test_sft31 / last-checkpoint /trainer_state.json
Ba2han's picture
Training in progress, step 1384, checkpoint
521b38e verified
Raw
History Blame Contribute Delete
122 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.18005887040379892,
"eval_steps": 500,
"global_step": 1384,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002602006797742759,
"grad_norm": 0.521027684211731,
"learning_rate": 4.3352601156069365e-06,
"loss": 3.296633720397949,
"step": 2
},
{
"epoch": 0.0005204013595485518,
"grad_norm": 0.529604434967041,
"learning_rate": 1.3005780346820809e-05,
"loss": 3.42961049079895,
"step": 4
},
{
"epoch": 0.0007806020393228277,
"grad_norm": 0.4618305563926697,
"learning_rate": 2.167630057803468e-05,
"loss": 3.335054397583008,
"step": 6
},
{
"epoch": 0.0010408027190971037,
"grad_norm": 0.4985038638114929,
"learning_rate": 3.0346820809248556e-05,
"loss": 3.381575584411621,
"step": 8
},
{
"epoch": 0.0013010033988713795,
"grad_norm": 0.4767224192619324,
"learning_rate": 3.901734104046243e-05,
"loss": 3.4511144161224365,
"step": 10
},
{
"epoch": 0.0015612040786456554,
"grad_norm": 0.4434731900691986,
"learning_rate": 4.76878612716763e-05,
"loss": 3.3980913162231445,
"step": 12
},
{
"epoch": 0.0018214047584199314,
"grad_norm": 0.5170185565948486,
"learning_rate": 5.6358381502890176e-05,
"loss": 3.4509780406951904,
"step": 14
},
{
"epoch": 0.0020816054381942073,
"grad_norm": 0.49620524048805237,
"learning_rate": 6.502890173410404e-05,
"loss": 3.425800323486328,
"step": 16
},
{
"epoch": 0.002341806117968483,
"grad_norm": 0.3991275429725647,
"learning_rate": 7.369942196531793e-05,
"loss": 3.3160603046417236,
"step": 18
},
{
"epoch": 0.002602006797742759,
"grad_norm": 0.4144597053527832,
"learning_rate": 8.23699421965318e-05,
"loss": 3.3297767639160156,
"step": 20
},
{
"epoch": 0.002862207477517035,
"grad_norm": 0.4789470434188843,
"learning_rate": 9.104046242774567e-05,
"loss": 3.307015895843506,
"step": 22
},
{
"epoch": 0.0031224081572913107,
"grad_norm": 0.40658894181251526,
"learning_rate": 9.971098265895953e-05,
"loss": 3.4203081130981445,
"step": 24
},
{
"epoch": 0.003382608837065587,
"grad_norm": 0.375639408826828,
"learning_rate": 0.00010838150289017342,
"loss": 3.364102840423584,
"step": 26
},
{
"epoch": 0.003642809516839863,
"grad_norm": 0.3961547315120697,
"learning_rate": 0.0001170520231213873,
"loss": 3.291555166244507,
"step": 28
},
{
"epoch": 0.0039030101966141388,
"grad_norm": 0.4585370719432831,
"learning_rate": 0.00012572254335260115,
"loss": 3.4974162578582764,
"step": 30
},
{
"epoch": 0.004163210876388415,
"grad_norm": 0.43081340193748474,
"learning_rate": 0.00013439306358381504,
"loss": 3.403614044189453,
"step": 32
},
{
"epoch": 0.00442341155616269,
"grad_norm": 0.37973612546920776,
"learning_rate": 0.0001430635838150289,
"loss": 3.296022415161133,
"step": 34
},
{
"epoch": 0.004683612235936966,
"grad_norm": 0.3765884041786194,
"learning_rate": 0.00015173410404624278,
"loss": 3.405014991760254,
"step": 36
},
{
"epoch": 0.004943812915711243,
"grad_norm": 0.38402050733566284,
"learning_rate": 0.00016040462427745666,
"loss": 3.428579092025757,
"step": 38
},
{
"epoch": 0.005204013595485518,
"grad_norm": 0.3614136576652527,
"learning_rate": 0.00016907514450867052,
"loss": 3.3713903427124023,
"step": 40
},
{
"epoch": 0.005464214275259794,
"grad_norm": 0.41867804527282715,
"learning_rate": 0.00017774566473988438,
"loss": 3.461496353149414,
"step": 42
},
{
"epoch": 0.00572441495503407,
"grad_norm": 0.33046382665634155,
"learning_rate": 0.00018641618497109826,
"loss": 3.3089582920074463,
"step": 44
},
{
"epoch": 0.005984615634808346,
"grad_norm": 0.3859819769859314,
"learning_rate": 0.00019508670520231212,
"loss": 3.388202667236328,
"step": 46
},
{
"epoch": 0.0062448163145826215,
"grad_norm": 0.3520834147930145,
"learning_rate": 0.000203757225433526,
"loss": 3.272517681121826,
"step": 48
},
{
"epoch": 0.006505016994356898,
"grad_norm": 0.3423490822315216,
"learning_rate": 0.00021242774566473992,
"loss": 3.260913848876953,
"step": 50
},
{
"epoch": 0.006765217674131174,
"grad_norm": 0.35582831501960754,
"learning_rate": 0.00022109826589595378,
"loss": 3.4315755367279053,
"step": 52
},
{
"epoch": 0.0070254183539054495,
"grad_norm": 0.3502774238586426,
"learning_rate": 0.00022976878612716763,
"loss": 3.317216634750366,
"step": 54
},
{
"epoch": 0.007285619033679726,
"grad_norm": 0.3774696886539459,
"learning_rate": 0.00023843930635838152,
"loss": 3.4877872467041016,
"step": 56
},
{
"epoch": 0.007545819713454001,
"grad_norm": 0.3579508662223816,
"learning_rate": 0.0002471098265895954,
"loss": 3.3067917823791504,
"step": 58
},
{
"epoch": 0.0078060203932282775,
"grad_norm": 0.3545570969581604,
"learning_rate": 0.00025578034682080926,
"loss": 3.3747382164001465,
"step": 60
},
{
"epoch": 0.008066221073002554,
"grad_norm": 0.4066823124885559,
"learning_rate": 0.0002644508670520231,
"loss": 3.37534761428833,
"step": 62
},
{
"epoch": 0.00832642175277683,
"grad_norm": 0.3766571283340454,
"learning_rate": 0.000273121387283237,
"loss": 3.3921797275543213,
"step": 64
},
{
"epoch": 0.008586622432551105,
"grad_norm": 0.3474276661872864,
"learning_rate": 0.00028179190751445083,
"loss": 3.3073554039001465,
"step": 66
},
{
"epoch": 0.00884682311232538,
"grad_norm": 0.36787399649620056,
"learning_rate": 0.00029046242774566475,
"loss": 3.465327262878418,
"step": 68
},
{
"epoch": 0.009107023792099657,
"grad_norm": 0.3730259835720062,
"learning_rate": 0.00029913294797687866,
"loss": 3.3730597496032715,
"step": 70
},
{
"epoch": 0.009367224471873933,
"grad_norm": 0.3592052459716797,
"learning_rate": 0.0003078034682080925,
"loss": 3.369673013687134,
"step": 72
},
{
"epoch": 0.009627425151648208,
"grad_norm": 0.4704977869987488,
"learning_rate": 0.0003164739884393064,
"loss": 3.4094486236572266,
"step": 74
},
{
"epoch": 0.009887625831422485,
"grad_norm": 0.29093804955482483,
"learning_rate": 0.00032514450867052023,
"loss": 3.298234462738037,
"step": 76
},
{
"epoch": 0.01014782651119676,
"grad_norm": 0.30112385749816895,
"learning_rate": 0.0003338150289017341,
"loss": 3.164336681365967,
"step": 78
},
{
"epoch": 0.010408027190971036,
"grad_norm": 0.25602561235427856,
"learning_rate": 0.000342485549132948,
"loss": 3.2490344047546387,
"step": 80
},
{
"epoch": 0.010668227870745312,
"grad_norm": 0.27550992369651794,
"learning_rate": 0.00035115606936416186,
"loss": 3.2643542289733887,
"step": 82
},
{
"epoch": 0.010928428550519589,
"grad_norm": 0.3303152024745941,
"learning_rate": 0.0003598265895953757,
"loss": 3.289999485015869,
"step": 84
},
{
"epoch": 0.011188629230293864,
"grad_norm": 0.31836414337158203,
"learning_rate": 0.0003684971098265896,
"loss": 3.3413586616516113,
"step": 86
},
{
"epoch": 0.01144882991006814,
"grad_norm": 0.33070388436317444,
"learning_rate": 0.0003771676300578035,
"loss": 3.32738995552063,
"step": 88
},
{
"epoch": 0.011709030589842417,
"grad_norm": 0.30830368399620056,
"learning_rate": 0.00038583815028901734,
"loss": 3.349341869354248,
"step": 90
},
{
"epoch": 0.011969231269616692,
"grad_norm": 0.30990368127822876,
"learning_rate": 0.00039450867052023126,
"loss": 3.316821575164795,
"step": 92
},
{
"epoch": 0.012229431949390968,
"grad_norm": 0.3708277940750122,
"learning_rate": 0.0004031791907514451,
"loss": 3.3271565437316895,
"step": 94
},
{
"epoch": 0.012489632629165243,
"grad_norm": 0.28574034571647644,
"learning_rate": 0.00041184971098265897,
"loss": 3.293184280395508,
"step": 96
},
{
"epoch": 0.01274983330893952,
"grad_norm": 0.2940095365047455,
"learning_rate": 0.00042052023121387283,
"loss": 3.35920786857605,
"step": 98
},
{
"epoch": 0.013010033988713796,
"grad_norm": 0.30244606733322144,
"learning_rate": 0.0004291907514450867,
"loss": 3.350550889968872,
"step": 100
},
{
"epoch": 0.013270234668488071,
"grad_norm": 0.35780057311058044,
"learning_rate": 0.0004378612716763006,
"loss": 3.3532772064208984,
"step": 102
},
{
"epoch": 0.013530435348262348,
"grad_norm": 0.2902573347091675,
"learning_rate": 0.00044653179190751446,
"loss": 3.2327017784118652,
"step": 104
},
{
"epoch": 0.013790636028036624,
"grad_norm": 0.28510838747024536,
"learning_rate": 0.0004552023121387283,
"loss": 3.253952741622925,
"step": 106
},
{
"epoch": 0.014050836707810899,
"grad_norm": 0.31303301453590393,
"learning_rate": 0.00046387283236994217,
"loss": 3.320916175842285,
"step": 108
},
{
"epoch": 0.014311037387585174,
"grad_norm": 0.2602003812789917,
"learning_rate": 0.00047254335260115603,
"loss": 3.1783814430236816,
"step": 110
},
{
"epoch": 0.014571238067359452,
"grad_norm": 0.29427075386047363,
"learning_rate": 0.00048121387283236994,
"loss": 3.199770450592041,
"step": 112
},
{
"epoch": 0.014831438747133727,
"grad_norm": 0.2756480574607849,
"learning_rate": 0.0004898843930635837,
"loss": 3.276580333709717,
"step": 114
},
{
"epoch": 0.015091639426908002,
"grad_norm": 0.2712593674659729,
"learning_rate": 0.0004985549132947977,
"loss": 3.2717957496643066,
"step": 116
},
{
"epoch": 0.015351840106682278,
"grad_norm": 0.3133692443370819,
"learning_rate": 0.0005072254335260116,
"loss": 3.2784416675567627,
"step": 118
},
{
"epoch": 0.015612040786456555,
"grad_norm": 0.27181175351142883,
"learning_rate": 0.0005158959537572255,
"loss": 3.2424092292785645,
"step": 120
},
{
"epoch": 0.01587224146623083,
"grad_norm": 0.26740762591362,
"learning_rate": 0.0005245664739884394,
"loss": 3.268554210662842,
"step": 122
},
{
"epoch": 0.016132442146005108,
"grad_norm": 0.32215583324432373,
"learning_rate": 0.0005332369942196532,
"loss": 3.3126766681671143,
"step": 124
},
{
"epoch": 0.01639264282577938,
"grad_norm": 0.28776511549949646,
"learning_rate": 0.0005419075144508671,
"loss": 3.120931386947632,
"step": 126
},
{
"epoch": 0.01665284350555366,
"grad_norm": 0.25681668519973755,
"learning_rate": 0.0005505780346820809,
"loss": 3.2850513458251953,
"step": 128
},
{
"epoch": 0.016913044185327936,
"grad_norm": 0.2619856297969818,
"learning_rate": 0.0005592485549132948,
"loss": 3.2361326217651367,
"step": 130
},
{
"epoch": 0.01717324486510221,
"grad_norm": 0.27186161279678345,
"learning_rate": 0.0005679190751445087,
"loss": 3.254220485687256,
"step": 132
},
{
"epoch": 0.017433445544876486,
"grad_norm": 0.30524536967277527,
"learning_rate": 0.0005765895953757225,
"loss": 3.230988025665283,
"step": 134
},
{
"epoch": 0.01769364622465076,
"grad_norm": 0.274209588766098,
"learning_rate": 0.0005852601156069364,
"loss": 3.2885119915008545,
"step": 136
},
{
"epoch": 0.017953846904425037,
"grad_norm": 0.2683689594268799,
"learning_rate": 0.0005939306358381503,
"loss": 3.2494893074035645,
"step": 138
},
{
"epoch": 0.018214047584199314,
