kenanga-lora-b-1-1200 / trainer_state.json
rmdhirr's picture
Upload folder using huggingface_hub
02af8f1 verified
Raw
History Blame Contribute Delete
46.3 kB
{
"best_global_step": 1200,
"best_metric": 1.2411783933639526,
"best_model_checkpoint": "outputs/checkpoint-1200",
"epoch": 0.23074704355350448,
"eval_steps": 300,
"global_step": 1200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009614460148062686,
"grad_norm": 5.263479232788086,
"learning_rate": 2.3032629558541267e-07,
"loss": 2.2998,
"step": 5
},
{
"epoch": 0.0019228920296125373,
"grad_norm": 4.919901371002197,
"learning_rate": 5.182341650671785e-07,
"loss": 2.2468,
"step": 10
},
{
"epoch": 0.002884338044418806,
"grad_norm": 3.7949042320251465,
"learning_rate": 8.061420345489444e-07,
"loss": 2.2097,
"step": 15
},
{
"epoch": 0.0038457840592250746,
"grad_norm": 3.5610361099243164,
"learning_rate": 1.0940499040307102e-06,
"loss": 2.083,
"step": 20
},
{
"epoch": 0.0048072300740313436,
"grad_norm": 3.32427978515625,
"learning_rate": 1.381957773512476e-06,
"loss": 2.0052,
"step": 25
},
{
"epoch": 0.005768676088837612,
"grad_norm": 3.5147716999053955,
"learning_rate": 1.6698656429942417e-06,
"loss": 2.043,
"step": 30
},
{
"epoch": 0.006730122103643881,
"grad_norm": 2.091193437576294,
"learning_rate": 1.9577735124760077e-06,
"loss": 2.0161,
"step": 35
},
{
"epoch": 0.007691568118450149,
"grad_norm": 2.3086185455322266,
"learning_rate": 2.2456813819577732e-06,
"loss": 1.9567,
"step": 40
},
{
"epoch": 0.008653014133256417,
"grad_norm": 1.6346129179000854,
"learning_rate": 2.5335892514395392e-06,
"loss": 1.8985,
"step": 45
},
{
"epoch": 0.009614460148062687,
"grad_norm": 1.260735034942627,
"learning_rate": 2.821497120921305e-06,
"loss": 1.8132,
"step": 50
},
{
"epoch": 0.010575906162868956,
"grad_norm": 1.5411990880966187,
"learning_rate": 3.109404990403071e-06,
"loss": 1.6944,
"step": 55
},
{
"epoch": 0.011537352177675224,
"grad_norm": 1.319563388824463,
"learning_rate": 3.397312859884837e-06,
"loss": 1.7036,
"step": 60
},
{
"epoch": 0.012498798192481493,
"grad_norm": 1.0878187417984009,
"learning_rate": 3.6852207293666026e-06,
"loss": 1.7662,
"step": 65
},
{
"epoch": 0.013460244207287761,
"grad_norm": 1.1386423110961914,
"learning_rate": 3.973128598848369e-06,
"loss": 1.6783,
"step": 70
},
{
"epoch": 0.01442169022209403,
"grad_norm": 1.2391140460968018,
"learning_rate": 4.2610364683301346e-06,
"loss": 1.5672,
"step": 75
},
{
"epoch": 0.015383136236900298,
"grad_norm": 1.0566521883010864,
"learning_rate": 4.5489443378119e-06,
"loss": 1.6949,
"step": 80
},
{
"epoch": 0.016344582251706565,
"grad_norm": 1.0937573909759521,
"learning_rate": 4.8368522072936665e-06,
"loss": 1.5464,
"step": 85
},
{
"epoch": 0.017306028266512834,
"grad_norm": 1.0400891304016113,
"learning_rate": 5.124760076775432e-06,
"loss": 1.5824,
"step": 90
},
{
"epoch": 0.018267474281319102,
"grad_norm": 1.1960211992263794,
"learning_rate": 5.4126679462571984e-06,
"loss": 1.6269,
"step": 95
},
{
"epoch": 0.019228920296125374,
"grad_norm": 1.197791576385498,
"learning_rate": 5.7005758157389635e-06,
"loss": 1.5177,
"step": 100
},
{
"epoch": 0.020190366310931643,
"grad_norm": 0.9536961913108826,
"learning_rate": 5.9884836852207295e-06,
"loss": 1.6222,
"step": 105
},
{
"epoch": 0.02115181232573791,
"grad_norm": 0.9854758977890015,
"learning_rate": 6.2763915547024955e-06,
"loss": 1.5503,
"step": 110
},
{
"epoch": 0.02211325834054418,
"grad_norm": 0.8579792976379395,
"learning_rate": 6.5642994241842614e-06,
"loss": 1.5246,
"step": 115
},
{
"epoch": 0.02307470435535045,
"grad_norm": 0.8161287307739258,
"learning_rate": 6.852207293666027e-06,
"loss": 1.5207,
"step": 120
},
{
"epoch": 0.024036150370156717,
"grad_norm": 1.0825903415679932,
"learning_rate": 7.1401151631477925e-06,
"loss": 1.4963,
"step": 125
},
{
"epoch": 0.024997596384962985,
"grad_norm": 0.9904459118843079,
"learning_rate": 7.4280230326295585e-06,
"loss": 1.5351,
"step": 130
},
{
"epoch": 0.025959042399769254,
"grad_norm": 1.0706708431243896,
"learning_rate": 7.715930902111324e-06,
"loss": 1.477,
"step": 135
},
{
"epoch": 0.026920488414575523,
"grad_norm": 0.910792887210846,
"learning_rate": 8.003838771593091e-06,
"loss": 1.563,
"step": 140
},
{
"epoch": 0.02788193442938179,
"grad_norm": 0.8813047409057617,
