1213 lines
30 KiB
JSON
1213 lines
30 KiB
JSON
|
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 733,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.0068212824010914054,
|
||
|
|
"grad_norm": 1.881799613195007,
|
||
|
|
"learning_rate": 5.405405405405406e-06,
|
||
|
|
"loss": 0.8521,
|
||
|
|
"num_tokens": 3759146.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.013642564802182811,
|
||
|
|
"grad_norm": 1.7101008743112052,
|
||
|
|
"learning_rate": 1.2162162162162164e-05,
|
||
|
|
"loss": 0.8047,
|
||
|
|
"num_tokens": 7668808.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.020463847203274217,
|
||
|
|
"grad_norm": 0.6865141351597414,
|
||
|
|
"learning_rate": 1.891891891891892e-05,
|
||
|
|
"loss": 0.7189,
|
||
|
|
"num_tokens": 11368873.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.027285129604365622,
|
||
|
|
"grad_norm": 0.5605759414177258,
|
||
|
|
"learning_rate": 2.5675675675675675e-05,
|
||
|
|
"loss": 0.6773,
|
||
|
|
"num_tokens": 15118063.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.034106412005457026,
|
||
|
|
"grad_norm": 0.48933370420808264,
|
||
|
|
"learning_rate": 3.2432432432432436e-05,
|
||
|
|
"loss": 0.6547,
|
||
|
|
"num_tokens": 18906839.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.040927694406548434,
|
||
|
|
"grad_norm": 0.4114426768382651,
|
||
|
|
"learning_rate": 3.918918918918919e-05,
|
||
|
|
"loss": 0.6323,
|
||
|
|
"num_tokens": 22641755.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.047748976807639835,
|
||
|
|
"grad_norm": 0.383721233103028,
|
||
|
|
"learning_rate": 4.594594594594595e-05,
|
||
|
|
"loss": 0.6278,
|
||
|
|
"num_tokens": 26636629.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.054570259208731244,
|
||
|
|
"grad_norm": 0.4012112843562271,
|
||
|
|
"learning_rate": 4.999908316574644e-05,
|
||
|
|
"loss": 0.5974,
|
||
|
|
"num_tokens": 30417967.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.061391541609822645,
|
||
|
|
"grad_norm": 0.3692014531581435,
|
||
|
|
"learning_rate": 4.998876963847189e-05,
|
||
|
|
"loss": 0.6003,
|
||
|
|
"num_tokens": 34231333.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.06821282401091405,
|
||
|
|
"grad_norm": 0.3955585216188017,
|
||
|
|
"learning_rate": 4.996700181165029e-05,
|
||
|
|
"loss": 0.6003,
|
||
|
|
"num_tokens": 37961424.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.07503410641200546,
|
||
|
|
"grad_norm": 0.4068234869096405,
|
||
|
|
"learning_rate": 4.993379077238036e-05,
|
||
|
|
"loss": 0.6008,
|
||
|
|
"num_tokens": 41826860.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08185538881309687,
|
||
|
|
"grad_norm": 0.4435585222122122,
|
||
|
|
"learning_rate": 4.9889153436180295e-05,
|
||
|
|
"loss": 0.5886,
|
||
|
|
"num_tokens": 45543403.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08867667121418826,
|
||
|
|
"grad_norm": 0.44550926213945213,
|
||
|
|
"learning_rate": 4.983311253837213e-05,
|
||
|
|
"loss": 0.5926,
|
||
|
|
"num_tokens": 49369486.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.09549795361527967,
|
||
|
|
"grad_norm": 0.41100266811481995,
|
||
|
|
"learning_rate": 4.9765696622501846e-05,
|
||
|
|
"loss": 0.582,
|
||
|
|
"num_tokens": 53010874.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.10231923601637108,
|
||
|
|
"grad_norm": 0.391153857076114,
|
||
|
|
"learning_rate": 4.968694002580118e-05,
|
||
|
|
"loss": 0.5841,
|
||
|
|
"num_tokens": 56909889.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.10914051841746249,
|
||
|
|
"grad_norm": 0.4403959276876663,
|
||
|
|
"learning_rate": 4.959688286169851e-05,
|
||
|
|
"loss": 0.5676,
|
||
|
|
"num_tokens": 60650570.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11596180081855388,
|
||
|
|
"grad_norm": 0.4486997016217728,
|
||
|
|
"learning_rate": 4.9495570999387685e-05,
|
||
|
|
"loss": 0.5613,
|
||
|
|
"num_tokens": 64564660.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.12278308321964529,
|
||
|
|
"grad_norm": 0.4400583628743631,
|
||
|
|
"learning_rate": 4.9383056040465276e-05,
|
||
|
|
"loss": 0.5794,
|
||
|
|
