chansung's picture
Model save
6ff5c14 verified
raw
history blame
49.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 1340,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007462686567164179,
"grad_norm": 138.84262084960938,
"learning_rate": 1.4925373134328358e-06,
"loss": 2.7919,
"step": 1
},
{
"epoch": 0.03731343283582089,
"grad_norm": 108.88359832763672,
"learning_rate": 7.4626865671641785e-06,
"loss": 2.7342,
"step": 5
},
{
"epoch": 0.07462686567164178,
"grad_norm": 13.541873931884766,
"learning_rate": 1.4925373134328357e-05,
"loss": 2.3501,
"step": 10
},
{
"epoch": 0.11194029850746269,
"grad_norm": 7.267947673797607,
"learning_rate": 2.238805970149254e-05,
"loss": 1.903,
"step": 15
},
{
"epoch": 0.14925373134328357,
"grad_norm": 4.06025505065918,
"learning_rate": 2.9850746268656714e-05,
"loss": 1.5868,
"step": 20
},
{
"epoch": 0.1865671641791045,
"grad_norm": 1.833858847618103,
"learning_rate": 3.73134328358209e-05,
"loss": 1.3748,
"step": 25
},
{
"epoch": 0.22388059701492538,
"grad_norm": 1.4598793983459473,
"learning_rate": 4.477611940298508e-05,
"loss": 1.2384,
"step": 30
},
{
"epoch": 0.26119402985074625,
"grad_norm": 1.4846118688583374,
"learning_rate": 5.223880597014925e-05,
"loss": 1.149,
"step": 35
},
{
"epoch": 0.29850746268656714,
"grad_norm": 0.9875138998031616,
"learning_rate": 5.970149253731343e-05,
"loss": 1.0731,
"step": 40
},
{
"epoch": 0.3358208955223881,
"grad_norm": 1.0995197296142578,
"learning_rate": 6.716417910447762e-05,
"loss": 1.0446,
"step": 45
},
{
"epoch": 0.373134328358209,
"grad_norm": 0.6559099555015564,
"learning_rate": 7.46268656716418e-05,
"loss": 1.014,
"step": 50
},
{
"epoch": 0.41044776119402987,
"grad_norm": 1.1354745626449585,
"learning_rate": 8.208955223880597e-05,
"loss": 0.994,
"step": 55
},
{
"epoch": 0.44776119402985076,
"grad_norm": 0.49952608346939087,
"learning_rate": 8.955223880597016e-05,
"loss": 0.9708,
"step": 60
},
{
"epoch": 0.48507462686567165,
"grad_norm": 0.8550089597702026,
"learning_rate": 9.701492537313434e-05,
"loss": 0.9634,
"step": 65
},
{
"epoch": 0.5223880597014925,
"grad_norm": 0.5180774927139282,
"learning_rate": 0.0001044776119402985,
"loss": 0.951,
"step": 70
},
{
"epoch": 0.5597014925373134,
"grad_norm": 0.6518343687057495,
"learning_rate": 0.00011194029850746269,
"loss": 0.9374,
"step": 75
},
{
"epoch": 0.5970149253731343,
"grad_norm": 0.9855380654335022,
"learning_rate": 0.00011940298507462686,
"loss": 0.9345,
"step": 80
},
{
"epoch": 0.6343283582089553,
"grad_norm": 1.1707885265350342,
"learning_rate": 0.00012686567164179105,
"loss": 0.9269,
"step": 85
},
{
"epoch": 0.6716417910447762,
"grad_norm": 0.527793824672699,
"learning_rate": 0.00013432835820895525,
"loss": 0.9095,
"step": 90
},
{
"epoch": 0.7089552238805971,
"grad_norm": 0.678547203540802,
"learning_rate": 0.00014179104477611942,
"loss": 0.9077,
"step": 95
},
{
"epoch": 0.746268656716418,
"grad_norm": 1.1332663297653198,
"learning_rate": 0.0001492537313432836,
"loss": 0.8974,
"step": 100
},
{
"epoch": 0.7835820895522388,
"grad_norm": 0.5298197865486145,
"learning_rate": 0.00015671641791044778,
"loss": 0.9071,
"step": 105
},
{
"epoch": 0.8208955223880597,
"grad_norm": 0.5773002505302429,
"learning_rate": 0.00016417910447761195,
"loss": 0.8858,
"step": 110
},
{
"epoch": 0.8582089552238806,
"grad_norm": 0.6888121962547302,
"learning_rate": 0.00017164179104477614,
"loss": 0.8891,
"step": 115
},
{
"epoch": 0.8955223880597015,
"grad_norm": 0.550254762172699,
"learning_rate": 0.0001791044776119403,
"loss": 0.8757,
"step": 120
},
{
"epoch": 0.9328358208955224,
"grad_norm": 0.5638606548309326,
"learning_rate": 0.00018656716417910448,
"loss": 0.872,
"step": 125
},
{
"epoch": 0.9701492537313433,
"grad_norm": 0.826892614364624,
"learning_rate": 0.00019402985074626867,
"loss": 0.8763,
"step": 130
},
{
"epoch": 1.0,
"eval_loss": 1.4227064847946167,
"eval_runtime": 0.5192,
"eval_samples_per_second": 3.852,
"eval_steps_per_second": 1.926,
"step": 134
},
{
"epoch": 1.007462686567164,
"grad_norm": 0.6830571293830872,
"learning_rate": 0.00019999966070700876,
"loss": 0.8669,
"step": 135
},
{
"epoch": 1.044776119402985,
"grad_norm": 0.6296478509902954,
"learning_rate": 0.0001999877856940653,
"loss": 0.8547,
"step": 140
},
{
"epoch": 1.0820895522388059,
"grad_norm": 0.7137119770050049,
"learning_rate": 0.00019995894833388465,
"loss": 0.8498,
"step": 145
},
{
"epoch": 1.1194029850746268,
"grad_norm": 0.44721338152885437,
"learning_rate": 0.00019991315351855748,
"loss": 0.848,
"step": 150
},
{
"epoch": 1.1567164179104479,
"grad_norm": 0.4353409707546234,
"learning_rate": 0.0001998504090169083,
"loss": 0.8289,
"step": 155
},
{
"epoch": 1.1940298507462686,
"grad_norm": 0.4284411668777466,
"learning_rate": 0.0001997707254731775,
"loss": 0.8298,
"step": 160
},
{
"epoch": 1.2313432835820897,