"grad_norm": 0.2528843879699707,
"learning_rate": 0.0006026011560693642,
"loss": 3.2656893730163574,
"step": 140
},
{
"epoch": 0.018474248263973588,
"grad_norm": 0.2937518358230591,
"learning_rate": 0.0006112716763005781,
"loss": 3.2583231925964355,
"step": 142
},
{
"epoch": 0.018734448943747865,
"grad_norm": 0.25858423113822937,
"learning_rate": 0.0006199421965317919,
"loss": 3.245497703552246,
"step": 144
},
{
"epoch": 0.018994649623522143,
"grad_norm": 0.2764334976673126,
"learning_rate": 0.0006286127167630058,
"loss": 3.2706778049468994,
"step": 146
},
{
"epoch": 0.019254850303296416,
"grad_norm": 0.2558375895023346,
"learning_rate": 0.0006372832369942196,
"loss": 3.2925539016723633,
"step": 148
},
{
"epoch": 0.019515050983070693,
"grad_norm": 0.26449859142303467,
"learning_rate": 0.0006459537572254335,
"loss": 3.1974246501922607,
"step": 150
},
{
"epoch": 0.01977525166284497,
"grad_norm": 0.2643563449382782,
"learning_rate": 0.0006546242774566474,
"loss": 3.2013633251190186,
"step": 152
},
{
"epoch": 0.020035452342619244,
"grad_norm": 0.25999486446380615,
"learning_rate": 0.0006632947976878612,
"loss": 3.2912192344665527,
"step": 154
},
{
"epoch": 0.02029565302239352,
"grad_norm": 0.23230506479740143,
"learning_rate": 0.0006719653179190752,
"loss": 3.2590725421905518,
"step": 156
},
{
"epoch": 0.0205558537021678,
"grad_norm": 0.25524914264678955,
"learning_rate": 0.000680635838150289,
"loss": 3.253737449645996,
"step": 158
},
{
"epoch": 0.020816054381942072,
"grad_norm": 0.27695125341415405,
"learning_rate": 0.000689306358381503,
"loss": 3.1709330081939697,
"step": 160
},
{
"epoch": 0.02107625506171635,
"grad_norm": 0.2362748086452484,
"learning_rate": 0.0006979768786127168,
"loss": 3.2747771739959717,
"step": 162
},
{
"epoch": 0.021336455741490623,
"grad_norm": 0.23591399192810059,
"learning_rate": 0.0007066473988439307,
"loss": 3.18483304977417,
"step": 164
},
{
"epoch": 0.0215966564212649,
"grad_norm": 0.2665315866470337,
"learning_rate": 0.0007153179190751446,
"loss": 3.208442211151123,
"step": 166
},
{
"epoch": 0.021856857101039177,
"grad_norm": 0.25159355998039246,
"learning_rate": 0.0007239884393063584,
"loss": 3.2677812576293945,
"step": 168
},
{
"epoch": 0.02211705778081345,
"grad_norm": 0.2371087670326233,
"learning_rate": 0.0007326589595375723,
"loss": 3.1868972778320312,
"step": 170
},
{
"epoch": 0.022377258460587728,
"grad_norm": 0.3146700859069824,
"learning_rate": 0.0007413294797687861,
"loss": 3.123814582824707,
"step": 172
},
{
"epoch": 0.022637459140362005,
"grad_norm": 0.2549314796924591,
"learning_rate": 0.00075,
"loss": 3.2187676429748535,
"step": 174
},
{
"epoch": 0.02289765982013628,
"grad_norm": 0.2223459631204605,
"learning_rate": 0.0007586705202312139,
"loss": 3.2054901123046875,
"step": 176
},
{
"epoch": 0.023157860499910556,
"grad_norm": 0.2565750181674957,
"learning_rate": 0.0007673410404624277,
"loss": 3.207458972930908,
"step": 178
},
{
"epoch": 0.023418061179684833,
"grad_norm": 0.2476375699043274,
"learning_rate": 0.0007760115606936418,
"loss": 3.1795835494995117,
"step": 180
},
{
"epoch": 0.023678261859459107,
"grad_norm": 0.23969122767448425,
"learning_rate": 0.0007846820809248554,
"loss": 3.187877655029297,
"step": 182
},
{
"epoch": 0.023938462539233384,
"grad_norm": 0.23113180696964264,
"learning_rate": 0.0007933526011560695,
"loss": 3.1212964057922363,
"step": 184
},
{
"epoch": 0.024198663219007658,
"grad_norm": 0.21042431890964508,
"learning_rate": 0.0008020231213872833,
"loss": 3.155189275741577,
"step": 186
},
{
"epoch": 0.024458863898781935,
"grad_norm": 0.197580486536026,
"learning_rate": 0.0008106936416184972,
"loss": 3.1081671714782715,
"step": 188
},
{
"epoch": 0.024719064578556212,
"grad_norm": 0.21269115805625916,
"learning_rate": 0.000819364161849711,
"loss": 3.1772332191467285,
"step": 190
},
{
"epoch": 0.024979265258330486,
"grad_norm": 0.2827216386795044,
"learning_rate": 0.0008280346820809249,
"loss": 3.035491466522217,
"step": 192
},
{
"epoch": 0.025239465938104763,
"grad_norm": 0.2425803542137146,
"learning_rate": 0.0008367052023121387,
"loss": 3.096795082092285,
"step": 194
},
{
"epoch": 0.02549966661787904,
"grad_norm": 0.20268665254116058,
"learning_rate": 0.0008453757225433526,
"loss": 3.10842227935791,
"step": 196
},
{
"epoch": 0.025759867297653314,
"grad_norm": 0.24778003990650177,
"learning_rate": 0.0008540462427745664,
"loss": 3.1295409202575684,
"step": 198
},
{
"epoch": 0.02602006797742759,
"grad_norm": 0.2006409615278244,
"learning_rate": 0.0008627167630057804,
"loss": 3.1514291763305664,
"step": 200
},
{
"epoch": 0.02628026865720187,
"grad_norm": 0.19448356330394745,
"learning_rate": 0.0008713872832369941,
"loss": 3.1217727661132812,
"step": 202
},
{
"epoch": 0.026540469336976142,
"grad_norm": 0.17982026934623718,
"learning_rate": 0.0008800578034682082,
"loss": 3.097832679748535,
"step": 204
},
{
"epoch": 0.02680067001675042,
"grad_norm": 0.2240755259990692,
"learning_rate": 0.000888728323699422,
"loss": 3.154944896697998,
"step": 206
},
{
"epoch": 0.027060870696524696,
"grad_norm": 0.19914984703063965,
"learning_rate": 0.0008973988439306359,
"loss": 3.128056049346924,
"step": 208
},
{
"epoch": 0.02732107137629897,
"grad_norm": 0.18972548842430115,
"learning_rate": 0.0009060693641618497,
"loss": 3.1953482627868652,
"step": 210
},
{
"epoch": 0.027581272056073247,
"grad_norm": 0.21920305490493774,
"learning_rate": 0.0009147398843930636,
"loss": 3.1071338653564453,
"step": 212
},
{
"epoch": 0.02784147273584752,
"grad_norm": 0.21467278897762299,
"learning_rate": 0.0009234104046242776,
"loss": 3.10892391204834,
"step": 214
},
{
"epoch": 0.028101673415621798,
"grad_norm": 0.19529728591442108,
"learning_rate": 0.0009320809248554913,
"loss": 3.0915136337280273,
"step": 216
},
{
"epoch": 0.028361874095396075,
"grad_norm": 0.2508365213871002,
"learning_rate": 0.0009407514450867053,
"loss": 3.0391974449157715,
"step": 218
},
{
"epoch": 0.02862207477517035,
"grad_norm": 0.18604034185409546,
"learning_rate": 0.0009494219653179191,
"loss": 3.029890537261963,
"step": 220
},
{
"epoch": 0.028882275454944626,
"grad_norm": 0.18298658728599548,
"learning_rate": 0.000958092485549133,
"loss": 3.0440821647644043,
"step": 222
},
{
"epoch": 0.029142476134718903,
"grad_norm": 0.19031928479671478,
"learning_rate": 0.0009667630057803468,
"loss": 3.0324721336364746,
"step": 224
},
{
"epoch": 0.029402676814493177,
"grad_norm": 0.2045256644487381,
"learning_rate": 0.0009754335260115607,
"loss": 3.027928352355957,
"step": 226
},
{
"epoch": 0.029662877494267454,
"grad_norm": 0.18090291321277618,
"learning_rate": 0.0009841040462427746,
"loss": 2.9796810150146484,
"step": 228
},
{
"epoch": 0.02992307817404173,
"grad_norm": 0.20732243359088898,
"learning_rate": 0.0009927745664739885,
"loss": 3.092945098876953,
"step": 230
},
{
"epoch": 0.030183278853816005,
"grad_norm": 0.19675296545028687,
"learning_rate": 0.0010014450867052024,
"loss": 3.1028237342834473,
"step": 232
},
{
"epoch": 0.030443479533590282,
"grad_norm": 0.2103000432252884,
"learning_rate": 0.0010101156069364163,
"loss": 3.0760812759399414,
"step": 234
},
{
"epoch": 0.030703680213364556,
"grad_norm": 0.18039967119693756,
"learning_rate": 0.00101878612716763,
"loss": 3.0807101726531982,
"step": 236
},
{
"epoch": 0.030963880893138833,
"grad_norm": 0.18566253781318665,
"learning_rate": 0.001027456647398844,
"loss": 3.0250244140625,
"step": 238
},
{
"epoch": 0.03122408157291311,
"grad_norm": 0.2228381484746933,
"learning_rate": 0.0010361271676300578,
"loss": 2.9628562927246094,
"step": 240
},
{
"epoch": 0.03148428225268739,
"grad_norm": 0.18055233359336853,
"learning_rate": 0.0010447976878612717,
"loss": 2.9055001735687256,
"step": 242
},
{
"epoch": 0.03174448293246166,
"grad_norm": 0.19681446254253387,
"learning_rate": 0.0010534682080924854,
"loss": 2.9425225257873535,
"step": 244
},
{
"epoch": 0.032004683612235935,
"grad_norm": 0.20274615287780762,
"learning_rate": 0.0010621387283236995,
"loss": 3.03011417388916,
"step": 246
},
{
"epoch": 0.032264884292010215,
"grad_norm": 0.1779792457818985,
"learning_rate": 0.0010708092485549132,
"loss": 3.05258846282959,
"step": 248
},
{
"epoch": 0.03252508497178449,
"grad_norm": 0.21098701655864716,
"learning_rate": 0.0010794797687861271,
"loss": 3.0425450801849365,
"step": 250
},
{
"epoch": 0.03278528565155876,
"grad_norm": 0.1870265156030655,
"learning_rate": 0.001088150289017341,
"loss": 2.993565082550049,
"step": 252
},
{
"epoch": 0.03304548633133304,
"grad_norm": 0.19540223479270935,
"learning_rate": 0.001096820809248555,
"loss": 2.9134411811828613,
"step": 254
},
{
"epoch": 0.03330568701110732,
"grad_norm": 0.21431873738765717,
"learning_rate": 0.0011054913294797689,
"loss": 2.93609619140625,
"step": 256
},
{
"epoch": 0.03356588769088159,
"grad_norm": 0.207144632935524,
"learning_rate": 0.0011141618497109826,
"loss": 2.9225587844848633,
"step": 258
},
{
"epoch": 0.03382608837065587,
"grad_norm": 0.2121778130531311,
"learning_rate": 0.0011228323699421967,
"loss": 3.0123167037963867,
"step": 260
},
{
"epoch": 0.034086289050430145,
"grad_norm": 0.18439042568206787,
"learning_rate": 0.0011315028901734104,
"loss": 2.919414520263672,
"step": 262
},
{
"epoch": 0.03434648973020442,
"grad_norm": 0.17453093826770782,
"learning_rate": 0.0011401734104046243,
"loss": 2.9711110591888428,
"step": 264
},
{
"epoch": 0.0346066904099787,
"grad_norm": 0.2020498514175415,
"learning_rate": 0.0011488439306358382,
"loss": 2.9616055488586426,
"step": 266
},
{
"epoch": 0.03486689108975297,
"grad_norm": 0.18789063394069672,
"learning_rate": 0.0011575144508670521,
"loss": 2.9807963371276855,
"step": 268
},
{
"epoch": 0.03512709176952725,
"grad_norm": 0.1720653921365738,
"learning_rate": 0.0011661849710982658,
"loss": 2.909268617630005,
"step": 270
},
{
"epoch": 0.03538729244930152,
"grad_norm": 0.22420282661914825,
"learning_rate": 0.0011748554913294797,
"loss": 2.9295620918273926,
"step": 272
},
{
"epoch": 0.0356474931290758,
"grad_norm": 0.1796054095029831,
"learning_rate": 0.0011835260115606937,
"loss": 2.838535785675049,
"step": 274
},
{
"epoch": 0.035907693808850075,
"grad_norm": 0.2178080528974533,
"learning_rate": 0.0011921965317919076,
"loss": 2.8897058963775635,
"step": 276
},
{
"epoch": 0.03616789448862435,
"grad_norm": 0.21806925535202026,
"learning_rate": 0.0012008670520231213,
"loss": 2.8932857513427734,
"step": 278
},
{
"epoch": 0.03642809516839863,
"grad_norm": 0.18577463924884796,
"learning_rate": 0.0012095375722543354,
"loss": 2.916924476623535,
"step": 280
},
{
"epoch": 0.0366882958481729,
"grad_norm": 0.2138700932264328,
"learning_rate": 0.001218208092485549,