"num_tokens": 68426882.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1296043656207367,
|
||
|
|
"grad_norm": 0.39088631890644404,
|
||
|
|
"learning_rate": 4.925939529264815e-05,
|
||
|
|
"loss": 0.5751,
|
||
|
|
"num_tokens": 72252819.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1364256480218281,
|
||
|
|
"grad_norm": 0.39462317452965684,
|
||
|
|
"learning_rate": 4.9124651740584684e-05,
|
||
|
|
"loss": 0.5613,
|
||
|
|
"num_tokens": 76160914.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1432469304229195,
|
||
|
|
"grad_norm": 0.3854843360933772,
|
||
|
|
"learning_rate": 4.897889401377447e-05,
|
||
|
|
"loss": 0.5631,
|
||
|
|
"num_tokens": 80152955.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.15006821282401092,
|
||
|
|
"grad_norm": 0.33367658431610214,
|
||
|
|
"learning_rate": 4.882219635161306e-05,
|
||
|
|
"loss": 0.5667,
|
||
|
|
"num_tokens": 83901702.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.15688949522510232,
|
||
|
|
"grad_norm": 0.42482706184560826,
|
||
|
|
"learning_rate": 4.865463856557922e-05,
|
||
|
|
"loss": 0.5655,
|
||
|
|
"num_tokens": 87691018.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16371077762619374,
|
||
|
|
"grad_norm": 0.3842124056837664,
|
||
|
|
"learning_rate": 4.847630599858426e-05,
|
||
|
|
"loss": 0.5547,
|
||
|
|
"num_tokens": 91542428.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17053206002728513,
|
||
|
|
"grad_norm": 0.337517505531631,
|
||
|
|
"learning_rate": 4.8287289481503954e-05,
|
||
|
|
"loss": 0.5615,
|
||
|
|
"num_tokens": 95438170.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17735334242837653,
|
||
|
|
"grad_norm": 0.4029687538155939,
|
||
|
|
"learning_rate": 4.8087685286915276e-05,
|
||
|
|
"loss": 0.5572,
|
||
|
|
"num_tokens": 99383692.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18417462482946795,
|
||
|
|
"grad_norm": 0.40405586857695963,
|
||
|
|
"learning_rate": 4.787759508006147e-05,
|
||
|
|
"loss": 0.5568,
|
||
|
|
"num_tokens": 103223537.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.19099590723055934,
|
||
|
|
"grad_norm": 0.4324587813631283,
|
||
|
|
"learning_rate": 4.765712586707048e-05,
|
||
|
|
"loss": 0.5694,
|
||
|
|
"num_tokens": 106901687.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.19781718963165076,
|
||
|
|
"grad_norm": 0.4024036288115306,
|
||
|
|
"learning_rate": 4.7426389940453065e-05,
|
||
|
|
"loss": 0.542,
|
||
|
|
"num_tokens": 110840758.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.20463847203274216,
|
||
|
|
"grad_norm": 0.42624775460173636,
|
||
|
|
"learning_rate": 4.718550482190837e-05,
|
||
|
|
"loss": 0.5579,
|
||
|
|
"num_tokens": 114521504.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.21145975443383355,
|
||
|
|
"grad_norm": 0.3394520387215503,
|
||
|
|
"learning_rate": 4.6934593202466127e-05,
|
||
|
|
"loss": 0.5424,
|
||
|
|
"num_tokens": 118445759.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.21828103683492497,
|
||
|
|
"grad_norm": 0.36684991077490176,
|
||
|
|
"learning_rate": 4.6673782879995896e-05,
|
||
|
|
"loss": 0.5511,
|
||
|
|
"num_tokens": 122311693.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.22510231923601637,
|
||
|
|
"grad_norm": 0.3418183579126294,
|
||
|
|
"learning_rate": 4.640320669411526e-05,
|
||
|
|
"loss": 0.554,
|
||
|
|
"num_tokens": 126094524.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.23192360163710776,
|
||
|
|
"grad_norm": 0.3573109791196806,
|
||
|
|
"learning_rate": 4.612300245853004e-05,
|
||
|
|
"loss": 0.5473,
|
||
|
|
"num_tokens": 129971056.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.23874488403819918,
|
||
|
|
"grad_norm": 0.4404011696788091,
|
||
|
|
"learning_rate": 4.5833312890841085e-05,
|
||
|
|
"loss": 0.562,
|
||
|
|
"num_tokens": 133765982.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.24556616643929058,
|
||
|
|
"grad_norm": 0.39333767306296735,
|
||
|
|
"learning_rate": 4.553428553985329e-05,
|
||
|
|
"loss": 0.5417,
|
||
|
|
"num_tokens": 137522281.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.252387448840382,
|
||
|
|
"grad_norm": 0.3766363049697423,
|
||
|
|