"grad_norm": 0.49997657537460327,
"learning_rate": 0.00019967411640521552,
"loss": 0.8305,
"step": 165
},
{
"epoch": 1.2686567164179103,
"grad_norm": 0.5145930647850037,
"learning_rate": 0.00019956059820218982,
"loss": 0.8165,
"step": 170
},
{
"epoch": 1.3059701492537314,
"grad_norm": 0.9191280007362366,
"learning_rate": 0.0001994301901218043,
"loss": 0.8228,
"step": 175
},
{
"epoch": 1.3432835820895521,
"grad_norm": 0.4731077551841736,
"learning_rate": 0.00019928291428703262,
"loss": 0.8218,
"step": 180
},
{
"epoch": 1.3805970149253732,
"grad_norm": 0.4273313879966736,
"learning_rate": 0.0001991187956823649,
"loss": 0.8277,
"step": 185
},
{
"epoch": 1.417910447761194,
"grad_norm": 0.512370228767395,
"learning_rate": 0.00019893786214956945,
"loss": 0.8075,
"step": 190
},
{
"epoch": 1.455223880597015,
"grad_norm": 0.6519188284873962,
"learning_rate": 0.00019874014438296946,
"loss": 0.8178,
"step": 195
},
{
"epoch": 1.4925373134328357,
"grad_norm": 0.5379275679588318,
"learning_rate": 0.0001985256759242359,
"loss": 0.8134,
"step": 200
},
{
"epoch": 1.5298507462686568,
"grad_norm": 0.5376815795898438,
"learning_rate": 0.00019829449315669748,
"loss": 0.8005,
"step": 205
},
{
"epoch": 1.5671641791044775,
"grad_norm": 0.5267529487609863,
"learning_rate": 0.00019804663529916826,
"loss": 0.8021,
"step": 210
},
{
"epoch": 1.6044776119402986,
"grad_norm": 0.582000732421875,
"learning_rate": 0.00019778214439929452,
"loss": 0.8107,
"step": 215
},
{
"epoch": 1.6417910447761193,
"grad_norm": 0.4234386086463928,
"learning_rate": 0.0001975010653264216,
"loss": 0.7975,
"step": 220
},
{
"epoch": 1.6791044776119404,
"grad_norm": 0.4661960005760193,
"learning_rate": 0.00019720344576398203,
"loss": 0.7991,
"step": 225
},
{
"epoch": 1.716417910447761,
"grad_norm": 0.66214519739151,
"learning_rate": 0.00019688933620140637,
"loss": 0.7966,
"step": 230
},
{
"epoch": 1.7537313432835822,
"grad_norm": 0.4201449453830719,
"learning_rate": 0.000196558789925558,
"loss": 0.8005,
"step": 235
},
{
"epoch": 1.7910447761194028,
"grad_norm": 0.4008370637893677,
"learning_rate": 0.00019621186301169315,
"loss": 0.7921,
"step": 240
},
{
"epoch": 1.828358208955224,
"grad_norm": 0.4507235884666443,
"learning_rate": 0.00019584861431394822,
"loss": 0.7956,
"step": 245
},
{
"epoch": 1.8656716417910446,
"grad_norm": 0.46443891525268555,
"learning_rate": 0.00019546910545535558,
"loss": 0.7932,
"step": 250
},
{
"epoch": 1.9029850746268657,
"grad_norm": 0.5451995134353638,
"learning_rate": 0.0001950734008173893,
"loss": 0.7889,
"step": 255
},
{
"epoch": 1.9402985074626866,
"grad_norm": 0.507540762424469,
"learning_rate": 0.00019466156752904343,
"loss": 0.7794,
"step": 260
},
{
"epoch": 1.9776119402985075,
"grad_norm": 0.4746926724910736,
"learning_rate": 0.00019423367545544395,
"loss": 0.7756,
"step": 265
},
{
"epoch": 2.0,
"eval_loss": 1.439745306968689,
"eval_runtime": 0.5176,
"eval_samples_per_second": 3.864,
"eval_steps_per_second": 1.932,
"step": 268
},
{
"epoch": 2.014925373134328,
"grad_norm": 0.6268861889839172,
"learning_rate": 0.00019378979718599645,
"loss": 0.7882,
"step": 270
},
{
"epoch": 2.0522388059701493,
"grad_norm": 0.549802839756012,
"learning_rate": 0.0001933300080220719,
"loss": 0.7609,
"step": 275
},
{
"epoch": 2.08955223880597,
"grad_norm": 0.6178936958312988,
"learning_rate": 0.00019285438596423204,
"loss": 0.7603,
"step": 280
},
{
"epoch": 2.126865671641791,
"grad_norm": 0.41491350531578064,
"learning_rate": 0.00019236301169899713,
"loss": 0.7554,
"step": 285
},
{
"epoch": 2.1641791044776117,
"grad_norm": 0.5220763683319092,
"learning_rate": 0.000191855968585158,
"loss": 0.759,
"step": 290
},
{
"epoch": 2.201492537313433,
"grad_norm": 0.5099439024925232,
"learning_rate": 0.0001913333426396346,
"loss": 0.7614,
"step": 295
},
{
"epoch": 2.2388059701492535,
"grad_norm": 0.5702708959579468,
"learning_rate": 0.00019079522252288386,
"loss": 0.7485,
"step": 300
},
{
"epoch": 2.2761194029850746,
"grad_norm": 0.4422476887702942,
"learning_rate": 0.00019024169952385885,
"loss": 0.76,
"step": 305
},
{
"epoch": 2.3134328358208958,
"grad_norm": 0.44903138279914856,
"learning_rate": 0.00018967286754452214,
"loss": 0.7632,
"step": 310
},
{
"epoch": 2.3507462686567164,
"grad_norm": 0.49397289752960205,
"learning_rate": 0.00018908882308391598,
"loss": 0.7568,
"step": 315
},
{
"epoch": 2.388059701492537,
"grad_norm": 0.4179913103580475,
"learning_rate": 0.00018848966522179168,
"loss": 0.7596,
"step": 320
},
{
"epoch": 2.425373134328358,
"grad_norm": 0.4103606045246124,
"learning_rate": 0.0001878754956018014,
"loss": 0.7487,
"step": 325
},
{
"epoch": 2.4626865671641793,
"grad_norm": 0.41152262687683105,
"learning_rate": 0.00018724641841425478,
"loss": 0.7565,
"step": 330
},
{
"epoch": 2.5,
"grad_norm": 0.4100894629955292,
