,
"loss": 5.7131,
"step": 274500
},
{
"epoch": 15.159867695700111,
"grad_norm": 0.3828125,
"learning_rate": 0.0006968026460859979,
"loss": 5.7542,
"step": 275000
},
{
"epoch": 15.187431091510474,
"grad_norm": 0.73828125,
"learning_rate": 0.0006962513781697906,
"loss": 5.7501,
"step": 275500
},
{
"epoch": 15.214994487320839,
"grad_norm": 0.373046875,
"learning_rate": 0.0006957001102535832,
"loss": 5.7513,
"step": 276000
},
{
"epoch": 15.242557883131202,
"grad_norm": 0.396484375,
"learning_rate": 0.000695148842337376,
"loss": 5.7289,
"step": 276500
},
{
"epoch": 15.270121278941566,
"grad_norm": 0.33984375,
"learning_rate": 0.0006945975744211686,
"loss": 5.7345,
"step": 277000
},
{
"epoch": 15.29768467475193,
"grad_norm": 0.3828125,
"learning_rate": 0.0006940463065049615,
"loss": 5.732,
"step": 277500
},
{
"epoch": 15.325248070562294,
"grad_norm": 0.326171875,
"learning_rate": 0.0006934950385887542,
"loss": 5.7349,
"step": 278000
},
{
"epoch": 15.352811466372657,
"grad_norm": 0.482421875,
"learning_rate": 0.0006929437706725468,
"loss": 5.7272,
"step": 278500
},
{
"epoch": 15.380374862183022,
"grad_norm": 0.322265625,
"learning_rate": 0.0006923925027563396,
"loss": 5.7469,
"step": 279000
},
{
"epoch": 15.407938257993385,
"grad_norm": 0.3125,
"learning_rate": 0.0006918412348401323,
"loss": 5.7411,
"step": 279500
},
{
"epoch": 15.43550165380375,
"grad_norm": 0.341796875,
"learning_rate": 0.0006912899669239251,
"loss": 5.7562,
"step": 280000
},
{
"epoch": 15.463065049614112,
"grad_norm": 0.365234375,
"learning_rate": 0.0006907386990077178,
"loss": 5.7441,
"step": 280500
},
{
"epoch": 15.490628445424477,
"grad_norm": 0.322265625,
"learning_rate": 0.0006901874310915105,
"loss": 5.7325,
"step": 281000
},
{
"epoch": 15.51819184123484,
"grad_norm": 0.85546875,
"learning_rate": 0.0006896361631753032,
"loss": 5.7548,
"step": 281500
},
{
"epoch": 15.545755237045205,
"grad_norm": 0.40234375,
"learning_rate": 0.0006890848952590959,
"loss": 5.7274,
"step": 282000
},
{
"epoch": 15.573318632855568,
"grad_norm": 0.341796875,
"learning_rate": 0.0006885336273428888,
"loss": 5.7324,
"step": 282500
},
{
"epoch": 15.600882028665932,
"grad_norm": 0.78125,
"learning_rate": 0.0006879823594266814,
"loss": 5.7302,
"step": 283000
},
{
"epoch": 15.628445424476295,
"grad_norm": 0.3984375,
"learning_rate": 0.0006874310915104741,
"loss": 5.7339,
"step": 283500
},
{
"epoch": 15.65600882028666,
"grad_norm": 0.36328125,
"learning_rate": 0.0006868798235942668,
"loss": 5.7307,
"step": 284000
},
{
"epoch": 15.683572216097023,
"grad_norm": 0.416015625,
"learning_rate": 0.0006863285556780595,
"loss": 5.7437,
"step": 284500
},
{
"epoch": 15.711135611907387,
"grad_norm": 0.41015625,
"learning_rate": 0.0006857772877618523,
"loss": 5.7391,
"step": 285000
},
{
"epoch": 15.73869900771775,
"grad_norm": 0.3828125,
"learning_rate": 0.000685226019845645,
"loss": 5.7501,
"step": 285500
},
{
"epoch": 15.766262403528115,
"grad_norm": 0.45703125,
"learning_rate": 0.0006846747519294377,
"loss": 5.7547,
"step": 286000
},
{
"epoch": 15.793825799338478,
"grad_norm": 0.3671875,
"learning_rate": 0.0006841234840132305,
"loss": 5.7367,
"step": 286500
},
{