"learning_rate": 4.522607271042399e-05,
|
||
|
|
"loss": 0.5366,
|
||
|
|
"num_tokens": 141196084.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2592087312414734,
|
||
|
|
"grad_norm": 0.4330332210434021,
|
||
|
|
"learning_rate": 4.490883138588882e-05,
|
||
|
|
"loss": 0.548,
|
||
|
|
"num_tokens": 145136704.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2660300136425648,
|
||
|
|
"grad_norm": 0.3130688257115034,
|
||
|
|
"learning_rate": 4.458272314810479e-05,
|
||
|
|
"loss": 0.5358,
|
||
|
|
"num_tokens": 148940122.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2728512960436562,
|
||
|
|
"grad_norm": 0.2958242457017384,
|
||
|
|
"learning_rate": 4.4247914095151086e-05,
|
||
|
|
"loss": 0.5456,
|
||
|
|
"num_tokens": 152809678.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.27967257844474763,
|
||
|
|
"grad_norm": 0.3631423972213163,
|
||
|
|
"learning_rate": 4.390457475672966e-05,
|
||
|
|
"loss": 0.5393,
|
||
|
|
"num_tokens": 156683573.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.286493860845839,
|
||
|
|
"grad_norm": 0.33299961683660967,
|
||
|
|
"learning_rate": 4.35528800073086e-05,
|
||
|
|
"loss": 0.5408,
|
||
|
|
"num_tokens": 160433326.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2933151432469304,
|
||
|
|
"grad_norm": 0.34487494790560014,
|
||
|
|
"learning_rate": 4.31930089770526e-05,
|
||
|
|
"loss": 0.5442,
|
||
|
|
"num_tokens": 164374316.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.30013642564802184,
|
||
|
|
"grad_norm": 0.33594816899871066,
|
||
|
|
"learning_rate": 4.282514496058582e-05,
|
||
|
|
"loss": 0.5238,
|
||
|
|
"num_tokens": 168223299.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3069577080491132,
|
||
|
|
"grad_norm": 0.2901309516034236,
|
||
|
|
"learning_rate": 4.24494753236337e-05,
|
||
|
|
"loss": 0.5365,
|
||
|
|
"num_tokens": 172132000.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.31377899045020463,
|
||
|
|
"grad_norm": 0.3239699981737236,
|
||
|
|
"learning_rate": 4.2066191407591125e-05,
|
||
|
|
"loss": 0.5321,
|
||
|
|
"num_tokens": 176086331.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.32060027285129605,
|
||
|
|
"grad_norm": 0.29347190102008297,
|
||
|
|
"learning_rate": 4.1675488432065785e-05,
|
||
|
|
"loss": 0.5244,
|
||
|
|
"num_tokens": 179917640.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3274215552523875,
|
||
|
|
"grad_norm": 0.2896636007704082,
|
||
|
|
"learning_rate": 4.127756539544609e-05,
|
||
|
|
"loss": 0.537,
|
||
|
|
"num_tokens": 183746129.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.33424283765347884,
|
||
|
|
"grad_norm": 0.37369409333673687,
|
||
|
|
"learning_rate": 4.087262497354452e-05,
|
||
|
|
"loss": 0.5454,
|
||
|
|
"num_tokens": 187699370.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.34106412005457026,
|
||
|
|
"grad_norm": 0.30263051124642876,
|
||
|
|
"learning_rate": 4.046087341636789e-05,
|
||
|
|
"loss": 0.5279,
|
||
|
|
"num_tokens": 191512142.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3478854024556617,
|
||
|
|
"grad_norm": 0.30602907118420253,
|
||
|
|
"learning_rate": 4.0042520443067176e-05,
|
||
|
|
"loss": 0.5292,
|
||
|
|
"num_tokens": 195367749.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.35470668485675305,
|
||
|
|
"grad_norm": 0.30856496307351244,
|
||
|
|
"learning_rate": 3.961777913512035e-05,
|
||
|
|
"loss": 0.5182,
|
||
|
|
"num_tokens": 199215371.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3615279672578445,
|
||
|
|
"grad_norm": 0.2991290787509346,
|
||
|
|
"learning_rate": 3.9186865827802724e-05,
|
||
|
|
"loss": 0.5378,
|
||
|
|
"num_tokens": 202903048.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3683492496589359,
|
||
|
|
"grad_norm": 0.3122122629436248,
|
||
|
|
"learning_rate": 3.875e-05,
|
||
|
|
"loss": 0.5266,
|
||
|
|
"num_tokens": 206761213.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.37517053206002726,
|
||
|
|
"grad_norm": 0.2853089099996772,
|
||
|
|
"learning_rate": 3.830740416242014e-05,
|
||
|
|
"loss": 0.5225,
|
||
|
|
"num_tokens": 210585632.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3819918144611187,