"learning_rate": 0.00018660254037844388,
"loss": 0.7538,
"step": 335
},
{
"epoch": 2.5373134328358207,
"grad_norm": 0.3992711901664734,
"learning_rate": 0.00018594397072453856,
"loss": 0.7524,
"step": 340
},
{
"epoch": 2.574626865671642,
"grad_norm": 0.42304080724716187,
"learning_rate": 0.0001852708211750564,
"loss": 0.7533,
"step": 345
},
{
"epoch": 2.611940298507463,
"grad_norm": 0.4376600384712219,
"learning_rate": 0.00018458320592590975,
"loss": 0.7635,
"step": 350
},
{
"epoch": 2.6492537313432836,
"grad_norm": 0.39463093876838684,
"learning_rate": 0.00018388124162703275,
"loss": 0.7438,
"step": 355
},
{
"epoch": 2.6865671641791042,
"grad_norm": 0.3841034770011902,
"learning_rate": 0.00018316504736259255,
"loss": 0.759,
"step": 360
},
{
"epoch": 2.7238805970149254,
"grad_norm": 0.43507230281829834,
"learning_rate": 0.00018243474463078735,
"loss": 0.7477,
"step": 365
},
{
"epoch": 2.7611940298507465,
"grad_norm": 0.41791486740112305,
"learning_rate": 0.00018169045732323492,
"loss": 0.7463,
"step": 370
},
{
"epoch": 2.798507462686567,
"grad_norm": 0.4145572781562805,
"learning_rate": 0.00018093231170395507,
"loss": 0.7438,
"step": 375
},
{
"epoch": 2.835820895522388,
"grad_norm": 0.39668190479278564,
"learning_rate": 0.00018016043638794974,
"loss": 0.7545,
"step": 380
},
{
"epoch": 2.873134328358209,
"grad_norm": 0.36246854066848755,
"learning_rate": 0.0001793749623193842,
"loss": 0.7483,
"step": 385
},
{
"epoch": 2.91044776119403,
"grad_norm": 0.4155827462673187,
"learning_rate": 0.00017857602274937308,
"loss": 0.7499,
"step": 390
},
{
"epoch": 2.9477611940298507,
"grad_norm": 0.3993385136127472,
"learning_rate": 0.00017776375321337521,
"loss": 0.7402,
"step": 395
},
{
"epoch": 2.9850746268656714,
"grad_norm": 0.40633976459503174,
"learning_rate": 0.00017693829150820068,
"loss": 0.7387,
"step": 400
},
{
"epoch": 3.0,
"eval_loss": 1.440061092376709,
"eval_runtime": 0.5179,
"eval_samples_per_second": 3.862,
"eval_steps_per_second": 1.931,
"step": 402
},
{
"epoch": 3.0223880597014925,
"grad_norm": 0.43004971742630005,
"learning_rate": 0.00017609977766863458,
"loss": 0.7429,
"step": 405
},
{
"epoch": 3.0597014925373136,
"grad_norm": 0.4013059735298157,
"learning_rate": 0.00017524835394368065,
"loss": 0.7087,
"step": 410
},
{
"epoch": 3.0970149253731343,
"grad_norm": 0.4613398313522339,
"learning_rate": 0.0001743841647724299,
"loss": 0.7234,
"step": 415
},
{
"epoch": 3.1343283582089554,
"grad_norm": 0.3847793936729431,
"learning_rate": 0.00017350735675955697,
"loss": 0.7214,
"step": 420
},
{
"epoch": 3.171641791044776,
"grad_norm": 0.4573831558227539,
"learning_rate": 0.00017261807865044993,
"loss": 0.7228,
"step": 425
},
{
"epoch": 3.208955223880597,
"grad_norm": 0.4393455684185028,
"learning_rate": 0.00017171648130597612,
"loss": 0.7202,
"step": 430
},
{
"epoch": 3.246268656716418,
"grad_norm": 0.45842474699020386,
"learning_rate": 0.00017080271767688963,
"loss": 0.7098,
"step": 435
},
{
"epoch": 3.283582089552239,
"grad_norm": 0.46594393253326416,
"learning_rate": 0.00016987694277788417,
"loss": 0.7159,
"step": 440
},
{
"epoch": 3.3208955223880596,
"grad_norm": 0.40664443373680115,
"learning_rate": 0.00016893931366129562,
"loss": 0.7128,
"step": 445
},
{
"epoch": 3.3582089552238807,
"grad_norm": 0.38857197761535645,
"learning_rate": 0.00016798998939045895,
"loss": 0.7223,
"step": 450
},
{
"epoch": 3.3955223880597014,
"grad_norm": 0.443276047706604,
"learning_rate": 0.0001670291310127242,
"loss": 0.7132,
"step": 455
},
{
"epoch": 3.4328358208955225,
"grad_norm": 0.3902607858181,
"learning_rate": 0.0001660569015321357,
"loss": 0.7139,
"step": 460
},
{
"epoch": 3.470149253731343,
"grad_norm": 0.3990344703197479,
"learning_rate": 0.00016507346588177935,
"loss": 0.7191,
"step": 465
},
{
"epoch": 3.5074626865671643,
"grad_norm": 0.4015812277793884,
"learning_rate": 0.00016407899089580262,
"loss": 0.7146,
"step": 470
},
{
"epoch": 3.544776119402985,
"grad_norm": 0.44737905263900757,
"learning_rate": 0.0001630736452811122,
"loss": 0.7182,
"step": 475
},
{
"epoch": 3.582089552238806,
"grad_norm": 0.4523073136806488,
"learning_rate": 0.0001620575995887538,
"loss": 0.7212,
"step": 480
},
{
"epoch": 3.6194029850746268,
"grad_norm": 0.4242749512195587,
"learning_rate": 0.00016103102618497922,
"loss": 0.7168,
"step": 485
},
{
"epoch": 3.656716417910448,
"grad_norm": 0.4483940899372101,
"learning_rate": 0.0001599940992220053,
"loss": 0.7145,
"step": 490
},
{
"epoch": 3.6940298507462686,
"grad_norm": 0.4250345826148987,
"learning_rate": 0.00015894699460847016,
"loss": 0.6993,
"step": 495
},
{
"epoch": 3.7313432835820897,
"grad_norm": 0.38691166043281555,
"learning_rate": 0.00015788988997959114,
"loss": 0.7135,
"step": 500
},
{
"epoch": 3.7686567164179103,
"grad_norm": 0.4665898382663727,
"learning_rate": 0.00015682296466703024,