"learning_rate": 8.291746641074856e-06,
"loss": 1.5286,
"step": 145
},
{
"epoch": 0.02884338044418806,
"grad_norm": 1.135494589805603,
"learning_rate": 8.579654510556621e-06,
"loss": 1.4987,
"step": 150
},
{
"epoch": 0.029804826458994328,
"grad_norm": 1.4200812578201294,
"learning_rate": 8.867562380038388e-06,
"loss": 1.5176,
"step": 155
},
{
"epoch": 0.030766272473800597,
"grad_norm": 0.9361958503723145,
"learning_rate": 9.155470249520153e-06,
"loss": 1.5375,
"step": 160
},
{
"epoch": 0.031727718488606865,
"grad_norm": 0.7996511459350586,
"learning_rate": 9.44337811900192e-06,
"loss": 1.504,
"step": 165
},
{
"epoch": 0.03268916450341313,
"grad_norm": 0.8341512680053711,
"learning_rate": 9.731285988483685e-06,
"loss": 1.5099,
"step": 170
},
{
"epoch": 0.0336506105182194,
"grad_norm": 0.8165861368179321,
"learning_rate": 1.001919385796545e-05,
"loss": 1.4714,
"step": 175
},
{
"epoch": 0.03461205653302567,
"grad_norm": 1.0153369903564453,
"learning_rate": 1.0307101727447217e-05,
"loss": 1.4675,
"step": 180
},
{
"epoch": 0.03557350254783194,
"grad_norm": 0.8753921985626221,
"learning_rate": 1.0595009596928982e-05,
"loss": 1.478,
"step": 185
},
{
"epoch": 0.036534948562638205,
"grad_norm": 0.8925352096557617,
"learning_rate": 1.088291746641075e-05,
"loss": 1.4238,
"step": 190
},
{
"epoch": 0.037496394577444477,
"grad_norm": 0.8326230049133301,
"learning_rate": 1.1170825335892514e-05,
"loss": 1.4648,
"step": 195
},
{
"epoch": 0.03845784059225075,
"grad_norm": 1.0663974285125732,
"learning_rate": 1.1458733205374281e-05,
"loss": 1.5123,
"step": 200
},
{
"epoch": 0.039419286607057014,
"grad_norm": 1.0833837985992432,
"learning_rate": 1.1746641074856046e-05,
"loss": 1.5031,
"step": 205
},
{
"epoch": 0.040380732621863286,
"grad_norm": 0.8054072260856628,
"learning_rate": 1.2034548944337811e-05,
"loss": 1.4416,
"step": 210
},
{
"epoch": 0.04134217863666955,
"grad_norm": 0.8595219850540161,
"learning_rate": 1.2322456813819578e-05,
"loss": 1.4417,
"step": 215
},
{
"epoch": 0.04230362465147582,
"grad_norm": 0.8635595440864563,
"learning_rate": 1.2610364683301345e-05,
"loss": 1.4175,
"step": 220
},
{
"epoch": 0.04326507066628209,
"grad_norm": 0.8640530705451965,
"learning_rate": 1.289827255278311e-05,
"loss": 1.4442,
"step": 225
},
{
"epoch": 0.04422651668108836,
"grad_norm": 0.8653771281242371,
"learning_rate": 1.3186180422264875e-05,
"loss": 1.4193,
"step": 230
},
{
"epoch": 0.045187962695894625,
"grad_norm": 0.7947669625282288,
"learning_rate": 1.347408829174664e-05,
"loss": 1.4092,
"step": 235
},
{
"epoch": 0.0461494087107009,
"grad_norm": 0.8416963815689087,
"learning_rate": 1.3761996161228407e-05,
"loss": 1.5512,
"step": 240
},
{
"epoch": 0.04711085472550716,
"grad_norm": 0.9726578593254089,
"learning_rate": 1.4049904030710174e-05,
"loss": 1.4525,
"step": 245
},
{
"epoch": 0.048072300740313434,
"grad_norm": 1.0061571598052979,
"learning_rate": 1.4337811900191939e-05,
"loss": 1.4552,
"step": 250
},
{
"epoch": 0.0490337467551197,
"grad_norm": 0.8465285897254944,
"learning_rate": 1.4625719769673704e-05,
"loss": 1.3991,
"step": 255
},
{
"epoch": 0.04999519276992597,
"grad_norm": 0.9697036147117615,
"learning_rate": 1.491362763915547e-05,
"loss": 1.4067,
"step": 260
},
{
"epoch": 0.050956638784732236,
"grad_norm": 0.9910932183265686,
"learning_rate": 1.5201535508637236e-05,
"loss": 1.4834,
"step": 265
},
{
"epoch": 0.05191808479953851,
"grad_norm": 0.937353789806366,
"learning_rate": 1.5489443378119003e-05,
"loss": 1.4806,
"step": 270
},
{
"epoch": 0.05287953081434477,
"grad_norm": 0.873612105846405,
"learning_rate": 1.577735124760077e-05,
"loss": 1.4694,
"step": 275
},
{
"epoch": 0.053840976829151045,
"grad_norm": 0.7373448610305786,
"learning_rate": 1.6065259117082533e-05,
"loss": 1.4042,
"step": 280
},
{
"epoch": 0.05480242284395731,
"grad_norm": 0.771385908126831,
"learning_rate": 1.63531669865643e-05,
"loss": 1.418,
"step": 285
},
{
"epoch": 0.05576386885876358,
"grad_norm": 0.8392884731292725,
"learning_rate": 1.6641074856046063e-05,
"loss": 1.3782,
"step": 290
},
{
"epoch": 0.05672531487356985,
"grad_norm": 0.8971521258354187,
"learning_rate": 1.692898272552783e-05,
"loss": 1.503,
"step": 295
},
{
"epoch": 0.05768676088837612,
"grad_norm": 0.938372790813446,
"learning_rate": 1.72168905950096e-05,