"loss": 2.985546827316284,
"step": 282
},
{
"epoch": 0.036948496527947176,
"grad_norm": 0.22238318622112274,
"learning_rate": 0.001226878612716763,
"loss": 2.9146595001220703,
"step": 284
},
{
"epoch": 0.03720869720772146,
"grad_norm": 0.21025969088077545,
"learning_rate": 0.001235549132947977,
"loss": 2.892270088195801,
"step": 286
},
{
"epoch": 0.03746889788749573,
"grad_norm": 0.23840492963790894,
"learning_rate": 0.0012442196531791908,
"loss": 2.8415307998657227,
"step": 288
},
{
"epoch": 0.037729098567270004,
"grad_norm": 0.20167258381843567,
"learning_rate": 0.0012528901734104047,
"loss": 2.9031810760498047,
"step": 290
},
{
"epoch": 0.037989299247044285,
"grad_norm": 0.24544967710971832,
"learning_rate": 0.0012615606936416184,
"loss": 2.934631824493408,
"step": 292
},
{
"epoch": 0.03824949992681856,
"grad_norm": 0.3102674186229706,
"learning_rate": 0.0012702312138728326,
"loss": 2.924362897872925,
"step": 294
},
{
"epoch": 0.03850970060659283,
"grad_norm": 0.17447885870933533,
"learning_rate": 0.0012789017341040463,
"loss": 2.841254711151123,
"step": 296
},
{
"epoch": 0.03876990128636711,
"grad_norm": 0.26619958877563477,
"learning_rate": 0.0012875722543352602,
"loss": 2.873321056365967,
"step": 298
},
{
"epoch": 0.03903010196614139,
"grad_norm": 0.27165448665618896,
"learning_rate": 0.001296242774566474,
"loss": 2.942399501800537,
"step": 300
},
{
"epoch": 0.03929030264591566,
"grad_norm": 0.17484025657176971,
"learning_rate": 0.001304913294797688,
"loss": 2.8616087436676025,
"step": 302
},
{
"epoch": 0.03955050332568994,
"grad_norm": 0.21328718960285187,
"learning_rate": 0.0013135838150289017,
"loss": 2.7787179946899414,
"step": 304
},
{
"epoch": 0.039810704005464215,
"grad_norm": 0.21324102580547333,
"learning_rate": 0.0013222543352601156,
"loss": 2.8903517723083496,
"step": 306
},
{
"epoch": 0.04007090468523849,
"grad_norm": 0.21711313724517822,
"learning_rate": 0.0013309248554913295,
"loss": 2.7644217014312744,
"step": 308
},
{
"epoch": 0.04033110536501277,
"grad_norm": 0.2328975945711136,
"learning_rate": 0.0013395953757225434,
"loss": 2.868736505508423,
"step": 310
},
{
"epoch": 0.04059130604478704,
"grad_norm": 0.246817484498024,
"learning_rate": 0.0013482658959537571,
"loss": 2.910038948059082,
"step": 312
},
{
"epoch": 0.040851506724561316,
"grad_norm": 0.1926267296075821,
"learning_rate": 0.0013569364161849712,
"loss": 2.795515537261963,
"step": 314
},
{
"epoch": 0.0411117074043356,
"grad_norm": 0.19206106662750244,
"learning_rate": 0.001365606936416185,
"loss": 2.8028244972229004,
"step": 316
},
{
"epoch": 0.04137190808410987,
"grad_norm": 0.17958422005176544,
"learning_rate": 0.0013742774566473989,
"loss": 2.8207240104675293,
"step": 318
},
{
"epoch": 0.041632108763884144,
"grad_norm": 0.30933892726898193,
"learning_rate": 0.0013829479768786128,
"loss": 2.8685462474823,
"step": 320
},
{
"epoch": 0.04189230944365842,
"grad_norm": 0.20292924344539642,
"learning_rate": 0.0013916184971098267,
"loss": 2.8181519508361816,
"step": 322
},
{
"epoch": 0.0421525101234327,
"grad_norm": 0.27987852692604065,
"learning_rate": 0.0014002890173410404,
"loss": 2.791168689727783,
"step": 324
},
{
"epoch": 0.04241271080320697,
"grad_norm": 0.26813364028930664,
"learning_rate": 0.0014089595375722543,
"loss": 2.758394718170166,
"step": 326
},
{
"epoch": 0.042672911482981246,
"grad_norm": 0.2212570607662201,
"learning_rate": 0.0014176300578034684,
"loss": 2.833681583404541,
"step": 328
},
{
"epoch": 0.04293311216275553,
"grad_norm": 0.19662605226039886,
"learning_rate": 0.001426300578034682,
"loss": 2.8058218955993652,
"step": 330
},
{
"epoch": 0.0431933128425298,
"grad_norm": 0.29693248867988586,
"learning_rate": 0.001434971098265896,
"loss": 2.775289535522461,
"step": 332
},
{
"epoch": 0.043453513522304074,
"grad_norm": 0.19609500467777252,
"learning_rate": 0.00144364161849711,
"loss": 2.815795660018921,
"step": 334
},
{
"epoch": 0.043713714202078355,
"grad_norm": 0.21622313559055328,
"learning_rate": 0.0014523121387283238,
"loss": 2.8070521354675293,
"step": 336
},
{
"epoch": 0.04397391488185263,
"grad_norm": 0.18037623167037964,
"learning_rate": 0.0014609826589595375,
"loss": 2.72457218170166,
"step": 338
},
{
"epoch": 0.0442341155616269,
"grad_norm": 0.19943048059940338,
"learning_rate": 0.0014696531791907514,
"loss": 2.7480547428131104,
"step": 340
},
{
"epoch": 0.04449431624140118,
"grad_norm": 0.16557621955871582,
"learning_rate": 0.0014783236994219654,
"loss": 2.745342493057251,
"step": 342
},
{
"epoch": 0.044754516921175456,
"grad_norm": 0.17805889248847961,
"learning_rate": 0.0014869942196531793,
"loss": 2.753793239593506,
"step": 344
},
{
"epoch": 0.04501471760094973,
"grad_norm": 0.23548759520053864,
"learning_rate": 0.001495664739884393,
"loss": 2.8414790630340576,
"step": 346
},
{
"epoch": 0.04527491828072401,
"grad_norm": 0.1648837774991989,
"learning_rate": 0.0015,
"loss": 2.7620575428009033,
"step": 348
},
{
"epoch": 0.045535118960498285,
"grad_norm": 0.16259492933750153,
"learning_rate": 0.0015,
"loss": 2.7154746055603027,
"step": 350
},
{
"epoch": 0.04579531964027256,
"grad_norm": 0.17988084256649017,
"learning_rate": 0.0015,
"loss": 2.700965404510498,
"step": 352
},
{
"epoch": 0.04605552032004684,
"grad_norm": 0.16477294266223907,
"learning_rate": 0.0015,
"loss": 2.755967140197754,
"step": 354
},
{
"epoch": 0.04631572099982111,
"grad_norm": 0.21754054725170135,
"learning_rate": 0.0015,
"loss": 2.6964268684387207,
"step": 356
},
{
"epoch": 0.046575921679595386,
"grad_norm": 0.1506672352552414,
"learning_rate": 0.0015,
"loss": 2.794830322265625,
"step": 358
},
{
"epoch": 0.04683612235936967,
"grad_norm": 0.1614987701177597,
"learning_rate": 0.0015,
"loss": 2.6898601055145264,
"step": 360
},
{
"epoch": 0.04709632303914394,
"grad_norm": 0.18936215341091156,
"learning_rate": 0.0015,
"loss": 2.647334575653076,
"step": 362
},
{
"epoch": 0.047356523718918214,
"grad_norm": 0.20592817664146423,
"learning_rate": 0.0015,
"loss": 2.7215371131896973,
"step": 364
},
{
"epoch": 0.047616724398692495,
"grad_norm": 0.1782323271036148,
"learning_rate": 0.0015,
"loss": 2.6734256744384766,
"step": 366
},
{
"epoch": 0.04787692507846677,
"grad_norm": 0.15602196753025055,
"learning_rate": 0.0015,
"loss": 2.667567729949951,
"step": 368
},
{
"epoch": 0.04813712575824104,
"grad_norm": 0.14590057730674744,
"learning_rate": 0.0015,
"loss": 2.7369422912597656,
"step": 370
},
{
"epoch": 0.048397326438015316,
"grad_norm": 0.16776956617832184,
"learning_rate": 0.0015,
"loss": 2.715961217880249,
"step": 372
},
{
"epoch": 0.0486575271177896,
"grad_norm": 0.13588234782218933,
"learning_rate": 0.0015,
"loss": 2.6299777030944824,
"step": 374
},
{
"epoch": 0.04891772779756387,
"grad_norm": 0.19670580327510834,
"learning_rate": 0.0015,
"loss": 2.7056634426116943,
"step": 376
},
{
"epoch": 0.049177928477338144,
"grad_norm": 0.16066035628318787,
"learning_rate": 0.0015,
"loss": 2.6497952938079834,
"step": 378
},
{
"epoch": 0.049438129157112425,
"grad_norm": 0.18578185141086578,
"learning_rate": 0.0015,
"loss": 2.6196389198303223,
"step": 380
},
{
"epoch": 0.0496983298368867,
"grad_norm": 0.1641508936882019,
"learning_rate": 0.0015,
"loss": 2.64473819732666,
"step": 382
},
{
"epoch": 0.04995853051666097,
"grad_norm": 0.15967334806919098,
"learning_rate": 0.0015,
"loss": 2.610323905944824,
"step": 384
},
{
"epoch": 0.05021873119643525,
"grad_norm": 0.19882506132125854,
"learning_rate": 0.0015,
"loss": 2.580444574356079,
"step": 386
},
{
"epoch": 0.050478931876209526,
"grad_norm": 0.15675006806850433,
"learning_rate": 0.0015,
"loss": 2.666419267654419,
"step": 388
},
{
"epoch": 0.0507391325559838,
"grad_norm": 0.16099196672439575,
"learning_rate": 0.0015,
"loss": 2.681671619415283,
"step": 390
},
{
"epoch": 0.05099933323575808,
"grad_norm": 0.15766847133636475,
"learning_rate": 0.0015,
"loss": 2.6991372108459473,
"step": 392
},
{
"epoch": 0.051259533915532354,
"grad_norm": 0.1549822986125946,
"learning_rate": 0.0015,
"loss": 2.6909019947052,
"step": 394
},
{
"epoch": 0.05151973459530663,
"grad_norm": 0.17178906500339508,
"learning_rate": 0.0015,
"loss": 2.6943092346191406,
"step": 396
},
{
"epoch": 0.05177993527508091,
"grad_norm": 0.15122868120670319,
"learning_rate": 0.0015,
"loss": 2.669128894805908,
"step": 398
},
{
"epoch": 0.05204013595485518,
"grad_norm": 0.13485313951969147,
"learning_rate": 0.0015,
"loss": 2.550992488861084,
"step": 400
},
{
"epoch": 0.052300336634629456,
"grad_norm": 0.13008184731006622,
"learning_rate": 0.0015,
"loss": 2.6252386569976807,
"step": 402
},
{
"epoch": 0.05256053731440374,
"grad_norm": 0.1430431306362152,
"learning_rate": 0.0015,
"loss": 2.6614580154418945,
"step": 404
},
{
"epoch": 0.05282073799417801,
"grad_norm": 0.15184569358825684,
"learning_rate": 0.0015,
"loss": 2.5884804725646973,
"step": 406
},
{
"epoch": 0.053080938673952284,
"grad_norm": 0.15028434991836548,
"learning_rate": 0.0015,
"loss": 2.534207344055176,
"step": 408
},
{
"epoch": 0.053341139353726565,
"grad_norm": 0.1342860609292984,
"learning_rate": 0.0015,
"loss": 2.650566816329956,
"step": 410
},
{
"epoch": 0.05360134003350084,
"grad_norm": 0.14909809827804565,
"learning_rate": 0.0015,
"loss": 2.575770616531372,
"step": 412
},
{
"epoch": 0.05386154071327511,
"grad_norm": 0.1467573493719101,
"learning_rate": 0.0015,
"loss": 2.600891590118408,
"step": 414
},
{
"epoch": 0.05412174139304939,
"grad_norm": 0.14627805352210999,
"learning_rate": 0.0015,
"loss": 2.6327264308929443,
"step": 416
},
{
"epoch": 0.054381942072823666,
"grad_norm": 0.11908523738384247,
"learning_rate": 0.0015,
"loss": 2.6035282611846924,
"step": 418
},
{
"epoch": 0.05464214275259794,
"grad_norm": 0.16153444349765778,
"learning_rate": 0.0015,
"loss": 2.6083431243896484,
"step": 420
},
{
"epoch": 0.054902343432372214,
"grad_norm": 0.12157187610864639,
"learning_rate": 0.0015,
"loss": 2.6335573196411133,
"step": 422
},
{
"epoch": 0.055162544112146494,
"grad_norm": 0.12891489267349243,
"learning_rate": 0.0015,
"loss": 2.6342296600341797,
"step": 424
},
{
"epoch": 0.05542274479192077,
"grad_norm": 0.1658623218536377,
"learning_rate": 0.0015,
"loss": 2.620544672012329,
"step": 426
},
{
"epoch": 0.05568294547169504,
"grad_norm": 0.14805150032043457,
"learning_rate": 0.0015,
"loss": 2.6231179237365723,
"step": 428
},
{
"epoch": 0.05594314615146932,
"grad_norm": 0.12362580001354218,
"learning_rate": 0.0015,
"loss": 2.6189422607421875,
"step": 430
},
{
"epoch": 0.056203346831243596,
"grad_norm": 0.14824257791042328,
"learning_rate": 0.0015,
"loss": 2.5241830348968506,
"step": 432
},
{
"epoch": 0.05646354751101787,
"grad_norm": 0.11885982751846313,
"learning_rate": 0.0015,