"loss": 0.7226,
"step": 505
},
{
"epoch": 3.8059701492537314,
"grad_norm": 0.501005232334137,
"learning_rate": 0.00015574639966847126,
"loss": 0.7189,
"step": 510
},
{
"epoch": 3.843283582089552,
"grad_norm": 0.3910924792289734,
"learning_rate": 0.0001546603776169149,
"loss": 0.7208,
"step": 515
},
{
"epoch": 3.8805970149253732,
"grad_norm": 0.4152643382549286,
"learning_rate": 0.00015356508274969594,
"loss": 0.7248,
"step": 520
},
{
"epoch": 3.917910447761194,
"grad_norm": 0.4302676022052765,
"learning_rate": 0.00015246070087722845,
"loss": 0.7169,
"step": 525
},
{
"epoch": 3.955223880597015,
"grad_norm": 0.39138561487197876,
"learning_rate": 0.0001513474193514842,
"loss": 0.7243,
"step": 530
},
{
"epoch": 3.9925373134328357,
"grad_norm": 0.4384176731109619,
"learning_rate": 0.0001502254270342095,
"loss": 0.7128,
"step": 535
},
{
"epoch": 4.0,
"eval_loss": 1.4540088176727295,
"eval_runtime": 0.518,
"eval_samples_per_second": 3.861,
"eval_steps_per_second": 1.93,
"step": 536
},
{
"epoch": 4.029850746268656,
"grad_norm": 0.4122828543186188,
"learning_rate": 0.00014909491426488578,
"loss": 0.6889,
"step": 540
},
{
"epoch": 4.067164179104478,
"grad_norm": 0.4475855827331543,
"learning_rate": 0.0001479560728284398,
"loss": 0.6847,
"step": 545
},
{
"epoch": 4.104477611940299,
"grad_norm": 0.47523927688598633,
"learning_rate": 0.0001468090959227082,
"loss": 0.6887,
"step": 550
},
{
"epoch": 4.141791044776119,
"grad_norm": 0.39732715487480164,
"learning_rate": 0.00014565417812566285,
"loss": 0.6877,
"step": 555
},
{
"epoch": 4.17910447761194,
"grad_norm": 0.4284641444683075,
"learning_rate": 0.00014449151536240166,
"loss": 0.6932,
"step": 560
},
{
"epoch": 4.2164179104477615,
"grad_norm": 0.43158912658691406,
"learning_rate": 0.0001433213048719111,
"loss": 0.6893,
"step": 565
},
{
"epoch": 4.253731343283582,
"grad_norm": 0.4248037338256836,
"learning_rate": 0.00014214374517360575,
"loss": 0.6846,
"step": 570
},
{
"epoch": 4.291044776119403,
"grad_norm": 0.4019497334957123,
"learning_rate": 0.00014095903603365066,
"loss": 0.6872,
"step": 575
},
{
"epoch": 4.3283582089552235,
"grad_norm": 0.42748814821243286,
"learning_rate": 0.00013976737843107202,
"loss": 0.6876,
"step": 580
},
{
"epoch": 4.365671641791045,
"grad_norm": 0.4337392747402191,
"learning_rate": 0.00013856897452366242,
"loss": 0.6981,
"step": 585
},
{
"epoch": 4.402985074626866,
"grad_norm": 0.4018155634403229,
"learning_rate": 0.00013736402761368598,
"loss": 0.6872,
"step": 590
},
{
"epoch": 4.440298507462686,
"grad_norm": 0.40716463327407837,
"learning_rate": 0.00013615274211338909,
"loss": 0.6874,
"step": 595
},
{
"epoch": 4.477611940298507,
"grad_norm": 0.4064732491970062,
"learning_rate": 0.0001349353235103232,
"loss": 0.69,
"step": 600
},
{
"epoch": 4.514925373134329,
"grad_norm": 0.38808923959732056,
"learning_rate": 0.00013371197833248507,
"loss": 0.6906,
"step": 605
},
{
"epoch": 4.552238805970149,
"grad_norm": 0.4051991105079651,
"learning_rate": 0.00013248291411328047,
"loss": 0.6898,
"step": 610
},
{
"epoch": 4.58955223880597,
"grad_norm": 0.4059875011444092,
"learning_rate": 0.00013124833935631726,
"loss": 0.688,
"step": 615
},
{
"epoch": 4.6268656716417915,
"grad_norm": 0.4350437521934509,
"learning_rate": 0.0001300084635000341,
"loss": 0.6868,
"step": 620
},
{
"epoch": 4.664179104477612,
"grad_norm": 0.43591079115867615,
"learning_rate": 0.0001287634968821703,
"loss": 0.6843,
"step": 625
},
{
"epoch": 4.701492537313433,
"grad_norm": 0.3807081878185272,
"learning_rate": 0.00012751365070408333,
"loss": 0.6792,
"step": 630
},
{
"epoch": 4.7388059701492535,
"grad_norm": 0.3958300054073334,
"learning_rate": 0.00012625913699491984,
"loss": 0.6896,
"step": 635
},
{
"epoch": 4.776119402985074,
"grad_norm": 0.4042377471923828,
"learning_rate": 0.00012500016857564585,
"loss": 0.6875,
"step": 640
},
{
"epoch": 4.813432835820896,
"grad_norm": 0.40110722184181213,
"learning_rate": 0.00012373695902294314,
"loss": 0.6923,
"step": 645
},
{
"epoch": 4.850746268656716,
"grad_norm": 0.4298909604549408,
"learning_rate": 0.0001224697226329772,
"loss": 0.6975,
"step": 650
},
{
"epoch": 4.888059701492537,
"grad_norm": 0.4291529655456543,
"learning_rate": 0.00012119867438504302,
"loss": 0.6908,
"step": 655
},
{
"epoch": 4.925373134328359,
"grad_norm": 0.4685961902141571,
"learning_rate": 0.00011992402990509515,
"loss": 0.6836,
"step": 660
},
{
"epoch": 4.962686567164179,
"grad_norm": 0.4041878879070282,
"learning_rate": 0.00011864600542916813,
"loss": 0.6921,
"step": 665
},
{
"epoch": 5.0,
"grad_norm": 0.3824089467525482,
"learning_rate": 0.00011736481776669306,
"loss": 0.6837,
"step": 670
},
{
"epoch": 5.0,
"eval_loss": 1.465812087059021,
"eval_runtime": 0.5174,
"eval_samples_per_second": 3.866,
"eval_steps_per_second": 1.933,
"step": 670
},
{
"epoch": 5.037313432835821,