"loss": 1.4005,
"step": 300
},
{
"epoch": 0.05768676088837612,
"eval_loss": 1.4069678783416748,
"eval_runtime": 1829.2346,
"eval_samples_per_second": 11.372,
"eval_steps_per_second": 2.843,
"step": 300
},
{
"epoch": 0.058648206903182384,
"grad_norm": 0.8293926119804382,
"learning_rate": 1.7504798464491364e-05,
"loss": 1.3648,
"step": 305
},
{
"epoch": 0.059609652917988656,
"grad_norm": 0.9733208417892456,
"learning_rate": 1.779270633397313e-05,
"loss": 1.4087,
"step": 310
},
{
"epoch": 0.06057109893279492,
"grad_norm": 0.9246333241462708,
"learning_rate": 1.8080614203454894e-05,
"loss": 1.4551,
"step": 315
},
{
"epoch": 0.061532544947601193,
"grad_norm": 0.7493950724601746,
"learning_rate": 1.836852207293666e-05,
"loss": 1.4551,
"step": 320
},
{
"epoch": 0.06249399096240746,
"grad_norm": 1.0027576684951782,
"learning_rate": 1.8656429942418428e-05,
"loss": 1.3908,
"step": 325
},
{
"epoch": 0.06345543697721373,
"grad_norm": 0.8040695190429688,
"learning_rate": 1.894433781190019e-05,
"loss": 1.424,
"step": 330
},
{
"epoch": 0.06441688299202,
"grad_norm": 0.8406041264533997,
"learning_rate": 1.9232245681381958e-05,
"loss": 1.353,
"step": 335
},
{
"epoch": 0.06537832900682626,
"grad_norm": 0.9334944486618042,
"learning_rate": 1.952015355086372e-05,
"loss": 1.431,
"step": 340
},
{
"epoch": 0.06633977502163253,
"grad_norm": 0.7912152409553528,
"learning_rate": 1.980806142034549e-05,
"loss": 1.4298,
"step": 345
},
{
"epoch": 0.0673012210364388,
"grad_norm": 0.9743331670761108,
"learning_rate": 2.009596928982726e-05,
"loss": 1.357,
"step": 350
},
{
"epoch": 0.06826266705124508,
"grad_norm": 0.9452155232429504,
"learning_rate": 2.0383877159309022e-05,
"loss": 1.4023,
"step": 355
},
{
"epoch": 0.06922411306605133,
"grad_norm": 0.8321967124938965,
"learning_rate": 2.067178502879079e-05,
"loss": 1.4188,
"step": 360
},
{
"epoch": 0.0701855590808576,
"grad_norm": 0.8946035504341125,
"learning_rate": 2.0959692898272552e-05,
"loss": 1.3417,
"step": 365
},
{
"epoch": 0.07114700509566388,
"grad_norm": 0.8722978234291077,
"learning_rate": 2.124760076775432e-05,
"loss": 1.4045,
"step": 370
},
{
"epoch": 0.07210845111047015,
"grad_norm": 1.0040546655654907,
"learning_rate": 2.1535508637236086e-05,
"loss": 1.4069,
"step": 375
},
{
"epoch": 0.07306989712527641,
"grad_norm": 0.8072942495346069,
"learning_rate": 2.182341650671785e-05,
"loss": 1.3406,
"step": 380
},
{
"epoch": 0.07403134314008268,
"grad_norm": 0.9878551363945007,
"learning_rate": 2.2111324376199616e-05,
"loss": 1.4355,
"step": 385
},
{
"epoch": 0.07499278915488895,
"grad_norm": 1.0963833332061768,
"learning_rate": 2.2399232245681383e-05,
"loss": 1.4208,
"step": 390
},
{
"epoch": 0.07595423516969523,
"grad_norm": 0.9907721281051636,
"learning_rate": 2.268714011516315e-05,
"loss": 1.3403,
"step": 395
},
{
"epoch": 0.0769156811845015,
"grad_norm": 0.9433814287185669,
"learning_rate": 2.2975047984644916e-05,
"loss": 1.3567,
"step": 400
},
{
"epoch": 0.07787712719930776,
"grad_norm": 0.9044313430786133,
"learning_rate": 2.326295585412668e-05,
"loss": 1.4668,
"step": 405
},
{
"epoch": 0.07883857321411403,
"grad_norm": 0.9079594612121582,
"learning_rate": 2.3550863723608447e-05,
"loss": 1.3796,
"step": 410
},
{
"epoch": 0.0798000192289203,
"grad_norm": 0.9176523685455322,
"learning_rate": 2.383877159309021e-05,
"loss": 1.41,
"step": 415
},
{
"epoch": 0.08076146524372657,
"grad_norm": 0.9850307106971741,
"learning_rate": 2.4126679462571977e-05,
"loss": 1.4052,
"step": 420
},
{
"epoch": 0.08172291125853283,
"grad_norm": 1.0259281396865845,
"learning_rate": 2.4414587332053744e-05,
"loss": 1.4044,
"step": 425
},
{
"epoch": 0.0826843572733391,
"grad_norm": 0.9912247061729431,
"learning_rate": 2.470249520153551e-05,
"loss": 1.3343,
"step": 430
},
{
"epoch": 0.08364580328814537,
"grad_norm": 0.9430367946624756,
"learning_rate": 2.4990403071017277e-05,
"loss": 1.4015,
"step": 435
},
{
"epoch": 0.08460724930295165,
"grad_norm": 0.9094961285591125,
"learning_rate": 2.527831094049904e-05,
"loss": 1.469,
"step": 440
},
{
"epoch": 0.0855686953177579,
"grad_norm": 0.8672477006912231,
"learning_rate": 2.5566218809980807e-05,
"loss": 1.3456,
"step": 445
},
{
"epoch": 0.08653014133256418,
"grad_norm": 0.9972670078277588,
"learning_rate": 2.5854126679462574e-05,
"loss": 1.2994,