|
||
|
|
"grad_norm": 0.30512356970359406,
|
||
|
|
"learning_rate": 3.7859303744261064e-05,
|
||
|
|
"loss": 0.5282,
|
||
|
|
"num_tokens": 214261738.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3888130968622101,
|
||
|
|
"grad_norm": 0.27496627808176893,
|
||
|
|
"learning_rate": 3.740592697839185e-05,
|
||
|
|
"loss": 0.533,
|
||
|
|
"num_tokens": 218144024.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3956343792633015,
|
||
|
|
"grad_norm": 0.2708720303111062,
|
||
|
|
"learning_rate": 3.694750478510596e-05,
|
||
|
|
"loss": 0.5285,
|
||
|
|
"num_tokens": 222057295.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4024556616643929,
|
||
|
|
"grad_norm": 0.2731317149721799,
|
||
|
|
"learning_rate": 3.648427065450555e-05,
|
||
|
|
"loss": 0.5198,
|
||
|
|
"num_tokens": 225828573.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4092769440654843,
|
||
|
|
"grad_norm": 0.2838811843668512,
|
||
|
|
"learning_rate": 3.601646052757707e-05,
|
||
|
|
"loss": 0.519,
|
||
|
|
"num_tokens": 229710487.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.41609822646657574,
|
||
|
|
"grad_norm": 0.31150738136265943,
|
||
|
|
"learning_rate": 3.55443126760184e-05,
|
||
|
|
"loss": 0.5344,
|
||
|
|
"num_tokens": 3907038.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4229195088676671,
|
||
|
|
"grad_norm": 0.3468593061143695,
|
||
|
|
"learning_rate": 3.506806758087894e-05,
|
||
|
|
"loss": 0.532,
|
||
|
|
"num_tokens": 7683984.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4297407912687585,
|
||
|
|
"grad_norm": 0.31656776462890823,
|
||
|
|
"learning_rate": 3.458796781007437e-05,
|
||
|
|
"loss": 0.5267,
|
||
|
|
"num_tokens": 11403774.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.43656207366984995,
|
||
|
|
"grad_norm": 0.2905862187240268,
|
||
|
|
"learning_rate": 3.410425789483854e-05,
|
||
|
|
"loss": 0.527,
|
||
|
|
"num_tokens": 15257500.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4433833560709413,
|
||
|
|
"grad_norm": 0.2862429453666647,
|
||
|
|
"learning_rate": 3.3617184205175304e-05,
|
||
|
|
"loss": 0.5335,
|
||
|
|
"num_tokens": 19040608.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.45020463847203274,
|
||
|
|
"grad_norm": 0.34169112866025547,
|
||
|
|
"learning_rate": 3.312699482437392e-05,
|
||
|
|
"loss": 0.5207,
|
||
|
|
"num_tokens": 22896778.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.45702592087312416,
|
||
|
|
"grad_norm": 0.28811353179764293,
|
||
|
|
"learning_rate": 3.263393942265168e-05,
|
||
|
|
"loss": 0.5274,
|
||
|
|
"num_tokens": 26707422.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4638472032742155,
|
||
|
|
"grad_norm": 0.25952079134670186,
|
||
|
|
"learning_rate": 3.213826912998838e-05,
|
||
|
|
"loss": 0.5199,
|
||
|
|
"num_tokens": 30745942.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.47066848567530695,
|
||
|
|
"grad_norm": 0.27171779465267426,
|
||
|
|
"learning_rate": 3.164023640821719e-05,
|
||
|
|
"loss": 0.5131,
|
||
|
|
"num_tokens": 34577418.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.47748976807639837,
|
||
|
|
"grad_norm": 0.2756410136692784,
|
||
|
|
"learning_rate": 3.114009492243721e-05,
|
||
|
|
"loss": 0.5216,
|
||
|
|
"num_tokens": 38388303.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4843110504774898,
|
||
|
|
"grad_norm": 0.2862166299702774,
|
||
|
|
"learning_rate": 3.063809941181321e-05,
|
||
|
|
"loss": 0.5312,
|
||
|
|
"num_tokens": 42263578.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.49113233287858116,
|
||
|
|
"grad_norm": 0.2776215155538455,
|
||
|
|
"learning_rate": 3.0134505559828203e-05,
|
||
|
|
"loss": 0.535,
|
||
|
|
"num_tokens": 46141558.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4979536152796726,
|
||
|
|
"grad_norm": 0.27939238016420803,
|
||
|
|
"learning_rate": 2.9629569864055125e-05,
|
||
|
|
"loss": 0.5129,
|
||
|
|
"num_tokens": 49793997.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.504774897680764,
|
||
|
|
"grad_norm": 0.27656045657678896,
|
||
|
|
"learning_rate": 2.9123549505513868e-05,
|
||
|
|
"loss": 0.5149,
|
||
|
|