"loss": 2.666518211364746,
"step": 434
},
{
"epoch": 0.05672374819079215,
"grad_norm": 0.12434994429349899,
"learning_rate": 0.0015,
"loss": 2.630044460296631,
"step": 436
},
{
"epoch": 0.056983948870566424,
"grad_norm": 0.13915260136127472,
"learning_rate": 0.0015,
"loss": 2.5746140480041504,
"step": 438
},
{
"epoch": 0.0572441495503407,
"grad_norm": 0.1307705193758011,
"learning_rate": 0.0015,
"loss": 2.5896520614624023,
"step": 440
},
{
"epoch": 0.05750435023011498,
"grad_norm": 0.14974114298820496,
"learning_rate": 0.0015,
"loss": 2.6500778198242188,
"step": 442
},
{
"epoch": 0.05776455090988925,
"grad_norm": 0.19642087817192078,
"learning_rate": 0.0015,
"loss": 2.6607859134674072,
"step": 444
},
{
"epoch": 0.058024751589663526,
"grad_norm": 0.1154959574341774,
"learning_rate": 0.0015,
"loss": 2.5340981483459473,
"step": 446
},
{
"epoch": 0.058284952269437806,
"grad_norm": 0.14795628190040588,
"learning_rate": 0.0015,
"loss": 2.624563217163086,
"step": 448
},
{
"epoch": 0.05854515294921208,
"grad_norm": 0.1298312097787857,
"learning_rate": 0.0015,
"loss": 2.5719261169433594,
"step": 450
},
{
"epoch": 0.058805353628986354,
"grad_norm": 0.14340487122535706,
"learning_rate": 0.0015,
"loss": 2.672295331954956,
"step": 452
},
{
"epoch": 0.059065554308760634,
"grad_norm": 0.12575502693653107,
"learning_rate": 0.0015,
"loss": 2.549506187438965,
"step": 454
},
{
"epoch": 0.05932575498853491,
"grad_norm": 0.14216049015522003,
"learning_rate": 0.0015,
"loss": 2.578552722930908,
"step": 456
},
{
"epoch": 0.05958595566830918,
"grad_norm": 0.15293440222740173,
"learning_rate": 0.0015,
"loss": 2.574181079864502,
"step": 458
},
{
"epoch": 0.05984615634808346,
"grad_norm": 0.1480940878391266,
"learning_rate": 0.0015,
"loss": 2.6374359130859375,
"step": 460
},
{
"epoch": 0.060106357027857736,
"grad_norm": 0.1261841058731079,
"learning_rate": 0.0015,
"loss": 2.5781521797180176,
"step": 462
},
{
"epoch": 0.06036655770763201,
"grad_norm": 0.14029991626739502,
"learning_rate": 0.0015,
"loss": 2.5884461402893066,
"step": 464
},
{
"epoch": 0.06062675838740629,
"grad_norm": 0.12325909733772278,
"learning_rate": 0.0015,
"loss": 2.495574474334717,
"step": 466
},
{
"epoch": 0.060886959067180564,
"grad_norm": 0.11361188441514969,
"learning_rate": 0.0015,
"loss": 2.4616265296936035,
"step": 468
},
{
"epoch": 0.06114715974695484,
"grad_norm": 0.18037493526935577,
"learning_rate": 0.0015,
"loss": 2.6190497875213623,
"step": 470
},
{
"epoch": 0.06140736042672911,
"grad_norm": 0.12276580929756165,
"learning_rate": 0.0015,
"loss": 2.635545253753662,
"step": 472
},
{
"epoch": 0.06166756110650339,
"grad_norm": 0.13119857013225555,
"learning_rate": 0.0015,
"loss": 2.639622688293457,
"step": 474
},
{
"epoch": 0.061927761786277666,
"grad_norm": 0.2235397845506668,
"learning_rate": 0.0015,
"loss": 2.612959146499634,
"step": 476
},
{
"epoch": 0.06218796246605194,
"grad_norm": 0.137590229511261,
"learning_rate": 0.0015,
"loss": 2.549914836883545,
"step": 478
},
{
"epoch": 0.06244816314582622,
"grad_norm": 0.12429803609848022,
"learning_rate": 0.0015,
"loss": 2.582479476928711,
"step": 480
},
{
"epoch": 0.0627083638256005,
"grad_norm": 0.12502647936344147,
"learning_rate": 0.0015,
"loss": 2.5637917518615723,
"step": 482
},
{
"epoch": 0.06296856450537477,
"grad_norm": 0.12629607319831848,
"learning_rate": 0.0015,
"loss": 2.54638671875,
"step": 484
},
{
"epoch": 0.06322876518514904,
"grad_norm": 0.14317424595355988,
"learning_rate": 0.0015,
"loss": 2.5885047912597656,
"step": 486
},
{
"epoch": 0.06348896586492332,
"grad_norm": 0.20382775366306305,
"learning_rate": 0.0015,
"loss": 2.593700885772705,
"step": 488
},
{
"epoch": 0.0637491665446976,
"grad_norm": 0.11687522381544113,
"learning_rate": 0.0015,
"loss": 2.5666115283966064,
"step": 490
},
{
"epoch": 0.06400936722447187,
"grad_norm": 0.183576762676239,
"learning_rate": 0.0015,
"loss": 2.6373448371887207,
"step": 492
},
{
"epoch": 0.06426956790424615,
"grad_norm": 0.13087429106235504,
"learning_rate": 0.0015,
"loss": 2.5889272689819336,
"step": 494
},
{
"epoch": 0.06452976858402043,
"grad_norm": 0.23603849112987518,
"learning_rate": 0.0015,
"loss": 2.5812132358551025,
"step": 496
},
{
"epoch": 0.0647899692637947,
"grad_norm": 0.13527603447437286,
"learning_rate": 0.0015,
"loss": 2.565682888031006,
"step": 498
},
{
"epoch": 0.06505016994356898,
"grad_norm": 0.14632058143615723,
"learning_rate": 0.0015,
"loss": 2.5053577423095703,
"step": 500
},
{
"epoch": 0.06531037062334326,
"grad_norm": 0.14276352524757385,
"learning_rate": 0.0015,
"loss": 2.6023128032684326,
"step": 502
},
{
"epoch": 0.06557057130311753,
"grad_norm": 0.14910876750946045,
"learning_rate": 0.0015,
"loss": 2.53865122795105,
"step": 504
},
{
"epoch": 0.0658307719828918,
"grad_norm": 0.198433518409729,
"learning_rate": 0.0015,
"loss": 2.635589122772217,
"step": 506
},
{
"epoch": 0.06609097266266609,
"grad_norm": 0.1372203230857849,
"learning_rate": 0.0015,
"loss": 2.589325428009033,
"step": 508
},
{
"epoch": 0.06635117334244035,
"grad_norm": 0.18355733156204224,
"learning_rate": 0.0015,
"loss": 2.5791945457458496,
"step": 510
},
{
"epoch": 0.06661137402221463,
"grad_norm": 0.11787902563810349,
"learning_rate": 0.0015,
"loss": 2.6067702770233154,
"step": 512
},
{
"epoch": 0.06687157470198891,
"grad_norm": 0.20993410050868988,
"learning_rate": 0.0015,
"loss": 2.5679943561553955,
"step": 514
},
{
"epoch": 0.06713177538176318,
"grad_norm": 0.1326153427362442,
"learning_rate": 0.0015,
"loss": 2.592912197113037,
"step": 516
},
{
"epoch": 0.06739197606153746,
"grad_norm": 0.15812049806118011,
"learning_rate": 0.0015,
"loss": 2.583249092102051,
"step": 518
},
{
"epoch": 0.06765217674131174,
"grad_norm": 0.22075560688972473,
"learning_rate": 0.0015,
"loss": 2.6351144313812256,
"step": 520
},
{
"epoch": 0.06791237742108601,
"grad_norm": 0.16961787641048431,
"learning_rate": 0.0015,
"loss": 2.545294761657715,
"step": 522
},
{
"epoch": 0.06817257810086029,
"grad_norm": 0.18332639336585999,
"learning_rate": 0.0015,
"loss": 2.6261959075927734,
"step": 524
},
{
"epoch": 0.06843277878063457,
"grad_norm": 0.1242636889219284,
"learning_rate": 0.0015,
"loss": 2.4783449172973633,
"step": 526
},
{
"epoch": 0.06869297946040884,
"grad_norm": 0.11733566224575043,
"learning_rate": 0.0015,
"loss": 2.513880491256714,
"step": 528
},
{
"epoch": 0.06895318014018312,
"grad_norm": 0.14355388283729553,
"learning_rate": 0.0015,
"loss": 2.5490798950195312,
"step": 530
},
{
"epoch": 0.0692133808199574,
"grad_norm": 0.1932661086320877,
"learning_rate": 0.0015,
"loss": 2.552743911743164,
"step": 532
},
{
"epoch": 0.06947358149973167,
"grad_norm": 0.12102755159139633,
"learning_rate": 0.0015,
"loss": 2.5844340324401855,
"step": 534
},
{
"epoch": 0.06973378217950595,
"grad_norm": 0.1957508772611618,
"learning_rate": 0.0015,
"loss": 2.4969468116760254,
"step": 536
},
{
"epoch": 0.06999398285928023,
"grad_norm": 0.13205446302890778,
"learning_rate": 0.0015,
"loss": 2.540651798248291,
"step": 538
},
{
"epoch": 0.0702541835390545,
"grad_norm": 0.19254012405872345,
"learning_rate": 0.0015,
"loss": 2.537437915802002,
"step": 540
},
{
"epoch": 0.07051438421882877,
"grad_norm": 0.12356755137443542,
"learning_rate": 0.0015,
"loss": 2.5964531898498535,
"step": 542
},
{
"epoch": 0.07077458489860304,
"grad_norm": 0.11281155794858932,
"learning_rate": 0.0015,
"loss": 2.5733652114868164,
"step": 544
},
{
"epoch": 0.07103478557837732,
"grad_norm": 0.1333414912223816,
"learning_rate": 0.0015,
"loss": 2.5084149837493896,
"step": 546
},
{
"epoch": 0.0712949862581516,
"grad_norm": 0.19750361144542694,
"learning_rate": 0.0015,
"loss": 2.58596134185791,
"step": 548
},
{
"epoch": 0.07155518693792587,
"grad_norm": 0.11615125089883804,
"learning_rate": 0.0015,
"loss": 2.4791383743286133,
"step": 550
},
{
"epoch": 0.07181538761770015,
"grad_norm": 0.23385246098041534,
"learning_rate": 0.0015,
"loss": 2.50321102142334,
"step": 552
},
{
"epoch": 0.07207558829747443,
"grad_norm": 0.17493095993995667,
"learning_rate": 0.0015,
"loss": 2.6158947944641113,
"step": 554
},
{
"epoch": 0.0723357889772487,
"grad_norm": 0.1401086300611496,
"learning_rate": 0.0015,
"loss": 2.517688274383545,
"step": 556
},
{
"epoch": 0.07259598965702298,
"grad_norm": 0.2651103734970093,
"learning_rate": 0.0015,
"loss": 2.4191396236419678,
"step": 558
},
{
"epoch": 0.07285619033679726,
"grad_norm": 0.1722913384437561,
"learning_rate": 0.0015,
"loss": 2.5673346519470215,
"step": 560
},
{
"epoch": 0.07311639101657152,
"grad_norm": 0.12414658069610596,
"learning_rate": 0.0015,
"loss": 2.6212687492370605,
"step": 562
},
{
"epoch": 0.0733765916963458,
"grad_norm": 0.12208303064107895,
"learning_rate": 0.0015,
"loss": 2.546102523803711,
"step": 564
},
{
"epoch": 0.07363679237612009,
"grad_norm": 0.18498128652572632,
"learning_rate": 0.0015,
"loss": 2.5047688484191895,
"step": 566
},
{
"epoch": 0.07389699305589435,
"grad_norm": 0.11353137344121933,
"learning_rate": 0.0015,
"loss": 2.6000404357910156,
"step": 568
},
{
"epoch": 0.07415719373566863,
"grad_norm": 0.11640340089797974,
"learning_rate": 0.0015,
"loss": 2.562701940536499,
"step": 570
},
{
"epoch": 0.07441739441544291,
"grad_norm": 0.16006167232990265,
"learning_rate": 0.0015,
"loss": 2.5445828437805176,
"step": 572
},
{
"epoch": 0.07467759509521718,
"grad_norm": 0.12379810959100723,
"learning_rate": 0.0015,
"loss": 2.532503128051758,
"step": 574
},
{
"epoch": 0.07493779577499146,
"grad_norm": 0.20058363676071167,
"learning_rate": 0.0015,
"loss": 2.4340412616729736,
"step": 576
},
{
"epoch": 0.07519799645476574,
"grad_norm": 0.14642098546028137,
"learning_rate": 0.0015,
"loss": 2.502790689468384,
"step": 578
},
{
"epoch": 0.07545819713454001,
"grad_norm": 0.14208285510540009,
"learning_rate": 0.0015,
"loss": 2.6028313636779785,
"step": 580
},
{
"epoch": 0.07571839781431429,
"grad_norm": 0.16576264798641205,
"learning_rate": 0.0015,
"loss": 2.590580463409424,
"step": 582
},
{
"epoch": 0.07597859849408857,
"grad_norm": 0.1109340563416481,
"learning_rate": 0.0015,
"loss": 2.454275608062744,
"step": 584
},
{
"epoch": 0.07623879917386284,
"grad_norm": 0.11368656903505325,
"learning_rate": 0.0015,
"loss": 2.559783935546875,
"step": 586
},
{
"epoch": 0.07649899985363712,
"grad_norm": 0.18466179072856903,
"learning_rate": 0.0015,
"loss": 2.5907435417175293,
"step": 588
},
{
"epoch": 0.0767592005334114,
"grad_norm": 0.15122883021831512,
"learning_rate": 0.0015,
"loss": 2.5490379333496094,
"step": 590
},
{
"epoch": 0.07701940121318566,
"grad_norm": 0.1400233656167984,
"learning_rate": 0.0015,
"loss": 2.5655360221862793,
"step": 592
},
{
"epoch": 0.07727960189295995,