"step": 450
},
{
"epoch": 0.08749158734737045,
"grad_norm": 0.9733589887619019,
"learning_rate": 2.6142034548944338e-05,
"loss": 1.3375,
"step": 455
},
{
"epoch": 0.08845303336217672,
"grad_norm": 0.9801984429359436,
"learning_rate": 2.6429942418426104e-05,
"loss": 1.3271,
"step": 460
},
{
"epoch": 0.08941447937698298,
"grad_norm": 0.8056566715240479,
"learning_rate": 2.6717850287907868e-05,
"loss": 1.3696,
"step": 465
},
{
"epoch": 0.09037592539178925,
"grad_norm": 0.9498573541641235,
"learning_rate": 2.7005758157389635e-05,
"loss": 1.3724,
"step": 470
},
{
"epoch": 0.09133737140659552,
"grad_norm": 0.9388139247894287,
"learning_rate": 2.7293666026871405e-05,
"loss": 1.3394,
"step": 475
},
{
"epoch": 0.0922988174214018,
"grad_norm": 0.9051626324653625,
"learning_rate": 2.758157389635317e-05,
"loss": 1.3465,
"step": 480
},
{
"epoch": 0.09326026343620805,
"grad_norm": 1.0678194761276245,
"learning_rate": 2.7869481765834935e-05,
"loss": 1.3369,
"step": 485
},
{
"epoch": 0.09422170945101432,
"grad_norm": 1.0179715156555176,
"learning_rate": 2.81573896353167e-05,
"loss": 1.2868,
"step": 490
},
{
"epoch": 0.0951831554658206,
"grad_norm": 1.025252103805542,
"learning_rate": 2.8445297504798465e-05,
"loss": 1.4128,
"step": 495
},
{
"epoch": 0.09614460148062687,
"grad_norm": 0.9994450211524963,
"learning_rate": 2.8733205374280232e-05,
"loss": 1.3105,
"step": 500
},
{
"epoch": 0.09710604749543313,
"grad_norm": 1.0843088626861572,
"learning_rate": 2.9021113243761996e-05,
"loss": 1.4405,
"step": 505
},
{
"epoch": 0.0980674935102394,
"grad_norm": 0.8648557662963867,
"learning_rate": 2.9309021113243762e-05,
"loss": 1.3738,
"step": 510
},
{
"epoch": 0.09902893952504567,
"grad_norm": 1.0407732725143433,
"learning_rate": 2.9596928982725526e-05,
"loss": 1.4331,
"step": 515
},
{
"epoch": 0.09999038553985194,
"grad_norm": 1.8220276832580566,
"learning_rate": 2.9884836852207296e-05,
"loss": 1.3347,
"step": 520
},
{
"epoch": 0.1009518315546582,
"grad_norm": 0.8917143940925598,
"learning_rate": 2.9990891610160915e-05,
"loss": 1.3576,
"step": 525
},
{
"epoch": 0.10191327756946447,
"grad_norm": 0.9336162209510803,
"learning_rate": 2.9975710960429106e-05,
"loss": 1.3353,
"step": 530
},
{
"epoch": 0.10287472358427074,
"grad_norm": 0.9028390049934387,
"learning_rate": 2.9960530310697297e-05,
"loss": 1.4185,
"step": 535
},
{
"epoch": 0.10383616959907702,
"grad_norm": 0.9123654365539551,
"learning_rate": 2.9945349660965488e-05,
"loss": 1.3747,
"step": 540
},
{
"epoch": 0.10479761561388327,
"grad_norm": 0.9282749891281128,
"learning_rate": 2.993016901123368e-05,
"loss": 1.3323,
"step": 545
},
{
"epoch": 0.10575906162868955,
"grad_norm": 1.06288743019104,
"learning_rate": 2.9914988361501872e-05,
"loss": 1.3638,
"step": 550
},
{
"epoch": 0.10672050764349582,
"grad_norm": 0.9988644123077393,
"learning_rate": 2.9899807711770063e-05,
"loss": 1.3527,
"step": 555
},
{
"epoch": 0.10768195365830209,
"grad_norm": 0.963537871837616,
"learning_rate": 2.9884627062038254e-05,
"loss": 1.3287,
"step": 560
},
{
"epoch": 0.10864339967310835,
"grad_norm": 1.1065447330474854,
"learning_rate": 2.9869446412306445e-05,
"loss": 1.3152,
"step": 565
},
{
"epoch": 0.10960484568791462,
"grad_norm": 0.9934567213058472,
"learning_rate": 2.985426576257464e-05,
"loss": 1.285,
"step": 570
},
{
"epoch": 0.11056629170272089,
"grad_norm": 0.9684432148933411,
"learning_rate": 2.983908511284283e-05,
"loss": 1.4081,
"step": 575
},
{
"epoch": 0.11152773771752716,
"grad_norm": 1.044866919517517,
"learning_rate": 2.982390446311102e-05,
"loss": 1.3684,
"step": 580
},
{
"epoch": 0.11248918373233342,
"grad_norm": 0.9235266447067261,
"learning_rate": 2.9808723813379215e-05,
"loss": 1.2453,
"step": 585
},
{
"epoch": 0.1134506297471397,
"grad_norm": 1.0257271528244019,
"learning_rate": 2.9793543163647405e-05,
"loss": 1.3664,
"step": 590
},
{
"epoch": 0.11441207576194597,
"grad_norm": 1.1091939210891724,
"learning_rate": 2.97783625139156e-05,
"loss": 1.2905,
"step": 595
},
{
"epoch": 0.11537352177675224,
"grad_norm": 0.9549099802970886,
"learning_rate": 2.976318186418379e-05,
"loss": 1.4162,
"step": 600
},
{
"epoch": 0.11537352177675224,
"eval_loss": 1.3265293836593628,
"eval_runtime": 1813.3194,
"eval_samples_per_second": 11.472,
"eval_steps_per_second": 2.868,