"num_tokens": 53751059.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5115961800818554,
|
||
|
|
"grad_norm": 0.2612718920094276,
|
||
|
|
"learning_rate": 2.8616702217680134e-05,
|
||
|
|
"loss": 0.5229,
|
||
|
|
"num_tokens": 57661431.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5184174624829468,
|
||
|
|
"grad_norm": 0.2707456092353873,
|
||
|
|
"learning_rate": 2.810928615521303e-05,
|
||
|
|
"loss": 0.5096,
|
||
|
|
"num_tokens": 61347251.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5252387448840382,
|
||
|
|
"grad_norm": 0.2775857141913436,
|
||
|
|
"learning_rate": 2.7601559762468022e-05,
|
||
|
|
"loss": 0.5188,
|
||
|
|
"num_tokens": 65171476.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5320600272851296,
|
||
|
|
"grad_norm": 0.2749180870715325,
|
||
|
|
"learning_rate": 2.7093781641862387e-05,
|
||
|
|
"loss": 0.5214,
|
||
|
|
"num_tokens": 68967408.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.538881309686221,
|
||
|
|
"grad_norm": 0.2736617594464445,
|
||
|
|
"learning_rate": 2.658621042216021e-05,
|
||
|
|
"loss": 0.5056,
|
||
|
|
"num_tokens": 72677498.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5457025920873124,
|
||
|
|
"grad_norm": 0.3724340666807813,
|
||
|
|
"learning_rate": 2.6079104626743845e-05,
|
||
|
|
"loss": 0.5275,
|
||
|
|
"num_tokens": 76420106.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5525238744884038,
|
||
|
|
"grad_norm": 0.30148187800324094,
|
||
|
|
"learning_rate": 2.5572722541939113e-05,
|
||
|
|
"loss": 0.536,
|
||
|
|
"num_tokens": 80241521.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5593451568894953,
|
||
|
|
"grad_norm": 0.2878146937468534,
|
||
|
|
"learning_rate": 2.5067322085461315e-05,
|
||
|
|
"loss": 0.5108,
|
||
|
|
"num_tokens": 84015002.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5661664392905866,
|
||
|
|
"grad_norm": 0.28481014661061205,
|
||
|
|
"learning_rate": 2.4563160675048846e-05,
|
||
|
|
"loss": 0.5158,
|
||
|
|
"num_tokens": 87814661.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.572987721691678,
|
||
|
|
"grad_norm": 0.24871308571539336,
|
||
|
|
"learning_rate": 2.406049509735156e-05,
|
||
|
|
"loss": 0.5154,
|
||
|
|
"num_tokens": 91699614.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5798090040927695,
|
||
|
|
"grad_norm": 0.26997468779109357,
|
||
|
|
"learning_rate": 2.355958137714056e-05,
|
||
|
|
"loss": 0.5108,
|
||
|
|
"num_tokens": 95391791.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5866302864938608,
|
||
|
|
"grad_norm": 0.26920569189193183,
|
||
|
|
"learning_rate": 2.3060674646906004e-05,
|
||
|
|
"loss": 0.5156,
|
||
|
|
"num_tokens": 99120584.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5934515688949522,
|
||
|
|
"grad_norm": 0.3031035959753903,
|
||
|
|
"learning_rate": 2.2564029016909416e-05,
|
||
|
|
"loss": 0.5049,
|
||
|
|
"num_tokens": 103056557.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6002728512960437,
|
||
|
|
"grad_norm": 0.2579912157887462,
|
||
|
|
"learning_rate": 2.2069897445756627e-05,
|
||
|
|
"loss": 0.5028,
|
||
|
|
"num_tokens": 106885151.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.607094133697135,
|
||
|
|
"grad_norm": 0.2784368496163028,
|
||
|
|
"learning_rate": 2.1578531611557322e-05,
|
||
|
|
"loss": 0.5158,
|
||
|
|
"num_tokens": 110648438.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6139154160982264,
|
||
|
|
"grad_norm": 0.23783581714130014,
|
||
|
|
"learning_rate": 2.109018178373675e-05,
|
||
|
|
"loss": 0.5147,
|
||
|
|
"num_tokens": 114528571.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6207366984993179,
|
||
|
|
"grad_norm": 0.2631301529092457,
|
||
|
|
"learning_rate": 2.0605096695564973e-05,
|
||
|
|
"loss": 0.5182,
|
||
|
|
"num_tokens": 118370098.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6275579809004093,
|
||
|
|
"grad_norm": 0.23896035357377207,
|
||
|
|
"learning_rate": 2.0123523417468466e-05,
|
||
|
|
"loss": 0.5115,
|
||
|
|
"num_tokens": 122107208.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6343792633015006,
|
||
|
|
"grad_norm": 0.23911200744006897,
|
||
|
|