"grad_norm": 0.4383637309074402,
"learning_rate": 0.0001160806842637173,
"loss": 0.6631,
"step": 675
},
{
"epoch": 5.074626865671641,
"grad_norm": 0.40598100423812866,
"learning_rate": 0.000114793822766033,
"loss": 0.6596,
"step": 680
},
{
"epoch": 5.111940298507463,
"grad_norm": 0.413703590631485,
"learning_rate": 0.00011350445158222074,
"loss": 0.6631,
"step": 685
},
{
"epoch": 5.149253731343284,
"grad_norm": 0.44605740904808044,
"learning_rate": 0.00011221278944661473,
"loss": 0.6463,
"step": 690
},
{
"epoch": 5.186567164179104,
"grad_norm": 0.43800660967826843,
"learning_rate": 0.00011091905548219597,
"loss": 0.6662,
"step": 695
},
{
"epoch": 5.223880597014926,
"grad_norm": 0.4596647620201111,
"learning_rate": 0.00010962346916341903,
"loss": 0.6638,
"step": 700
},
{
"epoch": 5.2611940298507465,
"grad_norm": 0.4407581090927124,
"learning_rate": 0.00010832625027897978,
"loss": 0.6644,
"step": 705
},
{
"epoch": 5.298507462686567,
"grad_norm": 0.41823288798332214,
"learning_rate": 0.0001070276188945293,
"loss": 0.6565,
"step": 710
},
{
"epoch": 5.335820895522388,
"grad_norm": 0.42799797654151917,
"learning_rate": 0.00010572779531534112,
"loss": 0.6555,
"step": 715
},
{
"epoch": 5.373134328358209,
"grad_norm": 0.3943883776664734,
"learning_rate": 0.00010442700004893764,
"loss": 0.6572,
"step": 720
},
{
"epoch": 5.41044776119403,
"grad_norm": 0.40598776936531067,
"learning_rate": 0.00010312545376768246,
"loss": 0.6564,
"step": 725
},
{
"epoch": 5.447761194029851,
"grad_norm": 0.42347079515457153,
"learning_rate": 0.0001018233772713443,
"loss": 0.6677,
"step": 730
},
{
"epoch": 5.485074626865671,
"grad_norm": 0.4139921963214874,
"learning_rate": 0.00010052099144964004,
"loss": 0.6701,
"step": 735
},
{
"epoch": 5.522388059701493,
"grad_norm": 0.4295801520347595,
"learning_rate": 9.92185172447616e-05,
"loss": 0.6605,
"step": 740
},
{
"epoch": 5.559701492537314,
"grad_norm": 0.41350170969963074,
"learning_rate": 9.791617561389475e-05,
"loss": 0.6671,
"step": 745
},
{
"epoch": 5.597014925373134,
"grad_norm": 0.4078296720981598,
"learning_rate": 9.661418749173467e-05,
"loss": 0.669,
"step": 750
},
{
"epoch": 5.634328358208955,
"grad_norm": 0.4294317066669464,
"learning_rate": 9.531277375300599e-05,
"loss": 0.6653,
"step": 755
},
{
"epoch": 5.6716417910447765,
"grad_norm": 0.4155528247356415,
"learning_rate": 9.40121551749925e-05,
"loss": 0.6587,
"step": 760
},
{
"epoch": 5.708955223880597,
"grad_norm": 0.4128773808479309,
"learning_rate": 9.271255240008356e-05,
"loss": 0.6572,
"step": 765
},
{
"epoch": 5.746268656716418,
"grad_norm": 0.4138401746749878,
"learning_rate": 9.141418589834339e-05,
"loss": 0.6619,
"step": 770
},
{
"epoch": 5.7835820895522385,
"grad_norm": 0.40413615107536316,
"learning_rate": 9.011727593010981e-05,
"loss": 0.6745,
"step": 775
},
{
"epoch": 5.82089552238806,
"grad_norm": 0.447427898645401,
"learning_rate": 8.882204250862796e-05,
"loss": 0.6625,
"step": 780
},
{
"epoch": 5.858208955223881,
"grad_norm": 0.4221794009208679,
"learning_rate": 8.752870536272673e-05,
"loss": 0.6743,
"step": 785
},
{
"epoch": 5.895522388059701,
"grad_norm": 0.4193105399608612,
"learning_rate": 8.623748389954283e-05,
"loss": 0.6666,
"step": 790
},
{
"epoch": 5.932835820895522,
"grad_norm": 0.4287867248058319,
"learning_rate": 8.494859716729962e-05,
"loss": 0.6676,
"step": 795
},
{
"epoch": 5.970149253731344,
"grad_norm": 0.40571707487106323,
"learning_rate": 8.366226381814697e-05,
"loss": 0.6691,
"step": 800
},
{
"epoch": 6.0,
"eval_loss": 1.4930399656295776,
"eval_runtime": 0.5186,
"eval_samples_per_second": 3.856,
"eval_steps_per_second": 1.928,
"step": 804
},
{
"epoch": 6.007462686567164,
"grad_norm": 0.4177990257740021,
"learning_rate": 8.237870207106821e-05,
"loss": 0.6566,
"step": 805
},
{
"epoch": 6.044776119402985,
"grad_norm": 0.4325125813484192,
"learning_rate": 8.109812967486025e-05,
"loss": 0.6271,
"step": 810
},
{
"epoch": 6.082089552238806,
"grad_norm": 0.42587417364120483,
"learning_rate": 7.982076387119421e-05,
"loss": 0.6384,
"step": 815
},
{
"epoch": 6.119402985074627,
"grad_norm": 0.4367959499359131,
"learning_rate": 7.854682135776131e-05,
"loss": 0.642,
"step": 820
},
{
"epoch": 6.156716417910448,
"grad_norm": 0.43222272396087646,
"learning_rate": 7.727651825151145e-05,
"loss": 0.6314,
"step": 825
},
{
"epoch": 6.1940298507462686,
"grad_norm": 0.44278955459594727,
"learning_rate": 7.601007005199021e-05,
"loss": 0.6389,
"step": 830
},
{
"epoch": 6.231343283582089,
"grad_norm": 0.4457733929157257,
"learning_rate": 7.474769160478079e-05,
"loss": 0.6411,
"step": 835
},
{
"epoch": 6.268656716417911,
"grad_norm": 0.4409390091896057,
"learning_rate": 7.348959706505626e-05,
"loss": 0.6381,
"step": 840
},
{
"epoch": 6.3059701492537314,
"grad_norm": 0.453755259513855,