"step": 600
},
{
"epoch": 0.11633496779155851,
"grad_norm": 1.1611406803131104,
"learning_rate": 2.974800121445198e-05,
"loss": 1.2258,
"step": 605
},
{
"epoch": 0.11729641380636477,
"grad_norm": 1.0069003105163574,
"learning_rate": 2.9732820564720172e-05,
"loss": 1.2956,
"step": 610
},
{
"epoch": 0.11825785982117104,
"grad_norm": 0.8448907732963562,
"learning_rate": 2.9717639914988363e-05,
"loss": 1.35,
"step": 615
},
{
"epoch": 0.11921930583597731,
"grad_norm": 0.8714330792427063,
"learning_rate": 2.9702459265256557e-05,
"loss": 1.2409,
"step": 620
},
{
"epoch": 0.12018075185078358,
"grad_norm": 0.8822401762008667,
"learning_rate": 2.9687278615524747e-05,
"loss": 1.3148,
"step": 625
},
{
"epoch": 0.12114219786558984,
"grad_norm": 1.030093789100647,
"learning_rate": 2.9672097965792938e-05,
"loss": 1.3713,
"step": 630
},
{
"epoch": 0.12210364388039611,
"grad_norm": 1.0077892541885376,
"learning_rate": 2.965691731606113e-05,
"loss": 1.354,
"step": 635
},
{
"epoch": 0.12306508989520239,
"grad_norm": 1.0031296014785767,
"learning_rate": 2.964173666632932e-05,
"loss": 1.3483,
"step": 640
},
{
"epoch": 0.12402653591000866,
"grad_norm": 0.9184396266937256,
"learning_rate": 2.9626556016597514e-05,
"loss": 1.2783,
"step": 645
},
{
"epoch": 0.12498798192481492,
"grad_norm": 0.9425734281539917,
"learning_rate": 2.9611375366865705e-05,
"loss": 1.2896,
"step": 650
},
{
"epoch": 0.1259494279396212,
"grad_norm": 0.8437754511833191,
"learning_rate": 2.9596194717133895e-05,
"loss": 1.3343,
"step": 655
},
{
"epoch": 0.12691087395442746,
"grad_norm": 0.9617599844932556,
"learning_rate": 2.9581014067402086e-05,
"loss": 1.2472,
"step": 660
},
{
"epoch": 0.12787231996923373,
"grad_norm": 0.9239601492881775,
"learning_rate": 2.9565833417670277e-05,
"loss": 1.3209,
"step": 665
},
{
"epoch": 0.12883376598404,
"grad_norm": 0.9953628182411194,
"learning_rate": 2.955065276793847e-05,
"loss": 1.3152,
"step": 670
},
{
"epoch": 0.12979521199884628,
"grad_norm": 0.8559119701385498,
"learning_rate": 2.9535472118206662e-05,
"loss": 1.3301,
"step": 675
},
{
"epoch": 0.13075665801365252,
"grad_norm": 0.984180212020874,
"learning_rate": 2.9520291468474853e-05,
"loss": 1.3678,
"step": 680
},
{
"epoch": 0.1317181040284588,
"grad_norm": 0.9163925647735596,
"learning_rate": 2.9505110818743043e-05,
"loss": 1.3398,
"step": 685
},
{
"epoch": 0.13267955004326507,
"grad_norm": 1.1147078275680542,
"learning_rate": 2.9489930169011234e-05,
"loss": 1.2758,
"step": 690
},
{
"epoch": 0.13364099605807134,
"grad_norm": 0.980420708656311,
"learning_rate": 2.947474951927943e-05,
"loss": 1.3137,
"step": 695
},
{
"epoch": 0.1346024420728776,
"grad_norm": 1.0157663822174072,
"learning_rate": 2.945956886954762e-05,
"loss": 1.2144,
"step": 700
},
{
"epoch": 0.13556388808768388,
"grad_norm": 0.8547846078872681,
"learning_rate": 2.944438821981581e-05,
"loss": 1.2879,
"step": 705
},
{
"epoch": 0.13652533410249015,
"grad_norm": 1.018324851989746,
"learning_rate": 2.9429207570084e-05,
"loss": 1.267,
"step": 710
},
{
"epoch": 0.13748678011729643,
"grad_norm": 0.832151472568512,
"learning_rate": 2.941402692035219e-05,
"loss": 1.3185,
"step": 715
},
{
"epoch": 0.13844822613210267,
"grad_norm": 1.0583784580230713,
"learning_rate": 2.9398846270620386e-05,
"loss": 1.2489,
"step": 720
},
{
"epoch": 0.13940967214690894,
"grad_norm": 1.0460695028305054,
"learning_rate": 2.9383665620888576e-05,
"loss": 1.3299,
"step": 725
},
{
"epoch": 0.1403711181617152,
"grad_norm": 0.8800564408302307,
"learning_rate": 2.9368484971156767e-05,
"loss": 1.3494,
"step": 730
},
{
"epoch": 0.14133256417652149,
"grad_norm": 0.9371108412742615,
"learning_rate": 2.9353304321424958e-05,
"loss": 1.3129,
"step": 735
},
{
"epoch": 0.14229401019132776,
"grad_norm": 0.9252986907958984,
"learning_rate": 2.933812367169315e-05,
"loss": 1.3028,
"step": 740
},
{
"epoch": 0.14325545620613403,
"grad_norm": 0.9625592827796936,
"learning_rate": 2.9322943021961343e-05,
"loss": 1.366,
"step": 745
},
{
"epoch": 0.1442169022209403,
"grad_norm": 0.9188767671585083,
"learning_rate": 2.9307762372229534e-05,
"loss": 1.3584,
"step": 750
},
{
"epoch": 0.14517834823574657,
"grad_norm": 0.8308439254760742,
"learning_rate": 2.9292581722497724e-05,
"loss": 1.2567,
"step": 755
},
{
"epoch": 0.14613979425055282,