"learning_rate": 1.9645707231188742e-05,
|
||
|
|
"loss": 0.5059,
|
||
|
|
"num_tokens": 125928696.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6412005457025921,
|
||
|
|
"grad_norm": 0.23484644246089895,
|
||
|
|
"learning_rate": 1.9171891504851925e-05,
|
||
|
|
"loss": 0.5245,
|
||
|
|
"num_tokens": 129727094.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6480218281036835,
|
||
|
|
"grad_norm": 0.24843133644098161,
|
||
|
|
"learning_rate": 1.8702317569013094e-05,
|
||
|
|
"loss": 0.5005,
|
||
|
|
"num_tokens": 133479496.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.654843110504775,
|
||
|
|
"grad_norm": 0.2298705134606327,
|
||
|
|
"learning_rate": 1.8237224593738327e-05,
|
||
|
|
"loss": 0.5027,
|
||
|
|
"num_tokens": 137152722.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6616643929058663,
|
||
|
|
"grad_norm": 0.22725265159045924,
|
||
|
|
"learning_rate": 1.7776849466787223e-05,
|
||
|
|
"loss": 0.5171,
|
||
|
|
"num_tokens": 141015373.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6684856753069577,
|
||
|
|
"grad_norm": 0.23065567630923026,
|
||
|
|
"learning_rate": 1.7321426672957896e-05,
|
||
|
|
"loss": 0.5025,
|
||
|
|
"num_tokens": 144856028.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6753069577080492,
|
||
|
|
"grad_norm": 0.2535249608874267,
|
||
|
|
"learning_rate": 1.6871188174655787e-05,
|
||
|
|
"loss": 0.4957,
|
||
|
|
"num_tokens": 148620002.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6821282401091405,
|
||
|
|
"grad_norm": 0.2364234203218564,
|
||
|
|
"learning_rate": 1.6426363293747334e-05,
|
||
|
|
"loss": 0.5001,
|
||
|
|
"num_tokens": 152392981.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6889495225102319,
|
||
|
|
"grad_norm": 0.23889880611363135,
|
||
|
|
"learning_rate": 1.598717859475846e-05,
|
||
|
|
"loss": 0.5087,
|
||
|
|
"num_tokens": 156126810.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6957708049113234,
|
||
|
|
"grad_norm": 0.2380901600704711,
|
||
|
|
"learning_rate": 1.5553857769477553e-05,
|
||
|
|
"loss": 0.5056,
|
||
|
|
"num_tokens": 159876193.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7025920873124147,
|
||
|
|
"grad_norm": 0.23096714274240995,
|
||
|
|
"learning_rate": 1.5126621523021518e-05,
|
||
|
|
"loss": 0.51,
|
||
|
|
"num_tokens": 163718273.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7094133697135061,
|
||
|
|
"grad_norm": 0.2614099659251973,
|
||
|
|
"learning_rate": 1.4705687461423209e-05,
|
||
|
|
"loss": 0.5222,
|
||
|
|
"num_tokens": 167448213.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7162346521145976,
|
||
|
|
"grad_norm": 0.24328778538778423,
|
||
|
|
"learning_rate": 1.4291269980797139e-05,
|
||
|
|
"loss": 0.5065,
|
||
|
|
"num_tokens": 171213451.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.723055934515689,
|
||
|
|
"grad_norm": 0.22585661056099277,
|
||
|
|
"learning_rate": 1.3883580158140291e-05,
|
||
|
|
"loss": 0.5005,
|
||
|
|
"num_tokens": 174975168.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7298772169167803,
|
||
|
|
"grad_norm": 0.215782449764828,
|
||
|
|
"learning_rate": 1.3482825643823293e-05,
|
||
|
|
"loss": 0.5061,
|
||
|
|
"num_tokens": 178872312.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7366984993178718,
|
||
|
|
"grad_norm": 0.222477664399686,
|
||
|
|
"learning_rate": 1.3089210555827086e-05,
|
||
|
|
"loss": 0.5118,
|
||
|
|
"num_tokens": 182675522.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7435197817189632,
|
||
|
|
"grad_norm": 0.2161279545613622,
|
||
|
|
"learning_rate": 1.270293537577855e-05,
|
||
|
|
"loss": 0.5148,
|
||
|
|
"num_tokens": 186661552.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7503410641200545,
|
||
|
|
"grad_norm": 0.22038438633805268,
|
||
|
|
"learning_rate": 1.232419684683844e-05,
|
||
|
|
"loss": 0.4995,
|
||
|
|
"num_tokens": 190341488.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.757162346521146,
|
||
|
|
"grad_norm": 0.22277137142362485,
|
||
|
|
"learning_rate": 1.1953187873493303e-05,
|
||
|
|
"loss": 0.5001,
|
||
|
|
"num_tokens": 193975222.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7639836289222374,