"epoch": 15.821389195148843,
"grad_norm": 0.375,
"learning_rate": 0.0006835722160970231,
"loss": 5.7488,
"step": 287000
},
{
"epoch": 15.848952590959206,
"grad_norm": 0.29296875,
"learning_rate": 0.0006830209481808159,
"loss": 5.7372,
"step": 287500
},
{
"epoch": 15.87651598676957,
"grad_norm": 0.314453125,
"learning_rate": 0.0006824696802646086,
"loss": 5.7485,
"step": 288000
},
{
"epoch": 15.904079382579933,
"grad_norm": 0.3984375,
"learning_rate": 0.0006819184123484013,
"loss": 5.7483,
"step": 288500
},
{
"epoch": 15.931642778390298,
"grad_norm": 0.486328125,
"learning_rate": 0.0006813671444321941,
"loss": 5.7407,
"step": 289000
},
{
"epoch": 15.959206174200661,
"grad_norm": 0.322265625,
"learning_rate": 0.0006808158765159867,
"loss": 5.7061,
"step": 289500
},
{
"epoch": 15.986769570011026,
"grad_norm": 0.453125,
"learning_rate": 0.0006802646085997795,
"loss": 5.7402,
"step": 290000
},
{
"epoch": 16.0,
"eval_loss": 5.680827617645264,
"eval_runtime": 3.4293,
"eval_samples_per_second": 84.857,
"eval_steps_per_second": 5.54,
"step": 290240
},
{
"epoch": 16.01433296582139,
"grad_norm": 0.310546875,
"learning_rate": 0.0006797133406835723,
"loss": 5.7171,
"step": 290500
},
{
"epoch": 16.041896361631753,
"grad_norm": 0.353515625,
"learning_rate": 0.0006791620727673649,
"loss": 5.7378,
"step": 291000
},
{
"epoch": 16.069459757442118,
"grad_norm": 0.373046875,
"learning_rate": 0.0006786108048511577,
"loss": 5.7238,
"step": 291500
},
{
"epoch": 16.09702315325248,
"grad_norm": 0.388671875,
"learning_rate": 0.0006780595369349503,
"loss": 5.7174,
"step": 292000
},
{
"epoch": 16.124586549062844,
"grad_norm": 0.330078125,
"learning_rate": 0.0006775082690187431,
"loss": 5.7536,
"step": 292500
},
{
"epoch": 16.15214994487321,
"grad_norm": 0.365234375,
"learning_rate": 0.0006769570011025359,
"loss": 5.7398,
"step": 293000
},
{
"epoch": 16.179713340683573,
"grad_norm": 0.3828125,
"learning_rate": 0.0006764057331863286,
"loss": 5.7189,
"step": 293500
},
{
"epoch": 16.207276736493935,
"grad_norm": 0.419921875,
"learning_rate": 0.0006758544652701213,
"loss": 5.7359,
"step": 294000
},
{
"epoch": 16.2348401323043,
"grad_norm": 0.458984375,
"learning_rate": 0.000675303197353914,
"loss": 5.723,
"step": 294500
},
{
"epoch": 16.262403528114664,
"grad_norm": 0.453125,
"learning_rate": 0.0006747519294377067,
"loss": 5.7319,
"step": 295000
},
{
"epoch": 16.28996692392503,
"grad_norm": 0.447265625,
"learning_rate": 0.0006742006615214995,
"loss": 5.7183,
"step": 295500
},
{
"epoch": 16.31753031973539,
"grad_norm": 0.322265625,
"learning_rate": 0.0006736493936052923,
"loss": 5.7189,
"step": 296000
},
{
"epoch": 16.345093715545755,
"grad_norm": 0.44140625,
"learning_rate": 0.0006730981256890849,
"loss": 5.7545,
"step": 296500
},
{
"epoch": 16.37265711135612,
"grad_norm": 0.490234375,
"learning_rate": 0.0006725468577728776,
"loss": 5.7382,
"step": 297000
},
{
"epoch": 16.400220507166484,
"grad_norm": 0.40234375,
"learning_rate": 0.0006719955898566703,
"loss": 5.7488,
"step": 297500
},
{
"epoch": 16.427783902976845,
"grad_norm": 0.388671875,
"learning_rate": 0.0006714443219404631,
"loss": 5.7106,
"step": 298000
},
{
"epoch": 16.45534729878721,