"grad_norm": 0.9764241576194763,
"learning_rate": 2.9277401072765915e-05,
"loss": 1.299,
"step": 760
},
{
"epoch": 0.1471012402653591,
"grad_norm": 0.854916512966156,
"learning_rate": 2.9262220423034106e-05,
"loss": 1.2568,
"step": 765
},
{
"epoch": 0.14806268628016536,
"grad_norm": 0.9988142251968384,
"learning_rate": 2.92470397733023e-05,
"loss": 1.2633,
"step": 770
},
{
"epoch": 0.14902413229497163,
"grad_norm": 1.032973051071167,
"learning_rate": 2.923185912357049e-05,
"loss": 1.3592,
"step": 775
},
{
"epoch": 0.1499855783097779,
"grad_norm": 1.057490587234497,
"learning_rate": 2.921667847383868e-05,
"loss": 1.3316,
"step": 780
},
{
"epoch": 0.15094702432458418,
"grad_norm": 0.9987697005271912,
"learning_rate": 2.9201497824106872e-05,
"loss": 1.2957,
"step": 785
},
{
"epoch": 0.15190847033939045,
"grad_norm": 1.0518527030944824,
"learning_rate": 2.9186317174375063e-05,
"loss": 1.3373,
"step": 790
},
{
"epoch": 0.15286991635419672,
"grad_norm": 0.9941504001617432,
"learning_rate": 2.9171136524643257e-05,
"loss": 1.3207,
"step": 795
},
{
"epoch": 0.153831362369003,
"grad_norm": 0.9565390348434448,
"learning_rate": 2.9155955874911448e-05,
"loss": 1.3035,
"step": 800
},
{
"epoch": 0.15479280838380924,
"grad_norm": 0.9072451591491699,
"learning_rate": 2.914077522517964e-05,
"loss": 1.3077,
"step": 805
},
{
"epoch": 0.1557542543986155,
"grad_norm": 0.8639485239982605,
"learning_rate": 2.912559457544783e-05,
"loss": 1.2388,
"step": 810
},
{
"epoch": 0.15671570041342178,
"grad_norm": 0.8549638390541077,
"learning_rate": 2.911041392571602e-05,
"loss": 1.2112,
"step": 815
},
{
"epoch": 0.15767714642822805,
"grad_norm": 0.9586772322654724,
"learning_rate": 2.9095233275984214e-05,
"loss": 1.3981,
"step": 820
},
{
"epoch": 0.15863859244303433,
"grad_norm": 1.0374456644058228,
"learning_rate": 2.9080052626252405e-05,
"loss": 1.2159,
"step": 825
},
{
"epoch": 0.1596000384578406,
"grad_norm": 0.9278589487075806,
"learning_rate": 2.9064871976520596e-05,
"loss": 1.2849,
"step": 830
},
{
"epoch": 0.16056148447264687,
"grad_norm": 0.8326074481010437,
"learning_rate": 2.9049691326788787e-05,
"loss": 1.3178,
"step": 835
},
{
"epoch": 0.16152293048745314,
"grad_norm": 1.0694983005523682,
"learning_rate": 2.9034510677056977e-05,
"loss": 1.2796,
"step": 840
},
{
"epoch": 0.1624843765022594,
"grad_norm": 1.1848194599151611,
"learning_rate": 2.901933002732517e-05,
"loss": 1.3145,
"step": 845
},
{
"epoch": 0.16344582251706566,
"grad_norm": 1.1083351373672485,
"learning_rate": 2.9004149377593362e-05,
"loss": 1.3274,
"step": 850
},
{
"epoch": 0.16440726853187193,
"grad_norm": 0.8984082937240601,
"learning_rate": 2.8988968727861553e-05,
"loss": 1.3023,
"step": 855
},
{
"epoch": 0.1653687145466782,
"grad_norm": 1.0397671461105347,
"learning_rate": 2.8973788078129744e-05,
"loss": 1.2713,
"step": 860
},
{
"epoch": 0.16633016056148447,
"grad_norm": 0.9931337237358093,
"learning_rate": 2.8958607428397935e-05,
"loss": 1.26,
"step": 865
},
{
"epoch": 0.16729160657629075,
"grad_norm": 1.0527026653289795,
"learning_rate": 2.894342677866613e-05,
"loss": 1.2944,
"step": 870
},
{
"epoch": 0.16825305259109702,
"grad_norm": 1.153441309928894,
"learning_rate": 2.892824612893432e-05,
"loss": 1.2475,
"step": 875
},
{
"epoch": 0.1692144986059033,
"grad_norm": 0.8572908639907837,
"learning_rate": 2.891306547920251e-05,
"loss": 1.242,
"step": 880
},
{
"epoch": 0.17017594462070953,
"grad_norm": 1.0271085500717163,
"learning_rate": 2.88978848294707e-05,
"loss": 1.3052,
"step": 885
},
{
"epoch": 0.1711373906355158,
"grad_norm": 1.0767736434936523,
"learning_rate": 2.8882704179738892e-05,
"loss": 1.2851,
"step": 890
},
{
"epoch": 0.17209883665032208,
"grad_norm": 0.9310041069984436,
"learning_rate": 2.8867523530007086e-05,
"loss": 1.367,
"step": 895
},
{
"epoch": 0.17306028266512835,
"grad_norm": 0.8906955122947693,
"learning_rate": 2.8852342880275277e-05,
"loss": 1.2853,
"step": 900
},
{
"epoch": 0.17306028266512835,
"eval_loss": 1.2756867408752441,
"eval_runtime": 1880.9614,
"eval_samples_per_second": 11.059,
"eval_steps_per_second": 2.765,
"step": 900
},
{
"epoch": 0.17402172867993462,
"grad_norm": 0.8874945640563965,
"learning_rate": 2.8837162230543468e-05,
"loss": 1.252,
"step": 905
},
{
"epoch": 0.1749831746947409,