"grad_norm": 0.12041738629341125,
"learning_rate": 0.0015,
"loss": 2.5855493545532227,
"step": 594
},
{
"epoch": 0.07753980257273423,
"grad_norm": 0.11596609652042389,
"learning_rate": 0.0015,
"loss": 2.538209915161133,
"step": 596
},
{
"epoch": 0.07780000325250849,
"grad_norm": 0.11742275953292847,
"learning_rate": 0.0015,
"loss": 2.4697577953338623,
"step": 598
},
{
"epoch": 0.07806020393228277,
"grad_norm": 0.1307411640882492,
"learning_rate": 0.0015,
"loss": 2.5475921630859375,
"step": 600
},
{
"epoch": 0.07832040461205705,
"grad_norm": 0.12216457724571228,
"learning_rate": 0.0015,
"loss": 2.4666059017181396,
"step": 602
},
{
"epoch": 0.07858060529183132,
"grad_norm": 0.1410822570323944,
"learning_rate": 0.0015,
"loss": 2.5005970001220703,
"step": 604
},
{
"epoch": 0.0788408059716056,
"grad_norm": 0.12861311435699463,
"learning_rate": 0.0015,
"loss": 2.554330825805664,
"step": 606
},
{
"epoch": 0.07910100665137988,
"grad_norm": 0.13337506353855133,
"learning_rate": 0.0015,
"loss": 2.5301127433776855,
"step": 608
},
{
"epoch": 0.07936120733115415,
"grad_norm": 0.15406863391399384,
"learning_rate": 0.0015,
"loss": 2.5119733810424805,
"step": 610
},
{
"epoch": 0.07962140801092843,
"grad_norm": 0.17507420480251312,
"learning_rate": 0.0015,
"loss": 2.5119690895080566,
"step": 612
},
{
"epoch": 0.07988160869070271,
"grad_norm": 0.11584312468767166,
"learning_rate": 0.0015,
"loss": 2.5782370567321777,
"step": 614
},
{
"epoch": 0.08014180937047698,
"grad_norm": 0.14256927371025085,
"learning_rate": 0.0015,
"loss": 2.5322585105895996,
"step": 616
},
{
"epoch": 0.08040201005025126,
"grad_norm": 0.16758249700069427,
"learning_rate": 0.0015,
"loss": 2.575878143310547,
"step": 618
},
{
"epoch": 0.08066221073002554,
"grad_norm": 0.13935622572898865,
"learning_rate": 0.0015,
"loss": 2.5629076957702637,
"step": 620
},
{
"epoch": 0.0809224114097998,
"grad_norm": 0.12993550300598145,
"learning_rate": 0.0015,
"loss": 2.503211259841919,
"step": 622
},
{
"epoch": 0.08118261208957409,
"grad_norm": 0.15919028222560883,
"learning_rate": 0.0015,
"loss": 2.6716480255126953,
"step": 624
},
{
"epoch": 0.08144281276934837,
"grad_norm": 0.11908809095621109,
"learning_rate": 0.0015,
"loss": 2.5645601749420166,
"step": 626
},
{
"epoch": 0.08170301344912263,
"grad_norm": 0.11332940310239792,
"learning_rate": 0.0015,
"loss": 2.548771619796753,
"step": 628
},
{
"epoch": 0.08196321412889691,
"grad_norm": 0.1313566267490387,
"learning_rate": 0.0015,
"loss": 2.6182522773742676,
"step": 630
},
{
"epoch": 0.0822234148086712,
"grad_norm": 0.12268718332052231,
"learning_rate": 0.0015,
"loss": 2.489835262298584,
"step": 632
},
{
"epoch": 0.08248361548844546,
"grad_norm": 0.12420812249183655,
"learning_rate": 0.0015,
"loss": 2.5113680362701416,
"step": 634
},
{
"epoch": 0.08274381616821974,
"grad_norm": 0.13908511400222778,
"learning_rate": 0.0015,
"loss": 2.5134804248809814,
"step": 636
},
{
"epoch": 0.08300401684799402,
"grad_norm": 0.14693544805049896,
"learning_rate": 0.0015,
"loss": 2.5647387504577637,
"step": 638
},
{
"epoch": 0.08326421752776829,
"grad_norm": 0.13369478285312653,
"learning_rate": 0.0015,
"loss": 2.5393519401550293,
"step": 640
},
{
"epoch": 0.08352441820754257,
"grad_norm": 0.13182099163532257,
"learning_rate": 0.0015,
"loss": 2.4621944427490234,
"step": 642
},
{
"epoch": 0.08378461888731684,
"grad_norm": 0.16078202426433563,
"learning_rate": 0.0015,
"loss": 2.4677064418792725,
"step": 644
},
{
"epoch": 0.08404481956709112,
"grad_norm": 0.18532077968120575,
"learning_rate": 0.0015,
"loss": 2.477581739425659,
"step": 646
},
{
"epoch": 0.0843050202468654,
"grad_norm": 0.10907570272684097,
"learning_rate": 0.0015,
"loss": 2.524442672729492,
"step": 648
},
{
"epoch": 0.08456522092663966,
"grad_norm": 0.14104482531547546,
"learning_rate": 0.0015,
"loss": 2.4496612548828125,
"step": 650
},
{
"epoch": 0.08482542160641394,
"grad_norm": 0.14776431024074554,
"learning_rate": 0.0015,
"loss": 2.530264377593994,
"step": 652
},
{
"epoch": 0.08508562228618823,
"grad_norm": 0.13904069364070892,
"learning_rate": 0.0015,
"loss": 2.604109287261963,
"step": 654
},
{
"epoch": 0.08534582296596249,
"grad_norm": 0.14588233828544617,
"learning_rate": 0.0015,
"loss": 2.4963693618774414,
"step": 656
},
{
"epoch": 0.08560602364573677,
"grad_norm": 0.15345178544521332,
"learning_rate": 0.0015,
"loss": 2.531615734100342,
"step": 658
},
{
"epoch": 0.08586622432551105,
"grad_norm": 0.15590955317020416,
"learning_rate": 0.0015,
"loss": 2.4773566722869873,
"step": 660
},
{
"epoch": 0.08612642500528532,
"grad_norm": 0.24131813645362854,
"learning_rate": 0.0015,
"loss": 2.534609317779541,
"step": 662
},
{
"epoch": 0.0863866256850596,
"grad_norm": 0.13829457759857178,
"learning_rate": 0.0015,
"loss": 2.4890403747558594,
"step": 664
},
{
"epoch": 0.08664682636483388,
"grad_norm": 0.2665689289569855,
"learning_rate": 0.0015,
"loss": 2.5261645317077637,
"step": 666
},
{
"epoch": 0.08690702704460815,
"grad_norm": 0.12278895080089569,
"learning_rate": 0.0015,
"loss": 2.4704575538635254,
"step": 668
},
{
"epoch": 0.08716722772438243,
"grad_norm": 0.1457744985818863,
"learning_rate": 0.0015,
"loss": 2.527120590209961,
"step": 670
},
{
"epoch": 0.08742742840415671,
"grad_norm": 0.18936526775360107,
"learning_rate": 0.0015,
"loss": 2.5764763355255127,
"step": 672
},
{
"epoch": 0.08768762908393098,
"grad_norm": 0.16044090688228607,
"learning_rate": 0.0015,
"loss": 2.557800531387329,
"step": 674
},
{
"epoch": 0.08794782976370526,
"grad_norm": 0.11910203844308853,
"learning_rate": 0.0015,
"loss": 2.515000820159912,
"step": 676
},
{
"epoch": 0.08820803044347954,
"grad_norm": 0.1980702430009842,
"learning_rate": 0.0015,
"loss": 2.4426794052124023,
"step": 678
},
{
"epoch": 0.0884682311232538,
"grad_norm": 0.2644166052341461,
"learning_rate": 0.0015,
"loss": 2.5487544536590576,
"step": 680
},
{
"epoch": 0.08872843180302808,
"grad_norm": 0.12081696093082428,
"learning_rate": 0.0015,
"loss": 2.489809036254883,
"step": 682
},
{
"epoch": 0.08898863248280237,
"grad_norm": 0.20768149197101593,
"learning_rate": 0.0015,
"loss": 2.4334044456481934,
"step": 684
},
{
"epoch": 0.08924883316257663,
"grad_norm": 0.1605047881603241,
"learning_rate": 0.0015,
"loss": 2.412212371826172,
"step": 686
},
{
"epoch": 0.08950903384235091,
"grad_norm": 0.1852238029241562,
"learning_rate": 0.0015,
"loss": 2.5724077224731445,
"step": 688
},
{
"epoch": 0.0897692345221252,
"grad_norm": 0.14606717228889465,
"learning_rate": 0.0015,
"loss": 2.5150301456451416,
"step": 690
},
{
"epoch": 0.09002943520189946,
"grad_norm": 0.1127178892493248,
"learning_rate": 0.0015,
"loss": 2.5333385467529297,
"step": 692
},
{
"epoch": 0.09028963588167374,
"grad_norm": 0.13244138658046722,
"learning_rate": 0.0015,
"loss": 2.506751537322998,
"step": 694
},
{
"epoch": 0.09054983656144802,
"grad_norm": 0.11649299412965775,
"learning_rate": 0.0015,
"loss": 2.4993643760681152,
"step": 696
},
{
"epoch": 0.09081003724122229,
"grad_norm": 0.11965850740671158,
"learning_rate": 0.0015,
"loss": 2.530313491821289,
"step": 698
},
{
"epoch": 0.09107023792099657,
"grad_norm": 0.13063354790210724,
"learning_rate": 0.0015,
"loss": 2.541741371154785,
"step": 700
},
{
"epoch": 0.09133043860077085,
"grad_norm": 0.1462620198726654,
"learning_rate": 0.0015,
"loss": 2.5551137924194336,
"step": 702
},
{
"epoch": 0.09159063928054512,
"grad_norm": 0.13256198167800903,
"learning_rate": 0.0015,
"loss": 2.4662652015686035,
"step": 704
},
{
"epoch": 0.0918508399603194,
"grad_norm": 0.15502355992794037,
"learning_rate": 0.0015,
"loss": 2.5150249004364014,
"step": 706
},
{
"epoch": 0.09211104064009368,
"grad_norm": 0.18196983635425568,
"learning_rate": 0.0015,
"loss": 2.4843883514404297,
"step": 708
},
{
"epoch": 0.09237124131986794,
"grad_norm": 0.14866191148757935,
"learning_rate": 0.0015,
"loss": 2.496154308319092,
"step": 710
},
{
"epoch": 0.09263144199964223,
"grad_norm": 0.11658824980258942,
"learning_rate": 0.0015,
"loss": 2.4449501037597656,
"step": 712
},
{
"epoch": 0.0928916426794165,
"grad_norm": 0.1440459042787552,
"learning_rate": 0.0015,
"loss": 2.490208625793457,
"step": 714
},
{
"epoch": 0.09315184335919077,
"grad_norm": 0.19502736628055573,
"learning_rate": 0.0015,
"loss": 2.5548291206359863,
"step": 716
},
{
"epoch": 0.09341204403896505,
"grad_norm": 0.1289069652557373,
"learning_rate": 0.0015,
"loss": 2.445272445678711,
"step": 718
},
{
"epoch": 0.09367224471873933,
"grad_norm": 0.11711007356643677,
"learning_rate": 0.0015,
"loss": 2.469451427459717,
"step": 720
},
{
"epoch": 0.0939324453985136,
"grad_norm": 0.12621375918388367,
"learning_rate": 0.0015,
"loss": 2.5695018768310547,
"step": 722
},
{
"epoch": 0.09419264607828788,
"grad_norm": 0.14285998046398163,
"learning_rate": 0.0015,
"loss": 2.477400302886963,
"step": 724
},
{
"epoch": 0.09445284675806216,
"grad_norm": 0.1324525624513626,
"learning_rate": 0.0015,
"loss": 2.4934685230255127,
"step": 726
},
{
"epoch": 0.09471304743783643,
"grad_norm": 0.10702130198478699,
"learning_rate": 0.0015,
"loss": 2.478593349456787,
"step": 728
},
{
"epoch": 0.09497324811761071,
"grad_norm": 0.12025975435972214,
"learning_rate": 0.0015,
"loss": 2.4158713817596436,
"step": 730
},
{
"epoch": 0.09523344879738499,
"grad_norm": 0.11236289143562317,
"learning_rate": 0.0015,
"loss": 2.529749870300293,
"step": 732
},
{
"epoch": 0.09549364947715926,
"grad_norm": 0.12934474647045135,
"learning_rate": 0.0015,
"loss": 2.531521797180176,
"step": 734
},
{
"epoch": 0.09575385015693354,
"grad_norm": 0.11176446080207825,
"learning_rate": 0.0015,
"loss": 2.436703681945801,
"step": 736
},
{
"epoch": 0.09601405083670782,
"grad_norm": 0.15079233050346375,
"learning_rate": 0.0015,
"loss": 2.425929069519043,
"step": 738
},
{
"epoch": 0.09627425151648208,
"grad_norm": 0.11708604544401169,
"learning_rate": 0.0015,
"loss": 2.4982924461364746,
"step": 740
},
{
"epoch": 0.09653445219625637,
"grad_norm": 0.14889422059059143,
"learning_rate": 0.0015,
"loss": 2.5074567794799805,
"step": 742
},
{
"epoch": 0.09679465287603063,
"grad_norm": 0.1744641363620758,
"learning_rate": 0.0015,
"loss": 2.4625606536865234,
"step": 744
},
{
"epoch": 0.09705485355580491,
"grad_norm": 0.10757909715175629,
"learning_rate": 0.0015,
"loss": 2.4002695083618164,
"step": 746
},
{
"epoch": 0.0973150542355792,
"grad_norm": 0.19156695902347565,
"learning_rate": 0.0015,
"loss": 2.5078234672546387,
"step": 748
},
{
"epoch": 0.09757525491535346,
"grad_norm": 0.13070686161518097,
"learning_rate": 0.0015,
"loss": 2.481682777404785,
"step": 750
},
{
"epoch": 0.09783545559512774,
"grad_norm": 0.1559971421957016,
"learning_rate": 0.0015,