"grad_norm": 0.490234375,
"learning_rate": 0.0006708930540242559,
"loss": 5.7385,
"step": 298500
},
{
"epoch": 16.482910694597575,
"grad_norm": 0.435546875,
"learning_rate": 0.0006703417861080485,
"loss": 5.7501,
"step": 299000
},
{
"epoch": 16.51047409040794,
"grad_norm": 0.392578125,
"learning_rate": 0.0006697905181918412,
"loss": 5.7298,
"step": 299500
},
{
"epoch": 16.5380374862183,
"grad_norm": 0.41015625,
"learning_rate": 0.000669239250275634,
"loss": 5.7651,
"step": 300000
},
{
"epoch": 16.565600882028665,
"grad_norm": 0.306640625,
"learning_rate": 0.0006686879823594267,
"loss": 5.7334,
"step": 300500
},
{
"epoch": 16.59316427783903,
"grad_norm": 0.50390625,
"learning_rate": 0.0006681367144432195,
"loss": 5.7408,
"step": 301000
},
{
"epoch": 16.620727673649395,
"grad_norm": 0.6484375,
"learning_rate": 0.0006675854465270121,
"loss": 5.7507,
"step": 301500
},
{
"epoch": 16.64829106945976,
"grad_norm": 0.37890625,
"learning_rate": 0.0006670341786108048,
"loss": 5.7275,
"step": 302000
},
{
"epoch": 16.67585446527012,
"grad_norm": 0.396484375,
"learning_rate": 0.0006664829106945976,
"loss": 5.7235,
"step": 302500
},
{
"epoch": 16.703417861080485,
"grad_norm": 0.48828125,
"learning_rate": 0.0006659316427783903,
"loss": 5.7495,
"step": 303000
},
{
"epoch": 16.73098125689085,
"grad_norm": 0.6171875,
"learning_rate": 0.0006653803748621831,
"loss": 5.7496,
"step": 303500
},
{
"epoch": 16.75854465270121,
"grad_norm": 0.388671875,
"learning_rate": 0.0006648291069459758,
"loss": 5.7355,
"step": 304000
},
{
"epoch": 16.786108048511576,
"grad_norm": 0.51953125,
"learning_rate": 0.0006642778390297684,
"loss": 5.7187,
"step": 304500
},
{
"epoch": 16.81367144432194,
"grad_norm": 0.359375,
"learning_rate": 0.0006637265711135612,
"loss": 5.7352,
"step": 305000
},
{
"epoch": 16.841234840132305,
"grad_norm": 0.341796875,
"learning_rate": 0.000663175303197354,
"loss": 5.7352,
"step": 305500
},
{
"epoch": 16.86879823594267,
"grad_norm": 0.478515625,
"learning_rate": 0.0006626240352811467,
"loss": 5.7216,
"step": 306000
},
{
"epoch": 16.89636163175303,
"grad_norm": 0.3203125,
"learning_rate": 0.0006620727673649394,
"loss": 5.735,
"step": 306500
},
{
"epoch": 16.923925027563396,
"grad_norm": 0.36328125,
"learning_rate": 0.000661521499448732,
"loss": 5.7457,
"step": 307000
},
{
"epoch": 16.95148842337376,
"grad_norm": 0.392578125,
"learning_rate": 0.0006609702315325248,
"loss": 5.7256,
"step": 307500
},
{
"epoch": 16.979051819184125,
"grad_norm": 0.31640625,
"learning_rate": 0.0006604189636163176,
"loss": 5.724,
"step": 308000
},
{
"epoch": 17.0,
"eval_loss": 5.677351951599121,
"eval_runtime": 3.5434,
"eval_samples_per_second": 82.125,
"eval_steps_per_second": 5.362,
"step": 308380
},
{
"epoch": 17.006615214994486,
"grad_norm": 0.4765625,
"learning_rate": 0.0006598676957001103,
"loss": 5.7348,
"step": 308500
},
{
"epoch": 17.03417861080485,
"grad_norm": 0.60546875,
"learning_rate": 0.000659316427783903,
"loss": 5.7402,
"step": 309000
},
{
"epoch": 17.061742006615216,
"grad_norm": 0.390625,
"learning_rate": 0.0006587651598676956,
"loss": 5.7306,
"step": 309500
},
{
"epoch": 17.08930540242558,
"grad_norm": 0.4296875,