"grad_norm": 0.992651641368866,
"learning_rate": 2.882198158081166e-05,
"loss": 1.3451,
"step": 910
},
{
"epoch": 0.17594462070954717,
"grad_norm": 1.1066889762878418,
"learning_rate": 2.8806800931079852e-05,
"loss": 1.2555,
"step": 915
},
{
"epoch": 0.17690606672435344,
"grad_norm": 1.0017170906066895,
"learning_rate": 2.8791620281348043e-05,
"loss": 1.3645,
"step": 920
},
{
"epoch": 0.17786751273915968,
"grad_norm": 1.146898627281189,
"learning_rate": 2.8776439631616234e-05,
"loss": 1.3557,
"step": 925
},
{
"epoch": 0.17882895875396596,
"grad_norm": 0.9736440777778625,
"learning_rate": 2.8761258981884425e-05,
"loss": 1.2755,
"step": 930
},
{
"epoch": 0.17979040476877223,
"grad_norm": 0.9591579437255859,
"learning_rate": 2.8746078332152616e-05,
"loss": 1.2618,
"step": 935
},
{
"epoch": 0.1807518507835785,
"grad_norm": 1.3127062320709229,
"learning_rate": 2.873089768242081e-05,
"loss": 1.2494,
"step": 940
},
{
"epoch": 0.18171329679838477,
"grad_norm": 1.2093756198883057,
"learning_rate": 2.8715717032689e-05,
"loss": 1.3055,
"step": 945
},
{
"epoch": 0.18267474281319104,
"grad_norm": 1.2279831171035767,
"learning_rate": 2.870053638295719e-05,
"loss": 1.2797,
"step": 950
},
{
"epoch": 0.18363618882799732,
"grad_norm": 0.9829315543174744,
"learning_rate": 2.8685355733225382e-05,
"loss": 1.252,
"step": 955
},
{
"epoch": 0.1845976348428036,
"grad_norm": 1.0075795650482178,
"learning_rate": 2.8670175083493573e-05,
"loss": 1.2432,
"step": 960
},
{
"epoch": 0.18555908085760983,
"grad_norm": 0.9815109968185425,
"learning_rate": 2.8654994433761767e-05,
"loss": 1.3011,
"step": 965
},
{
"epoch": 0.1865205268724161,
"grad_norm": 0.9473528265953064,
"learning_rate": 2.8639813784029958e-05,
"loss": 1.328,
"step": 970
},
{
"epoch": 0.18748197288722238,
"grad_norm": 1.0563870668411255,
"learning_rate": 2.862463313429815e-05,
"loss": 1.4197,
"step": 975
},
{
"epoch": 0.18844341890202865,
"grad_norm": 0.999548614025116,
"learning_rate": 2.860945248456634e-05,
"loss": 1.2636,
"step": 980
},
{
"epoch": 0.18940486491683492,
"grad_norm": 1.0543882846832275,
"learning_rate": 2.859427183483453e-05,
"loss": 1.2293,
"step": 985
},
{
"epoch": 0.1903663109316412,
"grad_norm": 1.0018796920776367,
"learning_rate": 2.8579091185102724e-05,
"loss": 1.262,
"step": 990
},
{
"epoch": 0.19132775694644746,
"grad_norm": 1.0547089576721191,
"learning_rate": 2.8563910535370915e-05,
"loss": 1.2329,
"step": 995
},
{
"epoch": 0.19228920296125374,
"grad_norm": 0.9648796916007996,
"learning_rate": 2.8548729885639106e-05,
"loss": 1.327,
"step": 1000
},
{
"epoch": 0.19325064897606,
"grad_norm": 0.964148998260498,
"learning_rate": 2.8533549235907296e-05,
"loss": 1.2733,
"step": 1005
},
{
"epoch": 0.19421209499086625,
"grad_norm": 1.0552051067352295,
"learning_rate": 2.8518368586175487e-05,
"loss": 1.2462,
"step": 1010
},
{
"epoch": 0.19517354100567252,
"grad_norm": 1.1029739379882812,
"learning_rate": 2.850318793644368e-05,
"loss": 1.2478,
"step": 1015
},
{
"epoch": 0.1961349870204788,
"grad_norm": 1.1883385181427002,
"learning_rate": 2.8488007286711872e-05,
"loss": 1.1937,
"step": 1020
},
{
"epoch": 0.19709643303528507,
"grad_norm": 0.9168397784233093,
"learning_rate": 2.8472826636980063e-05,
"loss": 1.3682,
"step": 1025
},
{
"epoch": 0.19805787905009134,
"grad_norm": 0.9574885964393616,
"learning_rate": 2.8457645987248254e-05,
"loss": 1.2358,
"step": 1030
},
{
"epoch": 0.1990193250648976,
"grad_norm": 1.0165746212005615,
"learning_rate": 2.8442465337516444e-05,
"loss": 1.2765,
"step": 1035
},
{
"epoch": 0.19998077107970388,
"grad_norm": 0.8473765254020691,
"learning_rate": 2.842728468778464e-05,
"loss": 1.1938,
"step": 1040
},
{
"epoch": 0.20094221709451016,
"grad_norm": 1.000200629234314,
"learning_rate": 2.841210403805283e-05,
"loss": 1.2242,
"step": 1045
},
{
"epoch": 0.2019036631093164,
"grad_norm": 1.1640363931655884,
"learning_rate": 2.839692338832102e-05,
"loss": 1.3152,
"step": 1050
},
{
"epoch": 0.20286510912412267,
"grad_norm": 1.0977058410644531,
"learning_rate": 2.838174273858921e-05,
"loss": 1.2639,
"step": 1055
},
{
"epoch": 0.20382655513892894,
"grad_norm": 1.0105798244476318,
"learning_rate": 2.83665620888574e-05,
"loss": 1.2381,
"step": 1060
},
{
"epoch": 0.20478800115373522,
"grad_norm": 0.9707632064819336,
"learning_rate": 2.8351381439125596e-05,