"loss": 2.483724594116211,
"step": 752
},
{
"epoch": 0.09809565627490202,
"grad_norm": 0.10168272256851196,
"learning_rate": 0.0015,
"loss": 2.4188013076782227,
"step": 754
},
{
"epoch": 0.09835585695467629,
"grad_norm": 0.17042742669582367,
"learning_rate": 0.0015,
"loss": 2.4481377601623535,
"step": 756
},
{
"epoch": 0.09861605763445057,
"grad_norm": 0.12191086262464523,
"learning_rate": 0.0015,
"loss": 2.4696085453033447,
"step": 758
},
{
"epoch": 0.09887625831422485,
"grad_norm": 0.18985164165496826,
"learning_rate": 0.0015,
"loss": 2.5029356479644775,
"step": 760
},
{
"epoch": 0.09913645899399912,
"grad_norm": 0.12053395062685013,
"learning_rate": 0.0015,
"loss": 2.471561908721924,
"step": 762
},
{
"epoch": 0.0993966596737734,
"grad_norm": 0.11260586231946945,
"learning_rate": 0.0015,
"loss": 2.4876153469085693,
"step": 764
},
{
"epoch": 0.09965686035354768,
"grad_norm": 0.10991669446229935,
"learning_rate": 0.0015,
"loss": 2.4546608924865723,
"step": 766
},
{
"epoch": 0.09991706103332194,
"grad_norm": 0.13373911380767822,
"learning_rate": 0.0015,
"loss": 2.4511330127716064,
"step": 768
},
{
"epoch": 0.10017726171309622,
"grad_norm": 0.09733694046735764,
"learning_rate": 0.0015,
"loss": 2.398179292678833,
"step": 770
},
{
"epoch": 0.1004374623928705,
"grad_norm": 0.13615287840366364,
"learning_rate": 0.0015,
"loss": 2.476090908050537,
"step": 772
},
{
"epoch": 0.10069766307264477,
"grad_norm": 0.12906911969184875,
"learning_rate": 0.0015,
"loss": 2.5038747787475586,
"step": 774
},
{
"epoch": 0.10095786375241905,
"grad_norm": 0.19029171764850616,
"learning_rate": 0.0015,
"loss": 2.515749454498291,
"step": 776
},
{
"epoch": 0.10121806443219333,
"grad_norm": 0.13701385259628296,
"learning_rate": 0.0015,
"loss": 2.5420799255371094,
"step": 778
},
{
"epoch": 0.1014782651119676,
"grad_norm": 0.13473469018936157,
"learning_rate": 0.0015,
"loss": 2.5171680450439453,
"step": 780
},
{
"epoch": 0.10173846579174188,
"grad_norm": 0.12206988036632538,
"learning_rate": 0.0015,
"loss": 2.5140299797058105,
"step": 782
},
{
"epoch": 0.10199866647151616,
"grad_norm": 0.16678650677204132,
"learning_rate": 0.0015,
"loss": 2.5734801292419434,
"step": 784
},
{
"epoch": 0.10225886715129043,
"grad_norm": 0.11919064074754715,
"learning_rate": 0.0015,
"loss": 2.3694310188293457,
"step": 786
},
{
"epoch": 0.10251906783106471,
"grad_norm": 0.11366023868322372,
"learning_rate": 0.0015,
"loss": 2.4591619968414307,
"step": 788
},
{
"epoch": 0.10277926851083899,
"grad_norm": 0.12312934547662735,
"learning_rate": 0.0015,
"loss": 2.5185508728027344,
"step": 790
},
{
"epoch": 0.10303946919061326,
"grad_norm": 0.1520123928785324,
"learning_rate": 0.0015,
"loss": 2.5622916221618652,
"step": 792
},
{
"epoch": 0.10329966987038754,
"grad_norm": 0.1643320620059967,
"learning_rate": 0.0015,
"loss": 2.4844510555267334,
"step": 794
},
{
"epoch": 0.10355987055016182,
"grad_norm": 0.11246604472398758,
"learning_rate": 0.0015,
"loss": 2.424683094024658,
"step": 796
},
{
"epoch": 0.10382007122993608,
"grad_norm": 0.1600845605134964,
"learning_rate": 0.0015,
"loss": 2.467665672302246,
"step": 798
},
{
"epoch": 0.10408027190971036,
"grad_norm": 0.11838793009519577,
"learning_rate": 0.0015,
"loss": 2.5429134368896484,
"step": 800
},
{
"epoch": 0.10434047258948465,
"grad_norm": 0.11583756655454636,
"learning_rate": 0.0015,
"loss": 2.4626121520996094,
"step": 802
},
{
"epoch": 0.10460067326925891,
"grad_norm": 0.11499626189470291,
"learning_rate": 0.0015,
"loss": 2.497128486633301,
"step": 804
},
{
"epoch": 0.10486087394903319,
"grad_norm": 0.2323618233203888,
"learning_rate": 0.0015,
"loss": 2.4246530532836914,
"step": 806
},
{
"epoch": 0.10512107462880747,
"grad_norm": 0.1438981145620346,
"learning_rate": 0.0015,
"loss": 2.5071704387664795,
"step": 808
},
{
"epoch": 0.10538127530858174,
"grad_norm": 0.11748737841844559,
"learning_rate": 0.0015,
"loss": 2.476731300354004,
"step": 810
},
{
"epoch": 0.10564147598835602,
"grad_norm": 0.19243799149990082,
"learning_rate": 0.0015,
"loss": 2.5406248569488525,
"step": 812
},
{
"epoch": 0.1059016766681303,
"grad_norm": 0.11459548771381378,
"learning_rate": 0.0015,
"loss": 2.415768623352051,
"step": 814
},
{
"epoch": 0.10616187734790457,
"grad_norm": 0.22774600982666016,
"learning_rate": 0.0015,
"loss": 2.455199718475342,
"step": 816
},
{
"epoch": 0.10642207802767885,
"grad_norm": 0.11443344503641129,
"learning_rate": 0.0015,
"loss": 2.5359983444213867,
"step": 818
},
{
"epoch": 0.10668227870745313,
"grad_norm": 0.1261078417301178,
"learning_rate": 0.0015,
"loss": 2.4155945777893066,
"step": 820
},
{
"epoch": 0.1069424793872274,
"grad_norm": 0.1700322926044464,
"learning_rate": 0.0015,
"loss": 2.5150909423828125,
"step": 822
},
{
"epoch": 0.10720268006700168,
"grad_norm": 0.11378102749586105,
"learning_rate": 0.0015,
"loss": 2.4695568084716797,
"step": 824
},
{
"epoch": 0.10746288074677596,
"grad_norm": 0.13540437817573547,
"learning_rate": 0.0015,
"loss": 2.515244960784912,
"step": 826
},
{
"epoch": 0.10772308142655022,
"grad_norm": 0.11232029646635056,
"learning_rate": 0.0015,
"loss": 2.4454617500305176,
"step": 828
},
{
"epoch": 0.1079832821063245,
"grad_norm": 0.1433100700378418,
"learning_rate": 0.0015,
"loss": 2.4610981941223145,
"step": 830
},
{
"epoch": 0.10824348278609879,
"grad_norm": 0.14747196435928345,
"learning_rate": 0.0015,
"loss": 2.512965440750122,
"step": 832
},
{
"epoch": 0.10850368346587305,
"grad_norm": 0.11969432234764099,
"learning_rate": 0.0015,
"loss": 2.528841018676758,
"step": 834
},
{
"epoch": 0.10876388414564733,
"grad_norm": 0.12883418798446655,
"learning_rate": 0.0015,
"loss": 2.5040335655212402,
"step": 836
},
{
"epoch": 0.10902408482542161,
"grad_norm": 0.19044166803359985,
"learning_rate": 0.0015,
"loss": 2.478750228881836,
"step": 838
},
{
"epoch": 0.10928428550519588,
"grad_norm": 0.15454842150211334,
"learning_rate": 0.0015,
"loss": 2.4856419563293457,
"step": 840
},
{
"epoch": 0.10954448618497016,
"grad_norm": 0.11819291859865189,
"learning_rate": 0.0015,
"loss": 2.4163312911987305,
"step": 842
},
{
"epoch": 0.10980468686474443,
"grad_norm": 0.1892247349023819,
"learning_rate": 0.0015,
"loss": 2.396820545196533,
"step": 844
},
{
"epoch": 0.11006488754451871,
"grad_norm": 0.19431066513061523,
"learning_rate": 0.0015,
"loss": 2.537531614303589,
"step": 846
},
{
"epoch": 0.11032508822429299,
"grad_norm": 0.15151803195476532,
"learning_rate": 0.0015,
"loss": 2.440938949584961,
"step": 848
},
{
"epoch": 0.11058528890406726,
"grad_norm": 0.13907906413078308,
"learning_rate": 0.0015,
"loss": 2.5495567321777344,
"step": 850
},
{
"epoch": 0.11084548958384154,
"grad_norm": 0.13976429402828217,
"learning_rate": 0.0015,
"loss": 2.4400763511657715,
"step": 852
},
{
"epoch": 0.11110569026361582,
"grad_norm": 0.1101430281996727,
"learning_rate": 0.0015,
"loss": 2.5156853199005127,
"step": 854
},
{
"epoch": 0.11136589094339008,
"grad_norm": 0.2034296840429306,
"learning_rate": 0.0015,
"loss": 2.4110891819000244,
"step": 856
},
{
"epoch": 0.11162609162316436,
"grad_norm": 0.21087896823883057,
"learning_rate": 0.0015,
"loss": 2.423288583755493,
"step": 858
},
{
"epoch": 0.11188629230293864,
"grad_norm": 0.15142200887203217,
"learning_rate": 0.0015,
"loss": 2.473625659942627,
"step": 860
},
{
"epoch": 0.11214649298271291,
"grad_norm": 0.11025089025497437,
"learning_rate": 0.0015,
"loss": 2.4484028816223145,
"step": 862
},
{
"epoch": 0.11240669366248719,
"grad_norm": 0.1491570919752121,
"learning_rate": 0.0015,
"loss": 2.505532741546631,
"step": 864
},
{
"epoch": 0.11266689434226147,
"grad_norm": 0.11216303706169128,
"learning_rate": 0.0015,
"loss": 2.548219680786133,
"step": 866
},
{
"epoch": 0.11292709502203574,
"grad_norm": 0.11430005729198456,
"learning_rate": 0.0015,
"loss": 2.4133553504943848,
"step": 868
},
{
"epoch": 0.11318729570181002,
"grad_norm": 0.18291090428829193,
"learning_rate": 0.0015,
"loss": 2.507143497467041,
"step": 870
},
{
"epoch": 0.1134474963815843,
"grad_norm": 0.1979239135980606,
"learning_rate": 0.0015,
"loss": 2.412238359451294,
"step": 872
},
{
"epoch": 0.11370769706135857,
"grad_norm": 0.13865049183368683,
"learning_rate": 0.0015,
"loss": 2.4398233890533447,
"step": 874
},
{
"epoch": 0.11396789774113285,
"grad_norm": 0.19918091595172882,
"learning_rate": 0.0015,
"loss": 2.4988279342651367,
"step": 876
},
{
"epoch": 0.11422809842090713,
"grad_norm": 0.11325831711292267,
"learning_rate": 0.0015,
"loss": 2.494500160217285,
"step": 878
},
{
"epoch": 0.1144882991006814,
"grad_norm": 0.14829902350902557,
"learning_rate": 0.0015,
"loss": 2.5095462799072266,
"step": 880
},
{
"epoch": 0.11474849978045568,
"grad_norm": 0.21892991662025452,
"learning_rate": 0.0015,
"loss": 2.4745447635650635,
"step": 882
},
{
"epoch": 0.11500870046022996,
"grad_norm": 0.11891723424196243,
"learning_rate": 0.0015,
"loss": 2.5164599418640137,
"step": 884
},
{
"epoch": 0.11526890114000422,
"grad_norm": 0.14889734983444214,
"learning_rate": 0.0015,
"loss": 2.4883475303649902,
"step": 886
},
{
"epoch": 0.1155291018197785,
"grad_norm": 0.1462695151567459,
"learning_rate": 0.0015,
"loss": 2.4669761657714844,
"step": 888
},
{
"epoch": 0.11578930249955278,
"grad_norm": 0.1408451497554779,
"learning_rate": 0.0015,
"loss": 2.4396119117736816,
"step": 890
},
{
"epoch": 0.11604950317932705,
"grad_norm": 0.104103684425354,
"learning_rate": 0.0015,
"loss": 2.4268996715545654,
"step": 892
},
{
"epoch": 0.11630970385910133,
"grad_norm": 0.1391294002532959,
"learning_rate": 0.0015,
"loss": 2.3986964225769043,
"step": 894
},
{
"epoch": 0.11656990453887561,
"grad_norm": 0.16641506552696228,
"learning_rate": 0.0015,
"loss": 2.48289155960083,
"step": 896
},
{
"epoch": 0.11683010521864988,
"grad_norm": 0.14706654846668243,
"learning_rate": 0.0015,
"loss": 2.5131571292877197,
"step": 898
},
{
"epoch": 0.11709030589842416,
"grad_norm": 0.14331388473510742,
"learning_rate": 0.0015,
"loss": 2.481987714767456,
"step": 900
},
{
"epoch": 0.11735050657819844,
"grad_norm": 0.1329609900712967,
"learning_rate": 0.0015,
"loss": 2.5684447288513184,
"step": 902
},
{
"epoch": 0.11761070725797271,
"grad_norm": 0.10474152863025665,
"learning_rate": 0.0015,
"loss": 2.496450424194336,
"step": 904
},
{
"epoch": 0.11787090793774699,
"grad_norm": 0.11489632725715637,
"learning_rate": 0.0015,
"loss": 2.486365556716919,
"step": 906
},
{
"epoch": 0.11813110861752127,
"grad_norm": 0.11455623060464859,
"learning_rate": 0.0015,
"loss": 2.392237901687622,
"step": 908
},
{
"epoch": 0.11839130929729554,
"grad_norm": 0.12375067919492722,
"learning_rate": 0.0015,
"loss": 2.416073799133301,
"step": 910
},
{
"epoch": 0.11865150997706982,