"learning_rate": 0.0006582138919514884,
"loss": 5.7248,
"step": 310000
},
{
"epoch": 17.11686879823594,
"grad_norm": 0.56640625,
"learning_rate": 0.0006576626240352812,
"loss": 5.7285,
"step": 310500
},
{
"epoch": 17.144432194046306,
"grad_norm": 0.369140625,
"learning_rate": 0.0006571113561190739,
"loss": 5.7293,
"step": 311000
},
{
"epoch": 17.17199558985667,
"grad_norm": 0.435546875,
"learning_rate": 0.0006565600882028666,
"loss": 5.7139,
"step": 311500
},
{
"epoch": 17.199558985667036,
"grad_norm": 0.51171875,
"learning_rate": 0.0006560088202866593,
"loss": 5.726,
"step": 312000
},
{
"epoch": 17.227122381477397,
"grad_norm": 0.279296875,
"learning_rate": 0.000655457552370452,
"loss": 5.731,
"step": 312500
},
{
"epoch": 17.25468577728776,
"grad_norm": 0.408203125,
"learning_rate": 0.0006549062844542448,
"loss": 5.7353,
"step": 313000
},
{
"epoch": 17.282249173098126,
"grad_norm": 0.376953125,
"learning_rate": 0.0006543550165380376,
"loss": 5.737,
"step": 313500
},
{
"epoch": 17.30981256890849,
"grad_norm": 0.388671875,
"learning_rate": 0.0006538037486218302,
"loss": 5.7319,
"step": 314000
},
{
"epoch": 17.337375964718852,
"grad_norm": 0.3671875,
"learning_rate": 0.000653252480705623,
"loss": 5.7445,
"step": 314500
},
{
"epoch": 17.364939360529217,
"grad_norm": 0.470703125,
"learning_rate": 0.0006527012127894156,
"loss": 5.7415,
"step": 315000
},
{
"epoch": 17.39250275633958,
"grad_norm": 0.353515625,
"learning_rate": 0.0006521499448732084,
"loss": 5.7488,
"step": 315500
},
{
"epoch": 17.420066152149946,
"grad_norm": 0.392578125,
"learning_rate": 0.0006515986769570012,
"loss": 5.7302,
"step": 316000
},
{
"epoch": 17.447629547960307,
"grad_norm": 0.55859375,
"learning_rate": 0.0006510474090407938,
"loss": 5.7229,
"step": 316500
},
{
"epoch": 17.475192943770672,
"grad_norm": 0.359375,
"learning_rate": 0.0006504961411245866,
"loss": 5.7164,
"step": 317000
},
{
"epoch": 17.502756339581037,
"grad_norm": 0.322265625,
"learning_rate": 0.0006499448732083793,
"loss": 5.7286,
"step": 317500
},
{
"epoch": 17.5303197353914,
"grad_norm": 0.30859375,
"learning_rate": 0.000649393605292172,
"loss": 5.7334,
"step": 318000
},
{
"epoch": 17.557883131201763,
"grad_norm": 0.73046875,
"learning_rate": 0.0006488423373759648,
"loss": 5.7309,
"step": 318500
},
{
"epoch": 17.585446527012127,
"grad_norm": 0.349609375,
"learning_rate": 0.0006482910694597574,
"loss": 5.7252,
"step": 319000
},
{
"epoch": 17.613009922822492,
"grad_norm": 0.32421875,
"learning_rate": 0.0006477398015435502,
"loss": 5.7413,
"step": 319500
},
{
"epoch": 17.640573318632857,
"grad_norm": 0.3984375,
"learning_rate": 0.0006471885336273429,
"loss": 5.732,
"step": 320000
},
{
"epoch": 17.668136714443218,
"grad_norm": 0.396484375,
"learning_rate": 0.0006466372657111356,
"loss": 5.7131,
"step": 320500
},
{
"epoch": 17.695700110253583,
"grad_norm": 0.5,
"learning_rate": 0.0006460859977949284,
"loss": 5.7292,
"step": 321000
},
{
"epoch": 17.723263506063947,
"grad_norm": 0.30859375,
"learning_rate": 0.0006455347298787211,
"loss": 5.7196,
"step": 321500
},
{
"epoch": 17.750826901874312,
"grad_norm": 0.427734375,
"learning_rate": 0.0006449834619625138,