"loss": 1.2691,
"step": 1065
},
{
"epoch": 0.2057494471685415,
"grad_norm": 0.8312526345252991,
"learning_rate": 2.8336200789393787e-05,
"loss": 1.2571,
"step": 1070
},
{
"epoch": 0.20671089318334776,
"grad_norm": 0.8867915868759155,
"learning_rate": 2.8321020139661977e-05,
"loss": 1.3126,
"step": 1075
},
{
"epoch": 0.20767233919815403,
"grad_norm": 0.9358422160148621,
"learning_rate": 2.8305839489930168e-05,
"loss": 1.3131,
"step": 1080
},
{
"epoch": 0.2086337852129603,
"grad_norm": 1.0027930736541748,
"learning_rate": 2.829065884019836e-05,
"loss": 1.3345,
"step": 1085
},
{
"epoch": 0.20959523122776655,
"grad_norm": 0.9601215720176697,
"learning_rate": 2.8275478190466553e-05,
"loss": 1.2801,
"step": 1090
},
{
"epoch": 0.21055667724257282,
"grad_norm": 0.8792690634727478,
"learning_rate": 2.8260297540734744e-05,
"loss": 1.2366,
"step": 1095
},
{
"epoch": 0.2115181232573791,
"grad_norm": 1.0058884620666504,
"learning_rate": 2.8245116891002935e-05,
"loss": 1.192,
"step": 1100
},
{
"epoch": 0.21247956927218536,
"grad_norm": 1.0079177618026733,
"learning_rate": 2.8229936241271125e-05,
"loss": 1.2698,
"step": 1105
},
{
"epoch": 0.21344101528699164,
"grad_norm": 1.0556343793869019,
"learning_rate": 2.8214755591539316e-05,
"loss": 1.2477,
"step": 1110
},
{
"epoch": 0.2144024613017979,
"grad_norm": 0.9617932438850403,
"learning_rate": 2.819957494180751e-05,
"loss": 1.2387,
"step": 1115
},
{
"epoch": 0.21536390731660418,
"grad_norm": 0.9451227188110352,
"learning_rate": 2.81843942920757e-05,
"loss": 1.276,
"step": 1120
},
{
"epoch": 0.21632535333141045,
"grad_norm": 0.9511146545410156,
"learning_rate": 2.8169213642343892e-05,
"loss": 1.2211,
"step": 1125
},
{
"epoch": 0.2172867993462167,
"grad_norm": 0.9459360241889954,
"learning_rate": 2.8154032992612082e-05,
"loss": 1.1895,
"step": 1130
},
{
"epoch": 0.21824824536102297,
"grad_norm": 0.9601720571517944,
"learning_rate": 2.8138852342880273e-05,
"loss": 1.2573,
"step": 1135
},
{
"epoch": 0.21920969137582924,
"grad_norm": 0.9400343894958496,
"learning_rate": 2.8123671693148467e-05,
"loss": 1.2944,
"step": 1140
},
{
"epoch": 0.2201711373906355,
"grad_norm": 1.0376919507980347,
"learning_rate": 2.8108491043416658e-05,
"loss": 1.2634,
"step": 1145
},
{
"epoch": 0.22113258340544178,
"grad_norm": 0.9042131304740906,
"learning_rate": 2.809331039368485e-05,
"loss": 1.2978,
"step": 1150
},
{
"epoch": 0.22209402942024806,
"grad_norm": 0.8955277800559998,
"learning_rate": 2.807812974395304e-05,
"loss": 1.314,
"step": 1155
},
{
"epoch": 0.22305547543505433,
"grad_norm": 0.9650217890739441,
"learning_rate": 2.806294909422123e-05,
"loss": 1.3183,
"step": 1160
},
{
"epoch": 0.2240169214498606,
"grad_norm": 0.9972891211509705,
"learning_rate": 2.8047768444489425e-05,
"loss": 1.2108,
"step": 1165
},
{
"epoch": 0.22497836746466685,
"grad_norm": 0.841851532459259,
"learning_rate": 2.8032587794757615e-05,
"loss": 1.2214,
"step": 1170
},
{
"epoch": 0.22593981347947312,
"grad_norm": 1.0023276805877686,
"learning_rate": 2.8017407145025806e-05,
"loss": 1.3031,
"step": 1175
},
{
"epoch": 0.2269012594942794,
"grad_norm": 0.9950117468833923,
"learning_rate": 2.8002226495293997e-05,
"loss": 1.2046,
"step": 1180
},
{
"epoch": 0.22786270550908566,
"grad_norm": 0.9552078247070312,
"learning_rate": 2.7987045845562188e-05,
"loss": 1.2556,
"step": 1185
},
{
"epoch": 0.22882415152389193,
"grad_norm": 0.9237502813339233,
"learning_rate": 2.7971865195830382e-05,
"loss": 1.3269,
"step": 1190
},
{
"epoch": 0.2297855975386982,
"grad_norm": 0.8797445893287659,
"learning_rate": 2.7956684546098576e-05,
"loss": 1.2626,
"step": 1195
},
{
"epoch": 0.23074704355350448,
"grad_norm": 1.0588504076004028,
"learning_rate": 2.7941503896366767e-05,
"loss": 1.2855,
"step": 1200
},
{
"epoch": 0.23074704355350448,
"eval_loss": 1.2411783933639526,
"eval_runtime": 1809.2447,
"eval_samples_per_second": 11.498,
"eval_steps_per_second": 2.875,
"step": 1200
}
],
"logging_steps": 5,
"max_steps": 10402,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 300,
"stateful_callbacks": {
"EarlyStoppingCallback": [
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"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": 7.135052072490493e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}