"grad_norm": 0.10999967157840729,
"learning_rate": 0.0015,
"loss": 2.4682672023773193,
"step": 912
},
{
"epoch": 0.1189117106568441,
"grad_norm": 0.1222982406616211,
"learning_rate": 0.0015,
"loss": 2.4839866161346436,
"step": 914
},
{
"epoch": 0.11917191133661836,
"grad_norm": 0.13484585285186768,
"learning_rate": 0.0015,
"loss": 2.488656997680664,
"step": 916
},
{
"epoch": 0.11943211201639264,
"grad_norm": 0.10286282002925873,
"learning_rate": 0.0015,
"loss": 2.525235652923584,
"step": 918
},
{
"epoch": 0.11969231269616692,
"grad_norm": 0.11514491587877274,
"learning_rate": 0.0015,
"loss": 2.5040040016174316,
"step": 920
},
{
"epoch": 0.11995251337594119,
"grad_norm": 0.12345292419195175,
"learning_rate": 0.0015,
"loss": 2.459651231765747,
"step": 922
},
{
"epoch": 0.12021271405571547,
"grad_norm": 0.1070815771818161,
"learning_rate": 0.0015,
"loss": 2.4803178310394287,
"step": 924
},
{
"epoch": 0.12047291473548975,
"grad_norm": 0.10990746319293976,
"learning_rate": 0.0015,
"loss": 2.457594394683838,
"step": 926
},
{
"epoch": 0.12073311541526402,
"grad_norm": 0.13413861393928528,
"learning_rate": 0.0015,
"loss": 2.4468042850494385,
"step": 928
},
{
"epoch": 0.1209933160950383,
"grad_norm": 0.11186478286981583,
"learning_rate": 0.0015,
"loss": 2.442903518676758,
"step": 930
},
{
"epoch": 0.12125351677481258,
"grad_norm": 0.12038417905569077,
"learning_rate": 0.0015,
"loss": 2.3339438438415527,
"step": 932
},
{
"epoch": 0.12151371745458685,
"grad_norm": 0.17366178333759308,
"learning_rate": 0.0015,
"loss": 2.4548568725585938,
"step": 934
},
{
"epoch": 0.12177391813436113,
"grad_norm": 0.11260256916284561,
"learning_rate": 0.0015,
"loss": 2.439826250076294,
"step": 936
},
{
"epoch": 0.12203411881413541,
"grad_norm": 0.16781844198703766,
"learning_rate": 0.0015,
"loss": 2.4350109100341797,
"step": 938
},
{
"epoch": 0.12229431949390968,
"grad_norm": 0.14944791793823242,
"learning_rate": 0.0015,
"loss": 2.4554519653320312,
"step": 940
},
{
"epoch": 0.12255452017368396,
"grad_norm": 0.12105905264616013,
"learning_rate": 0.0015,
"loss": 2.4930989742279053,
"step": 942
},
{
"epoch": 0.12281472085345822,
"grad_norm": 0.24054458737373352,
"learning_rate": 0.0015,
"loss": 2.5314407348632812,
"step": 944
},
{
"epoch": 0.1230749215332325,
"grad_norm": 0.11755185574293137,
"learning_rate": 0.0015,
"loss": 2.433711051940918,
"step": 946
},
{
"epoch": 0.12333512221300678,
"grad_norm": 0.2742673456668854,
"learning_rate": 0.0015,
"loss": 2.4475271701812744,
"step": 948
},
{
"epoch": 0.12359532289278105,
"grad_norm": 0.2013305127620697,
"learning_rate": 0.0015,
"loss": 2.4712271690368652,
"step": 950
},
{
"epoch": 0.12385552357255533,
"grad_norm": 0.1352348029613495,
"learning_rate": 0.0015,
"loss": 2.4669923782348633,
"step": 952
},
{
"epoch": 0.12411572425232961,
"grad_norm": 0.2573494017124176,
"learning_rate": 0.0015,
"loss": 2.403353214263916,
"step": 954
},
{
"epoch": 0.12437592493210388,
"grad_norm": 0.22976142168045044,
"learning_rate": 0.0015,
"loss": 2.4728734493255615,
"step": 956
},
{
"epoch": 0.12463612561187816,
"grad_norm": 0.12941211462020874,
"learning_rate": 0.0015,
"loss": 2.4981071949005127,
"step": 958
},
{
"epoch": 0.12489632629165244,
"grad_norm": 0.15471619367599487,
"learning_rate": 0.0015,
"loss": 2.483341693878174,
"step": 960
},
{
"epoch": 0.1251565269714267,
"grad_norm": 0.20464009046554565,
"learning_rate": 0.0015,
"loss": 2.348433017730713,
"step": 962
},
{
"epoch": 0.125416727651201,
"grad_norm": 0.12188667058944702,
"learning_rate": 0.0015,
"loss": 2.4026639461517334,
"step": 964
},
{
"epoch": 0.12567692833097527,
"grad_norm": 0.18323232233524323,
"learning_rate": 0.0015,
"loss": 2.5070765018463135,
"step": 966
},
{
"epoch": 0.12593712901074955,
"grad_norm": 0.16702760756015778,
"learning_rate": 0.0015,
"loss": 2.4475314617156982,
"step": 968
},
{
"epoch": 0.12619732969052383,
"grad_norm": 0.10072800517082214,
"learning_rate": 0.0015,
"loss": 2.398653030395508,
"step": 970
},
{
"epoch": 0.12645753037029808,
"grad_norm": 0.11068949848413467,
"learning_rate": 0.0015,
"loss": 2.5137791633605957,
"step": 972
},
{
"epoch": 0.12671773105007236,
"grad_norm": 0.11984645575284958,
"learning_rate": 0.0015,
"loss": 2.3543200492858887,
"step": 974
},
{
"epoch": 0.12697793172984664,
"grad_norm": 0.1345328390598297,
"learning_rate": 0.0015,
"loss": 2.5010509490966797,
"step": 976
},
{
"epoch": 0.12723813240962092,
"grad_norm": 0.10265976190567017,
"learning_rate": 0.0015,
"loss": 2.466796398162842,
"step": 978
},
{
"epoch": 0.1274983330893952,
"grad_norm": 0.1264086365699768,
"learning_rate": 0.0015,
"loss": 2.5070204734802246,
"step": 980
},
{
"epoch": 0.12775853376916949,
"grad_norm": 0.19938229024410248,
"learning_rate": 0.0015,
"loss": 2.357666015625,
"step": 982
},
{
"epoch": 0.12801873444894374,
"grad_norm": 0.12119675427675247,
"learning_rate": 0.0015,
"loss": 2.487483024597168,
"step": 984
},
{
"epoch": 0.12827893512871802,
"grad_norm": 0.1274806410074234,
"learning_rate": 0.0015,
"loss": 2.4527902603149414,
"step": 986
},
{
"epoch": 0.1285391358084923,
"grad_norm": 0.22585996985435486,
"learning_rate": 0.0015,
"loss": 2.494025707244873,
"step": 988
},
{
"epoch": 0.12879933648826658,
"grad_norm": 0.10816916823387146,
"learning_rate": 0.0015,
"loss": 2.49330472946167,
"step": 990
},
{
"epoch": 0.12905953716804086,
"grad_norm": 0.1344311386346817,
"learning_rate": 0.0015,
"loss": 2.4067468643188477,
"step": 992
},
{
"epoch": 0.1293197378478151,
"grad_norm": 0.12150255590677261,
"learning_rate": 0.0015,
"loss": 2.5098538398742676,
"step": 994
},
{
"epoch": 0.1295799385275894,
"grad_norm": 0.18154442310333252,
"learning_rate": 0.0015,
"loss": 2.4638562202453613,
"step": 996
},
{
"epoch": 0.12984013920736368,
"grad_norm": 0.12289196997880936,
"learning_rate": 0.0015,
"loss": 2.472836494445801,
"step": 998
},
{
"epoch": 0.13010033988713796,
"grad_norm": 0.22473278641700745,
"learning_rate": 0.0015,
"loss": 2.4230082035064697,
"step": 1000
},
{
"epoch": 0.13036054056691224,
"grad_norm": 0.15969176590442657,
"learning_rate": 0.0015,
"loss": 2.4526515007019043,
"step": 1002
},
{
"epoch": 0.13062074124668652,
"grad_norm": 0.12065639346837997,
"learning_rate": 0.0015,
"loss": 2.5058422088623047,
"step": 1004
},
{
"epoch": 0.13088094192646077,
"grad_norm": 0.1982503980398178,
"learning_rate": 0.0015,
"loss": 2.3470046520233154,
"step": 1006
},
{
"epoch": 0.13114114260623505,
"grad_norm": 0.11025986820459366,
"learning_rate": 0.0015,
"loss": 2.427471160888672,
"step": 1008
},
{
"epoch": 0.13140134328600933,
"grad_norm": 0.1502007246017456,
"learning_rate": 0.0015,
"loss": 2.4024569988250732,
"step": 1010
},
{
"epoch": 0.1316615439657836,
"grad_norm": 0.1308867335319519,
"learning_rate": 0.0015,
"loss": 2.429893970489502,
"step": 1012
},
{
"epoch": 0.1319217446455579,
"grad_norm": 0.13172170519828796,
"learning_rate": 0.0015,
"loss": 2.460587501525879,
"step": 1014
},
{
"epoch": 0.13218194532533217,
"grad_norm": 0.1112113669514656,
"learning_rate": 0.0015,
"loss": 2.452357292175293,
"step": 1016
},
{
"epoch": 0.13244214600510643,
"grad_norm": 0.10093437135219574,
"learning_rate": 0.0015,
"loss": 2.4399003982543945,
"step": 1018
},
{
"epoch": 0.1327023466848807,
"grad_norm": 0.1351321041584015,
"learning_rate": 0.0015,
"loss": 2.5169358253479004,
"step": 1020
},
{
"epoch": 0.132962547364655,
"grad_norm": 0.10677681118249893,
"learning_rate": 0.0015,
"loss": 2.4662139415740967,
"step": 1022
},
{
"epoch": 0.13322274804442927,
"grad_norm": 0.09946724027395248,
"learning_rate": 0.0015,
"loss": 2.460554599761963,
"step": 1024
},
{
"epoch": 0.13348294872420355,
"grad_norm": 0.14991725981235504,
"learning_rate": 0.0015,
"loss": 2.4160876274108887,
"step": 1026
},
{
"epoch": 0.13374314940397783,
"grad_norm": 0.11871107667684555,
"learning_rate": 0.0015,
"loss": 2.395324230194092,
"step": 1028
},
{
"epoch": 0.13400335008375208,
"grad_norm": 0.11057759076356888,
"learning_rate": 0.0015,
"loss": 2.472972869873047,
"step": 1030
},
{
"epoch": 0.13426355076352636,
"grad_norm": 0.16956132650375366,
"learning_rate": 0.0015,
"loss": 2.5264644622802734,
"step": 1032
},
{
"epoch": 0.13452375144330064,
"grad_norm": 0.11181381344795227,
"learning_rate": 0.0015,
"loss": 2.468268394470215,
"step": 1034
},
{
"epoch": 0.13478395212307492,
"grad_norm": 0.13414572179317474,
"learning_rate": 0.0015,
"loss": 2.362654447555542,
"step": 1036
},
{
"epoch": 0.1350441528028492,
"grad_norm": 0.24919535219669342,
"learning_rate": 0.0015,
"loss": 2.483491897583008,
"step": 1038
},
{
"epoch": 0.13530435348262349,
"grad_norm": 0.10450753569602966,
"learning_rate": 0.0015,
"loss": 2.523620128631592,
"step": 1040
},
{
"epoch": 0.13556455416239774,
"grad_norm": 0.2184949815273285,
"learning_rate": 0.0015,
"loss": 2.386420249938965,
"step": 1042
},
{
"epoch": 0.13582475484217202,
"grad_norm": 0.17390845715999603,
"learning_rate": 0.0015,
"loss": 2.4747018814086914,
"step": 1044
},
{
"epoch": 0.1360849555219463,
"grad_norm": 0.1654224693775177,
"learning_rate": 0.0015,
"loss": 2.5035622119903564,
"step": 1046
},
{
"epoch": 0.13634515620172058,
"grad_norm": 0.14311206340789795,
"learning_rate": 0.0015,
"loss": 2.499642848968506,
"step": 1048
},
{
"epoch": 0.13660535688149486,
"grad_norm": 0.19418315589427948,
"learning_rate": 0.0015,
"loss": 2.4356093406677246,
"step": 1050
},
{
"epoch": 0.13686555756126914,
"grad_norm": 0.12149766087532043,
"learning_rate": 0.0015,
"loss": 2.5009753704071045,
"step": 1052
},
{
"epoch": 0.1371257582410434,
"grad_norm": 0.12303480505943298,
"learning_rate": 0.0015,
"loss": 2.4662513732910156,
"step": 1054
},
{
"epoch": 0.13738595892081767,
"grad_norm": 0.2106712907552719,
"learning_rate": 0.0015,
"loss": 2.441244602203369,
"step": 1056
},
{
"epoch": 0.13764615960059196,
"grad_norm": 0.1418542116880417,
"learning_rate": 0.0015,
"loss": 2.5022647380828857,
"step": 1058
},
{
"epoch": 0.13790636028036624,
"grad_norm": 0.16257698833942413,
"learning_rate": 0.0015,
"loss": 2.45245361328125,
"step": 1060
},
{
"epoch": 0.13816656096014052,
"grad_norm": 0.17792272567749023,
"learning_rate": 0.0015,
"loss": 2.4715757369995117,
"step": 1062
},
{
"epoch": 0.1384267616399148,
"grad_norm": 0.1103525310754776,
"learning_rate": 0.0015,
"loss": 2.407827377319336,
"step": 1064
},
{
"epoch": 0.13868696231968905,
"grad_norm": 0.17640429735183716,
"learning_rate": 0.0015,
"loss": 2.4953856468200684,
"step": 1066
},
{
"epoch": 0.13894716299946333,
"grad_norm": 0.22436165809631348,
"learning_rate": 0.0015,
"loss": 2.515901565551758,
"step": 1068
},
{
"epoch": 0.1392073636792376,
"grad_norm": 0.1928934007883072,
"learning_rate": 0.0015,