"learning_rate": 7.223599986124994e-05,
"loss": 0.6458,
"step": 845
},
{
"epoch": 6.343283582089552,
"grad_norm": 0.420446515083313,
"learning_rate": 7.09871126588481e-05,
"loss": 0.6409,
"step": 850
},
{
"epoch": 6.380597014925373,
"grad_norm": 0.4332159757614136,
"learning_rate": 6.974314732431258e-05,
"loss": 0.6396,
"step": 855
},
{
"epoch": 6.417910447761194,
"grad_norm": 0.44185054302215576,
"learning_rate": 6.850431488913895e-05,
"loss": 0.6461,
"step": 860
},
{
"epoch": 6.455223880597015,
"grad_norm": 0.4363011121749878,
"learning_rate": 6.727082551405636e-05,
"loss": 0.6435,
"step": 865
},
{
"epoch": 6.492537313432836,
"grad_norm": 0.426645427942276,
"learning_rate": 6.604288845337453e-05,
"loss": 0.6443,
"step": 870
},
{
"epoch": 6.529850746268656,
"grad_norm": 0.4306298792362213,
"learning_rate": 6.482071201948556e-05,
"loss": 0.6405,
"step": 875
},
{
"epoch": 6.567164179104478,
"grad_norm": 0.42580053210258484,
"learning_rate": 6.360450354752458e-05,
"loss": 0.636,
"step": 880
},
{
"epoch": 6.604477611940299,
"grad_norm": 0.4214308261871338,
"learning_rate": 6.239446936019657e-05,
"loss": 0.6411,
"step": 885
},
{
"epoch": 6.641791044776119,
"grad_norm": 0.44287511706352234,
"learning_rate": 6.119081473277501e-05,
"loss": 0.6427,
"step": 890
},
{
"epoch": 6.67910447761194,
"grad_norm": 0.4150986671447754,
"learning_rate": 5.99937438582782e-05,
"loss": 0.6472,
"step": 895
},
{
"epoch": 6.7164179104477615,
"grad_norm": 0.446879118680954,
"learning_rate": 5.880345981282876e-05,
"loss": 0.6408,
"step": 900
},
{
"epoch": 6.753731343283582,
"grad_norm": 0.4269532561302185,
"learning_rate": 5.7620164521203356e-05,
"loss": 0.6367,
"step": 905
},
{
"epoch": 6.791044776119403,
"grad_norm": 0.4269901216030121,
"learning_rate": 5.6444058722577165e-05,
"loss": 0.6396,
"step": 910
},
{
"epoch": 6.8283582089552235,
"grad_norm": 0.42097654938697815,
"learning_rate": 5.5275341936469396e-05,
"loss": 0.6473,
"step": 915
},
{
"epoch": 6.865671641791045,
"grad_norm": 0.4283384680747986,
"learning_rate": 5.4114212428896424e-05,
"loss": 0.6496,
"step": 920
},
{
"epoch": 6.902985074626866,
"grad_norm": 0.4407792389392853,
"learning_rate": 5.296086717873685e-05,
"loss": 0.6459,
"step": 925
},
{
"epoch": 6.940298507462686,
"grad_norm": 0.43775680661201477,
"learning_rate": 5.1815501844315105e-05,
"loss": 0.6414,
"step": 930
},
{
"epoch": 6.977611940298507,
"grad_norm": 0.4383552372455597,
"learning_rate": 5.0678310730209275e-05,
"loss": 0.6389,
"step": 935
},
{
"epoch": 7.0,
"eval_loss": 1.5040441751480103,
"eval_runtime": 0.5191,
"eval_samples_per_second": 3.853,
"eval_steps_per_second": 1.927,
"step": 938
},
{
"epoch": 7.014925373134329,
"grad_norm": 0.4299301505088806,
"learning_rate": 4.954948675428853e-05,
"loss": 0.6411,
"step": 940
},
{
"epoch": 7.052238805970149,
"grad_norm": 0.44037163257598877,
"learning_rate": 4.84292214149855e-05,
"loss": 0.6185,
"step": 945
},
{
"epoch": 7.08955223880597,
"grad_norm": 0.4394110441207886,
"learning_rate": 4.7317704758809946e-05,
"loss": 0.6158,
"step": 950
},
{
"epoch": 7.126865671641791,
"grad_norm": 0.441795289516449,
"learning_rate": 4.6215125348108247e-05,
"loss": 0.6202,
"step": 955
},
{
"epoch": 7.164179104477612,
"grad_norm": 0.44138744473457336,
"learning_rate": 4.512167022907494e-05,
"loss": 0.6238,
"step": 960
},
{
"epoch": 7.201492537313433,
"grad_norm": 0.453387588262558,
"learning_rate": 4.40375249000216e-05,
"loss": 0.6258,
"step": 965
},
{
"epoch": 7.2388059701492535,
"grad_norm": 0.44053417444229126,
"learning_rate": 4.296287327990797e-05,
"loss": 0.6237,
"step": 970
},
{
"epoch": 7.276119402985074,
"grad_norm": 0.44405415654182434,
"learning_rate": 4.189789767714102e-05,
"loss": 0.6214,
"step": 975
},
{
"epoch": 7.313432835820896,
"grad_norm": 0.4466931223869324,
"learning_rate": 4.084277875864776e-05,
"loss": 0.6258,
"step": 980
},
{
"epoch": 7.350746268656716,
"grad_norm": 0.45868679881095886,
"learning_rate": 3.979769551922592e-05,
"loss": 0.6271,
"step": 985
},
{
"epoch": 7.388059701492537,
"grad_norm": 0.44392016530036926,
"learning_rate": 3.876282525117847e-05,
"loss": 0.6191,
"step": 990
},
{
"epoch": 7.425373134328359,
"grad_norm": 0.4744507670402527,
"learning_rate": 3.7738343514237106e-05,
"loss": 0.6291,
"step": 995
},
{
"epoch": 7.462686567164179,
"grad_norm": 0.43945175409317017,
"learning_rate": 3.672442410577965e-05,
"loss": 0.6305,
"step": 1000
},
{
"epoch": 7.5,
"grad_norm": 0.4612315893173218,
"learning_rate": 3.5721239031346066e-05,
"loss": 0.6236,
"step": 1005
},
{
"epoch": 7.537313432835821,
"grad_norm": 0.45296919345855713,
"learning_rate": 3.472895847545905e-05,
"loss": 0.6282,
"step": 1010
},
{
"epoch": 7.574626865671641,
"grad_norm": 0.4535280466079712,
"learning_rate": 3.374775077275293e-05,
"loss": 0.6249,
"step": 1015
},
{
"epoch": 7.611940298507463,