"loss": 5.751,
"step": 322000
},
{
"epoch": 17.778390297684673,
"grad_norm": 0.3515625,
"learning_rate": 0.0006444321940463065,
"loss": 5.7218,
"step": 322500
},
{
"epoch": 17.805953693495038,
"grad_norm": 0.357421875,
"learning_rate": 0.0006438809261300991,
"loss": 5.7297,
"step": 323000
},
{
"epoch": 17.833517089305403,
"grad_norm": 0.55078125,
"learning_rate": 0.000643329658213892,
"loss": 5.7535,
"step": 323500
},
{
"epoch": 17.861080485115767,
"grad_norm": 1.1875,
"learning_rate": 0.0006427783902976847,
"loss": 5.7217,
"step": 324000
},
{
"epoch": 17.88864388092613,
"grad_norm": 0.43359375,
"learning_rate": 0.0006422271223814774,
"loss": 5.7584,
"step": 324500
},
{
"epoch": 17.916207276736493,
"grad_norm": 0.68359375,
"learning_rate": 0.0006416758544652701,
"loss": 5.7269,
"step": 325000
},
{
"epoch": 17.943770672546858,
"grad_norm": 0.310546875,
"learning_rate": 0.0006411245865490628,
"loss": 5.7163,
"step": 325500
},
{
"epoch": 17.971334068357223,
"grad_norm": 0.40234375,
"learning_rate": 0.0006405733186328556,
"loss": 5.7437,
"step": 326000
},
{
"epoch": 17.998897464167584,
"grad_norm": 0.33203125,
"learning_rate": 0.0006400220507166483,
"loss": 5.7127,
"step": 326500
},
{
"epoch": 18.0,
"eval_loss": 5.67610502243042,
"eval_runtime": 3.4429,
"eval_samples_per_second": 84.521,
"eval_steps_per_second": 5.519,
"step": 326520
},
{
"epoch": 18.02646085997795,
"grad_norm": 0.52734375,
"learning_rate": 0.0006394707828004411,
"loss": 5.7263,
"step": 327000
},
{
"epoch": 18.054024255788313,
"grad_norm": 0.94140625,
"learning_rate": 0.0006389195148842337,
"loss": 5.729,
"step": 327500
},
{
"epoch": 18.081587651598678,
"grad_norm": 0.408203125,
"learning_rate": 0.0006383682469680264,
"loss": 5.716,
"step": 328000
},
{
"epoch": 18.10915104740904,
"grad_norm": 0.59375,
"learning_rate": 0.0006378169790518193,
"loss": 5.7466,
"step": 328500
},
{
"epoch": 18.136714443219404,
"grad_norm": 0.3828125,
"learning_rate": 0.0006372657111356119,
"loss": 5.729,
"step": 329000
},
{
"epoch": 18.16427783902977,
"grad_norm": 0.359375,
"learning_rate": 0.0006367144432194047,
"loss": 5.7284,
"step": 329500
},
{
"epoch": 18.191841234840133,
"grad_norm": 0.50390625,
"learning_rate": 0.0006361631753031973,
"loss": 5.7361,
"step": 330000
},
{
"epoch": 18.219404630650494,
"grad_norm": 0.333984375,
"learning_rate": 0.00063561190738699,
"loss": 5.7429,
"step": 330500
},
{
"epoch": 18.24696802646086,
"grad_norm": 0.322265625,
"learning_rate": 0.0006350606394707829,
"loss": 5.7463,
"step": 331000
},
{
"epoch": 18.274531422271224,
"grad_norm": 0.3125,
"learning_rate": 0.0006345093715545755,
"loss": 5.7233,
"step": 331500
},
{
"epoch": 18.30209481808159,
"grad_norm": 0.39453125,
"learning_rate": 0.0006339581036383683,
"loss": 5.7377,
"step": 332000
},
{
"epoch": 18.329658213891953,
"grad_norm": 0.515625,
"learning_rate": 0.000633406835722161,
"loss": 5.7343,
"step": 332500
},
{
"epoch": 18.357221609702314,
"grad_norm": 0.375,
"learning_rate": 0.0006328555678059536,
"loss": 5.7412,
"step": 333000
},
{
"epoch": 18.38478500551268,
"grad_norm": 0.3515625,
"learning_rate": 0.0006323042998897465,
"loss": 5.7272,
"step": 333500
},
{