|
||
|
|
"grad_norm": 0.22629794051271598,
|
||
|
|
"learning_rate": 1.1590097423302684e-05,
|
||
|
|
"loss": 0.496,
|
||
|
|
"num_tokens": 197695417.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7708049113233287,
|
||
|
|
"grad_norm": 0.22169310674789464,
|
||
|
|
"learning_rate": 1.1235110430651421e-05,
|
||
|
|
"loss": 0.496,
|
||
|
|
"num_tokens": 201577891.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7776261937244202,
|
||
|
|
"grad_norm": 0.23737206300393107,
|
||
|
|
"learning_rate": 1.0888407702556284e-05,
|
||
|
|
"loss": 0.4998,
|
||
|
|
"num_tokens": 205367508.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7844474761255116,
|
||
|
|
"grad_norm": 0.2393464614182903,
|
||
|
|
"learning_rate": 1.0550165826574766e-05,
|
||
|
|
"loss": 0.4997,
|
||
|
|
"num_tokens": 209296377.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.791268758526603,
|
||
|
|
"grad_norm": 0.23434104494246727,
|
||
|
|
"learning_rate": 1.0220557080862985e-05,
|
||
|
|
"loss": 0.5149,
|
||
|
|
"num_tokens": 213335201.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7980900409276944,
|
||
|
|
"grad_norm": 0.2163862184189319,
|
||
|
|
"learning_rate": 9.899749346428556e-06,
|
||
|
|
"loss": 0.5021,
|
||
|
|
"num_tokens": 217141531.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8049113233287858,
|
||
|
|
"grad_norm": 0.20944439534899864,
|
||
|
|
"learning_rate": 9.587906021623016e-06,
|
||
|
|
"loss": 0.5161,
|
||
|
|
"num_tokens": 220976800.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8117326057298773,
|
||
|
|
"grad_norm": 0.240618025701599,
|
||
|
|
"learning_rate": 9.28518593891749e-06,
|
||
|
|
"loss": 0.5013,
|
||
|
|
"num_tokens": 224773409.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8185538881309686,
|
||
|
|
"grad_norm": 0.22360256823330674,
|
||
|
|
"learning_rate": 8.99174328400385e-06,
|
||
|
|
"loss": 0.4997,
|
||
|
|
"num_tokens": 228615374.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.82537517053206,
|
||
|
|
"grad_norm": 0.22996095480097895,
|
||
|
|
"learning_rate": 8.707727517262697e-06,
|
||
|
|
"loss": 0.5049,
|
||
|
|
"num_tokens": 232345381.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8321964529331515,
|
||
|
|
"grad_norm": 0.20996010138499008,
|
||
|
|
"learning_rate": 8.433283297638053e-06,
|
||
|
|
"loss": 0.4993,
|
||
|
|
"num_tokens": 236263389.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8390177353342428,
|
||
|
|
"grad_norm": 0.21860095878565663,
|
||
|
|
"learning_rate": 8.168550408957632e-06,
|
||
|
|
"loss": 0.497,
|
||
|
|
"num_tokens": 240081011.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8458390177353342,
|
||
|
|
"grad_norm": 0.2245915474005529,
|
||
|
|
"learning_rate": 7.91366368873613e-06,
|
||
|
|
"loss": 0.4944,
|
||
|
|
"num_tokens": 243860094.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8526603001364257,
|
||
|
|
"grad_norm": 0.2282695347327931,
|
||
|
|
"learning_rate": 7.66875295949791e-06,
|
||
|
|
"loss": 0.5105,
|
||
|
|
"num_tokens": 247690866.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.859481582537517,
|
||
|
|
"grad_norm": 0.20590616989328062,
|
||
|
|
"learning_rate": 7.4339429626539e-06,
|
||
|
|
"loss": 0.5102,
|
||
|
|
"num_tokens": 251638405.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8663028649386084,
|
||
|
|
"grad_norm": 0.22956608740204826,
|
||
|
|
"learning_rate": 7.2093532949665715e-06,
|
||
|
|
"loss": 0.5081,
|
||
|
|
"num_tokens": 255461423.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8731241473396999,
|
||
|
|
"grad_norm": 0.20757611016240565,
|
||
|
|
"learning_rate": 6.995098347635173e-06,
|
||
|
|
"loss": 0.4933,
|
||
|
|
"num_tokens": 259349061.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8799454297407913,
|
||
|
|
"grad_norm": 0.20964621674214579,
|
||
|
|
"learning_rate": 6.791287248032431e-06,
|
||
|
|
"loss": 0.4966,
|
||
|
|
"num_tokens": 263182542.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8867667121418826,
|
||
|
|
"grad_norm": 0.21533152300615474,
|
||
|
|
"learning_rate": 6.598023804122194e-06,
|
||
|
|
"loss": 0.5039,