"grad_norm": 0.4502476155757904,
"learning_rate": 3.27777823794168e-05,
"loss": 0.6267,
"step": 1020
},
{
"epoch": 7.649253731343284,
"grad_norm": 0.4433761239051819,
"learning_rate": 3.1819217844956214e-05,
"loss": 0.6344,
"step": 1025
},
{
"epoch": 7.686567164179104,
"grad_norm": 0.4449211657047272,
"learning_rate": 3.0872219784278354e-05,
"loss": 0.6241,
"step": 1030
},
{
"epoch": 7.723880597014926,
"grad_norm": 0.47005486488342285,
"learning_rate": 2.9936948850105152e-05,
"loss": 0.6166,
"step": 1035
},
{
"epoch": 7.7611940298507465,
"grad_norm": 0.4615201950073242,
"learning_rate": 2.901356370571967e-05,
"loss": 0.6269,
"step": 1040
},
{
"epoch": 7.798507462686567,
"grad_norm": 0.44223588705062866,
"learning_rate": 2.8102220998049843e-05,
"loss": 0.6299,
"step": 1045
},
{
"epoch": 7.835820895522388,
"grad_norm": 0.4457671642303467,
"learning_rate": 2.7203075331094017e-05,
"loss": 0.627,
"step": 1050
},
{
"epoch": 7.8731343283582085,
"grad_norm": 0.4446623623371124,
"learning_rate": 2.6316279239693465e-05,
"loss": 0.6195,
"step": 1055
},
{
"epoch": 7.91044776119403,
"grad_norm": 0.4469725489616394,
"learning_rate": 2.54419831636557e-05,
"loss": 0.612,
"step": 1060
},
{
"epoch": 7.947761194029851,
"grad_norm": 0.4488806426525116,
"learning_rate": 2.458033542223316e-05,
"loss": 0.6139,
"step": 1065
},
{
"epoch": 7.985074626865671,
"grad_norm": 0.44639790058135986,
"learning_rate": 2.3731482188961818e-05,
"loss": 0.6291,
"step": 1070
},
{
"epoch": 8.0,
"eval_loss": 1.5243113040924072,
"eval_runtime": 0.5203,
"eval_samples_per_second": 3.844,
"eval_steps_per_second": 1.922,
"step": 1072
},
{
"epoch": 8.022388059701493,
"grad_norm": 0.43840205669403076,
"learning_rate": 2.28955674668636e-05,
"loss": 0.6144,
"step": 1075
},
{
"epoch": 8.059701492537313,
"grad_norm": 0.44431746006011963,
"learning_rate": 2.2072733064017103e-05,
"loss": 0.6062,
"step": 1080
},
{
"epoch": 8.097014925373134,
"grad_norm": 0.44257909059524536,
"learning_rate": 2.1263118569500795e-05,
"loss": 0.6067,
"step": 1085
},
{
"epoch": 8.134328358208956,
"grad_norm": 0.4406292140483856,
"learning_rate": 2.0466861329712473e-05,
"loss": 0.6169,
"step": 1090
},
{
"epoch": 8.171641791044776,
"grad_norm": 0.45199882984161377,
"learning_rate": 1.968409642506913e-05,
"loss": 0.6133,
"step": 1095
},
{
"epoch": 8.208955223880597,
"grad_norm": 0.4403633773326874,
"learning_rate": 1.89149566470915e-05,
"loss": 0.6059,
"step": 1100
},
{
"epoch": 8.246268656716419,
"grad_norm": 0.45532822608947754,
"learning_rate": 1.8159572475876718e-05,
"loss": 0.6042,
"step": 1105
},
{
"epoch": 8.283582089552239,
"grad_norm": 0.4559955596923828,
"learning_rate": 1.741807205796314e-05,
"loss": 0.6189,
"step": 1110
},
{
"epoch": 8.32089552238806,
"grad_norm": 0.45486971735954285,
"learning_rate": 1.6690581184590858e-05,
"loss": 0.6116,
"step": 1115
},
{
"epoch": 8.35820895522388,
"grad_norm": 0.44671645760536194,
"learning_rate": 1.5977223270362196e-05,
"loss": 0.6149,
"step": 1120
},
{
"epoch": 8.395522388059701,
"grad_norm": 0.45056024193763733,
"learning_rate": 1.5278119332305053e-05,
"loss": 0.614,
"step": 1125
},
{
"epoch": 8.432835820895523,
"grad_norm": 0.4756515920162201,
"learning_rate": 1.459338796934293e-05,
"loss": 0.6163,
"step": 1130
},
{
"epoch": 8.470149253731343,
"grad_norm": 0.4487175941467285,
"learning_rate": 1.3923145342175482e-05,
"loss": 0.6098,
"step": 1135
},
{
"epoch": 8.507462686567164,
"grad_norm": 0.46132373809814453,
"learning_rate": 1.3267505153572501e-05,
"loss": 0.6099,
"step": 1140
},
{
"epoch": 8.544776119402986,
"grad_norm": 0.44755882024765015,
"learning_rate": 1.2626578629084784e-05,
"loss": 0.6169,
"step": 1145
},
{
"epoch": 8.582089552238806,
"grad_norm": 0.46651872992515564,
"learning_rate": 1.2000474498175552e-05,
"loss": 0.6099,
"step": 1150
},
{
"epoch": 8.619402985074627,
"grad_norm": 0.47415512800216675,
"learning_rate": 1.138929897577493e-05,
"loss": 0.6104,
"step": 1155
},
{
"epoch": 8.656716417910447,
"grad_norm": 0.4649696350097656,
"learning_rate": 1.0793155744261351e-05,
"loss": 0.6094,
"step": 1160
},
{
"epoch": 8.694029850746269,
"grad_norm": 0.44566088914871216,
"learning_rate": 1.0212145935872375e-05,
"loss": 0.6223,
"step": 1165
},
{
"epoch": 8.73134328358209,
"grad_norm": 0.4482034742832184,
"learning_rate": 9.646368115548232e-06,
"loss": 0.6064,
"step": 1170
},
{
"epoch": 8.76865671641791,
"grad_norm": 0.4628354012966156,
"learning_rate": 9.095918264210779e-06,
"loss": 0.6139,
"step": 1175
},
{
"epoch": 8.805970149253731,
"grad_norm": 0.4561688303947449,
"learning_rate": 8.56088976248095e-06,
"loss": 0.6141,
"step": 1180
},
{
"epoch": 8.843283582089553,
"grad_norm": 0.4501047730445862,
"learning_rate": 8.041373374837302e-06,
"loss": 0.6184,
"step": 1185
},
{
"epoch": 8.880597014925373,
"grad_norm": 0.4514229893684387,