"epoch": 18.412348401323044,
"grad_norm": 0.375,
"learning_rate": 0.0006317530319735391,
"loss": 5.7074,
"step": 334000
},
{
"epoch": 18.43991179713341,
"grad_norm": 0.357421875,
"learning_rate": 0.0006312017640573319,
"loss": 5.7206,
"step": 334500
},
{
"epoch": 18.46747519294377,
"grad_norm": 0.474609375,
"learning_rate": 0.0006306504961411246,
"loss": 5.6941,
"step": 335000
},
{
"epoch": 18.495038588754134,
"grad_norm": 0.37890625,
"learning_rate": 0.0006300992282249172,
"loss": 5.7386,
"step": 335500
},
{
"epoch": 18.5226019845645,
"grad_norm": 0.345703125,
"learning_rate": 0.0006295479603087101,
"loss": 5.7343,
"step": 336000
},
{
"epoch": 18.550165380374864,
"grad_norm": 0.35546875,
"learning_rate": 0.0006289966923925028,
"loss": 5.7212,
"step": 336500
},
{
"epoch": 18.577728776185225,
"grad_norm": 0.3125,
"learning_rate": 0.0006284454244762955,
"loss": 5.7416,
"step": 337000
},
{
"epoch": 18.60529217199559,
"grad_norm": 0.94140625,
"learning_rate": 0.0006278941565600882,
"loss": 5.7385,
"step": 337500
},
{
"epoch": 18.632855567805954,
"grad_norm": 0.51953125,
"learning_rate": 0.0006273428886438809,
"loss": 5.7053,
"step": 338000
},
{
"epoch": 18.66041896361632,
"grad_norm": 0.3984375,
"learning_rate": 0.0006267916207276737,
"loss": 5.742,
"step": 338500
},
{
"epoch": 18.68798235942668,
"grad_norm": 0.41796875,
"learning_rate": 0.0006262403528114664,
"loss": 5.7315,
"step": 339000
},
{
"epoch": 18.715545755237045,
"grad_norm": 0.353515625,
"learning_rate": 0.0006256890848952591,
"loss": 5.7446,
"step": 339500
},
{
"epoch": 18.74310915104741,
"grad_norm": 0.365234375,
"learning_rate": 0.0006251378169790518,
"loss": 5.723,
"step": 340000
},
{
"epoch": 18.770672546857774,
"grad_norm": 0.373046875,
"learning_rate": 0.0006245865490628446,
"loss": 5.7278,
"step": 340500
},
{
"epoch": 18.798235942668136,
"grad_norm": 0.35546875,
"learning_rate": 0.0006240352811466373,
"loss": 5.7344,
"step": 341000
},
{
"epoch": 18.8257993384785,
"grad_norm": 0.42578125,
"learning_rate": 0.00062348401323043,
"loss": 5.7251,
"step": 341500
},
{
"epoch": 18.853362734288865,
"grad_norm": 0.291015625,
"learning_rate": 0.0006229327453142228,
"loss": 5.7415,
"step": 342000
},
{
"epoch": 18.88092613009923,
"grad_norm": 0.39453125,
"learning_rate": 0.0006223814773980154,
"loss": 5.7231,
"step": 342500
},
{
"epoch": 18.90848952590959,
"grad_norm": 0.34375,
"learning_rate": 0.0006218302094818082,
"loss": 5.7078,
"step": 343000
},
{
"epoch": 18.936052921719956,
"grad_norm": 0.33984375,
"learning_rate": 0.0006212789415656009,
"loss": 5.7255,
"step": 343500
},
{
"epoch": 18.96361631753032,
"grad_norm": 0.369140625,
"learning_rate": 0.0006207276736493936,
"loss": 5.7394,
"step": 344000
},
{
"epoch": 18.991179713340685,
"grad_norm": 0.58203125,
"learning_rate": 0.0006201764057331864,
"loss": 5.7248,
"step": 344500
},
{
"epoch": 19.0,
"eval_loss": 5.676168918609619,
"eval_runtime": 3.4816,
"eval_samples_per_second": 83.582,
"eval_steps_per_second": 5.457,
"step": 344660
}
],
"logging_steps": 500,
"max_steps": 907000,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1404914590783722e+20,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}