|
||
|
|
"num_tokens": 267195187.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8935879945429741,
|
||
|
|
"grad_norm": 0.20262214665120437,
|
||
|
|
"learning_rate": 6.415406451586528e-06,
|
||
|
|
"loss": 0.4994,
|
||
|
|
"num_tokens": 271154055.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9004092769440655,
|
||
|
|
"grad_norm": 0.20455436089558837,
|
||
|
|
"learning_rate": 6.243528203689025e-06,
|
||
|
|
"loss": 0.5033,
|
||
|
|
"num_tokens": 275099879.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9072305593451568,
|
||
|
|
"grad_norm": 0.2160125533680774,
|
||
|
|
"learning_rate": 6.0824766039e-06,
|
||
|
|
"loss": 0.4994,
|
||
|
|
"num_tokens": 278896745.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9140518417462483,
|
||
|
|
"grad_norm": 0.20835263251242925,
|
||
|
|
"learning_rate": 5.932333681307571e-06,
|
||
|
|
"loss": 0.5062,
|
||
|
|
"num_tokens": 282763597.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9208731241473397,
|
||
|
|
"grad_norm": 0.2056127608186567,
|
||
|
|
"learning_rate": 5.793175908837471e-06,
|
||
|
|
"loss": 0.4967,
|
||
|
|
"num_tokens": 286505617.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.927694406548431,
|
||
|
|
"grad_norm": 0.20738306050857,
|
||
|
|
"learning_rate": 5.665074164302742e-06,
|
||
|
|
"loss": 0.5064,
|
||
|
|
"num_tokens": 290255858.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9345156889495225,
|
||
|
|
"grad_norm": 0.1943049409331778,
|
||
|
|
"learning_rate": 5.548093694303275e-06,
|
||
|
|
"loss": 0.4919,
|
||
|
|
"num_tokens": 294083350.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9413369713506139,
|
||
|
|
"grad_norm": 0.21891210362180955,
|
||
|
|
"learning_rate": 5.442294080993446e-06,
|
||
|
|
"loss": 0.5059,
|
||
|
|
"num_tokens": 297956377.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9481582537517054,
|
||
|
|
"grad_norm": 0.2045825966835107,
|
||
|
|
"learning_rate": 5.347729211734919e-06,
|
||
|
|
"loss": 0.5034,
|
||
|
|
"num_tokens": 301755872.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9549795361527967,
|
||
|
|
"grad_norm": 0.20096771321359547,
|
||
|
|
"learning_rate": 5.264447251649954e-06,
|
||
|
|
"loss": 0.5057,
|
||
|
|
"num_tokens": 305542730.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9618008185538881,
|
||
|
|
"grad_norm": 0.20627903017723062,
|
||
|
|
"learning_rate": 5.192490619089267e-06,
|
||
|
|
"loss": 0.49,
|
||
|
|
"num_tokens": 309426949.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9686221009549796,
|
||
|
|
"grad_norm": 0.20761322654529332,
|
||
|
|
"learning_rate": 5.1318959640269095e-06,
|
||
|
|
"loss": 0.5005,
|
||
|
|
"num_tokens": 313113611.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.975443383356071,
|
||
|
|
"grad_norm": 0.2108636029151623,
|
||
|
|
"learning_rate": 5.082694149393189e-06,
|
||
|
|
"loss": 0.5114,
|
||
|
|
"num_tokens": 316867560.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9822646657571623,
|
||
|
|
"grad_norm": 0.2031630473017727,
|
||
|
|
"learning_rate": 5.044910235355121e-06,
|
||
|
|
"loss": 0.4974,
|
||
|
|
"num_tokens": 320667324.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9890859481582538,
|
||
|
|
"grad_norm": 0.19315901995067375,
|
||
|
|
"learning_rate": 5.0185634665524255e-06,
|
||
|
|
"loss": 0.4934,
|
||
|
|
"num_tokens": 324513537.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9959072305593452,
|
||
|
|
"grad_norm": 0.1922060062694041,
|
||
|
|
"learning_rate": 5.003667262295572e-06,
|
||
|
|
"loss": 0.5015,
|
||
|
|
"num_tokens": 328290879.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"num_tokens": 330600785.0,
|
||
|
|
"step": 733,
|
||
|
|
"total_flos": 1147472759488512.0,
|
||
|
|
"train_loss": 0.30104584323107625,
|
||
|
|
"train_runtime": 3582.5752,
|
||
|
|
"train_samples_per_second": 26.164,
|
||
|
|
"train_steps_per_second": 0.205
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 733,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"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": 1147472759488512.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|