"learning_rate": 7.53745723421827e-06,
"loss": 0.6069,
"step": 1190
},
{
"epoch": 8.917910447761194,
"grad_norm": 0.4529721438884735,
"learning_rate": 7.0492268270709875e-06,
"loss": 0.6136,
"step": 1195
},
{
"epoch": 8.955223880597014,
"grad_norm": 0.4562200605869293,
"learning_rate": 6.576764978849004e-06,
"loss": 0.6053,
"step": 1200
},
{
"epoch": 8.992537313432836,
"grad_norm": 0.455243319272995,
"learning_rate": 6.1201518399613635e-06,
"loss": 0.6197,
"step": 1205
},
{
"epoch": 9.0,
"eval_loss": 1.5375313758850098,
"eval_runtime": 0.5174,
"eval_samples_per_second": 3.865,
"eval_steps_per_second": 1.933,
"step": 1206
},
{
"epoch": 9.029850746268657,
"grad_norm": 0.44451919198036194,
"learning_rate": 5.679464872175666e-06,
"loss": 0.6126,
"step": 1210
},
{
"epoch": 9.067164179104477,
"grad_norm": 0.4510916471481323,
"learning_rate": 5.254778835477015e-06,
"loss": 0.619,
"step": 1215
},
{
"epoch": 9.104477611940299,
"grad_norm": 0.4504685699939728,
"learning_rate": 4.846165775385459e-06,
"loss": 0.6059,
"step": 1220
},
{
"epoch": 9.14179104477612,
"grad_norm": 0.4434657692909241,
"learning_rate": 4.4536950107339605e-06,
"loss": 0.601,
"step": 1225
},
{
"epoch": 9.17910447761194,
"grad_norm": 0.46363726258277893,
"learning_rate": 4.077433121908747e-06,
"loss": 0.6165,
"step": 1230
},
{
"epoch": 9.216417910447761,
"grad_norm": 0.45644015073776245,
"learning_rate": 3.717443939554388e-06,
"loss": 0.6102,
"step": 1235
},
{
"epoch": 9.253731343283581,
"grad_norm": 0.45389410853385925,
"learning_rate": 3.3737885337452814e-06,
"loss": 0.6029,
"step": 1240
},
{
"epoch": 9.291044776119403,
"grad_norm": 0.4506882131099701,
"learning_rate": 3.0465252036255165e-06,
"loss": 0.6091,
"step": 1245
},
{
"epoch": 9.328358208955224,
"grad_norm": 0.44706588983535767,
"learning_rate": 2.735709467518699e-06,
"loss": 0.6114,
"step": 1250
},
{
"epoch": 9.365671641791044,
"grad_norm": 0.45065855979919434,
"learning_rate": 2.4413940535096156e-06,
"loss": 0.603,
"step": 1255
},
{
"epoch": 9.402985074626866,
"grad_norm": 0.4460483491420746,
"learning_rate": 2.1636288904992585e-06,
"loss": 0.6019,
"step": 1260
},
{
"epoch": 9.440298507462687,
"grad_norm": 0.4578142762184143,
"learning_rate": 1.902461099734587e-06,
"loss": 0.6065,
"step": 1265
},
{
"epoch": 9.477611940298507,
"grad_norm": 0.46080294251441956,
"learning_rate": 1.6579349868147687e-06,
"loss": 0.5979,
"step": 1270
},
{
"epoch": 9.514925373134329,
"grad_norm": 0.451742559671402,
"learning_rate": 1.430092034174979e-06,
"loss": 0.6133,
"step": 1275
},
{
"epoch": 9.552238805970148,
"grad_norm": 0.4507807493209839,
"learning_rate": 1.2189708940490652e-06,
"loss": 0.604,
"step": 1280
},
{
"epoch": 9.58955223880597,
"grad_norm": 0.45165741443634033,
"learning_rate": 1.0246073819125345e-06,
"loss": 0.604,
"step": 1285
},
{
"epoch": 9.626865671641792,
"grad_norm": 0.45481327176094055,
"learning_rate": 8.470344704066046e-07,
"loss": 0.6077,
"step": 1290
},
{
"epoch": 9.664179104477611,
"grad_norm": 0.4481595456600189,
"learning_rate": 6.862822837445881e-07,
"loss": 0.6021,
"step": 1295
},
{
"epoch": 9.701492537313433,
"grad_norm": 0.4543148875236511,
"learning_rate": 5.42378092601481e-07,
"loss": 0.5979,
"step": 1300
},
{
"epoch": 9.738805970149254,
"grad_norm": 0.4538787305355072,
"learning_rate": 4.153463094877186e-07,
"loss": 0.6013,
"step": 1305
},
{
"epoch": 9.776119402985074,
"grad_norm": 0.4568292796611786,
"learning_rate": 3.0520848460765527e-07,
"loss": 0.6035,
"step": 1310
},
{
"epoch": 9.813432835820896,
"grad_norm": 0.4435996115207672,
"learning_rate": 2.119833022037221e-07,
"loss": 0.6022,
"step": 1315
},
{
"epoch": 9.850746268656717,
"grad_norm": 0.4439810514450073,
"learning_rate": 1.3568657738678435e-07,
"loss": 0.6025,
"step": 1320
},
{
"epoch": 9.888059701492537,
"grad_norm": 0.4461255371570587,
"learning_rate": 7.633125345317682e-08,
"loss": 0.5931,
"step": 1325
},
{
"epoch": 9.925373134328359,
"grad_norm": 0.4546414315700531,
"learning_rate": 3.392739968894887e-08,
"loss": 0.6182,
"step": 1330
},
{
"epoch": 9.962686567164178,
"grad_norm": 0.45576563477516174,
"learning_rate": 8.48220966164215e-09,
"loss": 0.6126,
"step": 1335
},
{
"epoch": 10.0,
"grad_norm": 0.4497128427028656,
"learning_rate": 0.0,
"loss": 0.6028,
"step": 1340
},
{
"epoch": 10.0,
"eval_loss": 1.542757511138916,
"eval_runtime": 0.5408,
"eval_samples_per_second": 3.698,
"eval_steps_per_second": 1.849,
"step": 1340
},
{
"epoch": 10.0,
"step": 1340,
"total_flos": 3.755518175798624e+18,
"train_loss": 0.7269157813556159,
"train_runtime": 7393.4759,
"train_samples_per_second": 11.586,
"train_steps_per_second": 0.181
}
],
"logging_steps": 5,
"max_steps": 1340,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.755518175798624e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}