"loss": 2.436163902282715,
"step": 1070
},
{
"epoch": 0.1394675643590119,
"grad_norm": 0.12063254415988922,
"learning_rate": 0.0015,
"loss": 2.388546943664551,
"step": 1072
},
{
"epoch": 0.13972776503878617,
"grad_norm": 0.13112172484397888,
"learning_rate": 0.0015,
"loss": 2.4899964332580566,
"step": 1074
},
{
"epoch": 0.13998796571856045,
"grad_norm": 0.11329298466444016,
"learning_rate": 0.0015,
"loss": 2.474388837814331,
"step": 1076
},
{
"epoch": 0.1402481663983347,
"grad_norm": 0.09997786581516266,
"learning_rate": 0.0015,
"loss": 2.440237045288086,
"step": 1078
},
{
"epoch": 0.140508367078109,
"grad_norm": 0.16203705966472626,
"learning_rate": 0.0015,
"loss": 2.4485199451446533,
"step": 1080
},
{
"epoch": 0.14076856775788327,
"grad_norm": 0.1024545356631279,
"learning_rate": 0.0015,
"loss": 2.4308876991271973,
"step": 1082
},
{
"epoch": 0.14102876843765755,
"grad_norm": 0.12663713097572327,
"learning_rate": 0.0015,
"loss": 2.4554238319396973,
"step": 1084
},
{
"epoch": 0.14128896911743183,
"grad_norm": 0.17677250504493713,
"learning_rate": 0.0015,
"loss": 2.507059097290039,
"step": 1086
},
{
"epoch": 0.14154916979720608,
"grad_norm": 0.11777018010616302,
"learning_rate": 0.0015,
"loss": 2.4577083587646484,
"step": 1088
},
{
"epoch": 0.14180937047698036,
"grad_norm": 0.1278468370437622,
"learning_rate": 0.0015,
"loss": 2.445704460144043,
"step": 1090
},
{
"epoch": 0.14206957115675464,
"grad_norm": 0.13680873811244965,
"learning_rate": 0.0015,
"loss": 2.413355827331543,
"step": 1092
},
{
"epoch": 0.14232977183652892,
"grad_norm": 0.11125652492046356,
"learning_rate": 0.0015,
"loss": 2.4675405025482178,
"step": 1094
},
{
"epoch": 0.1425899725163032,
"grad_norm": 0.11100263893604279,
"learning_rate": 0.0015,
"loss": 2.3913791179656982,
"step": 1096
},
{
"epoch": 0.14285017319607748,
"grad_norm": 0.11483151465654373,
"learning_rate": 0.0015,
"loss": 2.3454768657684326,
"step": 1098
},
{
"epoch": 0.14311037387585174,
"grad_norm": 0.10911301523447037,
"learning_rate": 0.0015,
"loss": 2.4192733764648438,
"step": 1100
},
{
"epoch": 0.14337057455562602,
"grad_norm": 0.1157718300819397,
"learning_rate": 0.0015,
"loss": 2.465139150619507,
"step": 1102
},
{
"epoch": 0.1436307752354003,
"grad_norm": 0.11563188582658768,
"learning_rate": 0.0015,
"loss": 2.4586434364318848,
"step": 1104
},
{
"epoch": 0.14389097591517458,
"grad_norm": 0.11557405441999435,
"learning_rate": 0.0015,
"loss": 2.4535820484161377,
"step": 1106
},
{
"epoch": 0.14415117659494886,
"grad_norm": 0.12103701382875443,
"learning_rate": 0.0015,
"loss": 2.3909735679626465,
"step": 1108
},
{
"epoch": 0.14441137727472314,
"grad_norm": 0.18862950801849365,
"learning_rate": 0.0015,
"loss": 2.3988637924194336,
"step": 1110
},
{
"epoch": 0.1446715779544974,
"grad_norm": 0.17689956724643707,
"learning_rate": 0.0015,
"loss": 2.38931941986084,
"step": 1112
},
{
"epoch": 0.14493177863427167,
"grad_norm": 0.22612197697162628,
"learning_rate": 0.0015,
"loss": 2.3580808639526367,
"step": 1114
},
{
"epoch": 0.14519197931404595,
"grad_norm": 0.12673230469226837,
"learning_rate": 0.0015,
"loss": 2.442720413208008,
"step": 1116
},
{
"epoch": 0.14545217999382024,
"grad_norm": 0.17612653970718384,
"learning_rate": 0.0015,
"loss": 2.463355779647827,
"step": 1118
},
{
"epoch": 0.14571238067359452,
"grad_norm": 0.12333007901906967,
"learning_rate": 0.0015,
"loss": 2.380070209503174,
"step": 1120
},
{
"epoch": 0.1459725813533688,
"grad_norm": 0.1020858958363533,
"learning_rate": 0.0015,
"loss": 2.4536514282226562,
"step": 1122
},
{
"epoch": 0.14623278203314305,
"grad_norm": 0.32838383316993713,
"learning_rate": 0.0015,
"loss": 2.4055564403533936,
"step": 1124
},
{
"epoch": 0.14649298271291733,
"grad_norm": 0.19968973100185394,
"learning_rate": 0.0015,
"loss": 2.4536662101745605,
"step": 1126
},
{
"epoch": 0.1467531833926916,
"grad_norm": 0.18876910209655762,
"learning_rate": 0.0015,
"loss": 2.4924776554107666,
"step": 1128
},
{
"epoch": 0.1470133840724659,
"grad_norm": 0.1943730115890503,
"learning_rate": 0.0015,
"loss": 2.4222571849823,
"step": 1130
},
{
"epoch": 0.14727358475224017,
"grad_norm": 0.18540358543395996,
"learning_rate": 0.0015,
"loss": 2.411162853240967,
"step": 1132
},
{
"epoch": 0.14753378543201445,
"grad_norm": 0.17939861118793488,
"learning_rate": 0.0015,
"loss": 2.4838457107543945,
"step": 1134
},
{
"epoch": 0.1477939861117887,
"grad_norm": 0.1577775776386261,
"learning_rate": 0.0015,
"loss": 2.4425199031829834,
"step": 1136
},
{
"epoch": 0.14805418679156299,
"grad_norm": 0.23459453880786896,
"learning_rate": 0.0015,
"loss": 2.5058655738830566,
"step": 1138
},
{
"epoch": 0.14831438747133727,
"grad_norm": 0.14127010107040405,
"learning_rate": 0.0015,
"loss": 2.405430793762207,
"step": 1140
},
{
"epoch": 0.14857458815111155,
"grad_norm": 0.13933320343494415,
"learning_rate": 0.0015,
"loss": 2.4516453742980957,
"step": 1142
},
{
"epoch": 0.14883478883088583,
"grad_norm": 0.12083790451288223,
"learning_rate": 0.0015,
"loss": 2.441802501678467,
"step": 1144
},
{
"epoch": 0.1490949895106601,
"grad_norm": 0.11597343534231186,
"learning_rate": 0.0015,
"loss": 2.44309663772583,
"step": 1146
},
{
"epoch": 0.14935519019043436,
"grad_norm": 0.11108209192752838,
"learning_rate": 0.0015,
"loss": 2.4176034927368164,
"step": 1148
},
{
"epoch": 0.14961539087020864,
"grad_norm": 0.12201856821775436,
"learning_rate": 0.0015,
"loss": 2.441558361053467,
"step": 1150
},
{
"epoch": 0.14987559154998292,
"grad_norm": 0.13071376085281372,
"learning_rate": 0.0015,
"loss": 2.429281711578369,
"step": 1152
},
{
"epoch": 0.1501357922297572,
"grad_norm": 0.11141698807477951,
"learning_rate": 0.0015,
"loss": 2.4551773071289062,
"step": 1154
},
{
"epoch": 0.15039599290953148,
"grad_norm": 0.11565087735652924,
"learning_rate": 0.0015,
"loss": 2.3742003440856934,
"step": 1156
},
{
"epoch": 0.15065619358930576,
"grad_norm": 0.10863198339939117,
"learning_rate": 0.0015,
"loss": 2.3950302600860596,
"step": 1158
},
{
"epoch": 0.15091639426908002,
"grad_norm": 0.17658548057079315,
"learning_rate": 0.0015,
"loss": 2.4297618865966797,
"step": 1160
},
{
"epoch": 0.1511765949488543,
"grad_norm": 0.11242704093456268,
"learning_rate": 0.0015,
"loss": 2.4334096908569336,
"step": 1162
},
{
"epoch": 0.15143679562862858,
"grad_norm": 0.23384493589401245,
"learning_rate": 0.0015,
"loss": 2.4612202644348145,
"step": 1164
},
{
"epoch": 0.15169699630840286,
"grad_norm": 0.13724996149539948,
"learning_rate": 0.0015,
"loss": 2.4340977668762207,
"step": 1166
},
{
"epoch": 0.15195719698817714,
"grad_norm": 0.12144450843334198,
"learning_rate": 0.0015,
"loss": 2.5139427185058594,
"step": 1168
},
{
"epoch": 0.15221739766795142,
"grad_norm": 0.11372646689414978,
"learning_rate": 0.0015,
"loss": 2.4092471599578857,
"step": 1170
},
{
"epoch": 0.15247759834772567,
"grad_norm": 0.11893589049577713,
"learning_rate": 0.0015,
"loss": 2.365037441253662,
"step": 1172
},
{
"epoch": 0.15273779902749995,
"grad_norm": 0.1765247881412506,
"learning_rate": 0.0015,
"loss": 2.5289974212646484,
"step": 1174
},
{
"epoch": 0.15299799970727423,
"grad_norm": 0.19714157283306122,
"learning_rate": 0.0015,
"loss": 2.4510278701782227,
"step": 1176
},
{
"epoch": 0.15325820038704852,
"grad_norm": 0.1067543625831604,
"learning_rate": 0.0015,
"loss": 2.4470250606536865,
"step": 1178
},
{
"epoch": 0.1535184010668228,
"grad_norm": 0.12346280366182327,
"learning_rate": 0.0015,
"loss": 2.4941210746765137,
"step": 1180
},
{
"epoch": 0.15377860174659708,
"grad_norm": 0.17956458032131195,
"learning_rate": 0.0015,
"loss": 2.3808820247650146,
"step": 1182
},
{
"epoch": 0.15403880242637133,
"grad_norm": 0.11279787123203278,
"learning_rate": 0.0015,
"loss": 2.402820110321045,
"step": 1184
},
{
"epoch": 0.1542990031061456,
"grad_norm": 0.1782272905111313,
"learning_rate": 0.0015,
"loss": 2.454741954803467,
"step": 1186
},
{
"epoch": 0.1545592037859199,
"grad_norm": 0.14567869901657104,
"learning_rate": 0.0015,
"loss": 2.387033700942993,
"step": 1188
},
{
"epoch": 0.15481940446569417,
"grad_norm": 0.13391685485839844,
"learning_rate": 0.0015,
"loss": 2.4758825302124023,
"step": 1190
},
{
"epoch": 0.15507960514546845,
"grad_norm": 0.15669213235378265,
"learning_rate": 0.0015,
"loss": 2.4722981452941895,
"step": 1192
},
{
"epoch": 0.1553398058252427,
"grad_norm": 0.12036886811256409,
"learning_rate": 0.0015,
"loss": 2.3432040214538574,
"step": 1194
},
{
"epoch": 0.15560000650501699,
"grad_norm": 0.11269272118806839,
"learning_rate": 0.0015,
"loss": 2.4520320892333984,
"step": 1196
},
{
"epoch": 0.15586020718479127,
"grad_norm": 0.10365239530801773,
"learning_rate": 0.0015,
"loss": 2.447770595550537,
"step": 1198
},
{
"epoch": 0.15612040786456555,
"grad_norm": 0.14448872208595276,
"learning_rate": 0.0015,
"loss": 2.4342339038848877,
"step": 1200
},
{
"epoch": 0.15638060854433983,
"grad_norm": 0.1512068510055542,
"learning_rate": 0.0015,
"loss": 2.44174861907959,
"step": 1202
},
{
"epoch": 0.1566408092241141,
"grad_norm": 0.11856794357299805,
"learning_rate": 0.0015,
"loss": 2.462867498397827,
"step": 1204
},
{
"epoch": 0.15690100990388836,
"grad_norm": 0.15060612559318542,
"learning_rate": 0.0015,
"loss": 2.444382429122925,
"step": 1206
},
{
"epoch": 0.15716121058366264,
"grad_norm": 0.1236223429441452,
"learning_rate": 0.0015,
"loss": 2.432056188583374,
"step": 1208
},
{
"epoch": 0.15742141126343692,
"grad_norm": 0.12084182351827621,
"learning_rate": 0.0015,
"loss": 2.4530110359191895,
"step": 1210
},
{
"epoch": 0.1576816119432112,
"grad_norm": 0.11235949397087097,
"learning_rate": 0.0015,
"loss": 2.417367458343506,
"step": 1212
},
{
"epoch": 0.15794181262298548,
"grad_norm": 0.10813146084547043,
"learning_rate": 0.0015,
"loss": 2.4447574615478516,
"step": 1214
},
{
"epoch": 0.15820201330275976,
"grad_norm": 0.11305201053619385,
"learning_rate": 0.0015,
"loss": 2.458041191101074,
"step": 1216
},
{
"epoch": 0.15846221398253402,
"grad_norm": 0.1399001181125641,
"learning_rate": 0.0015,
"loss": 2.3876781463623047,
"step": 1218
},
{
"epoch": 0.1587224146623083,
"grad_norm": 0.1301049292087555,
"learning_rate": 0.0015,
"loss": 2.4322681427001953,
"step": 1220
},
{
"epoch": 0.15898261534208258,
"grad_norm": 0.19871819019317627,
"learning_rate": 0.0015,
"loss": 2.3859105110168457,
"step": 1222
},
{
"epoch": 0.15924281602185686,
"grad_norm": 0.11344478279352188,
"learning_rate": 0.0015,
"loss": 2.411940813064575,
"step": 1224
},
{
"epoch": 0.15950301670163114,
"grad_norm": 0.10705609619617462,
"learning_rate": 0.0015,
"loss": 2.471545696258545,
"step": 1226
},
{
"epoch": 0.15976321738140542,
"grad_norm": 0.1352146714925766,
"learning_rate": 0.0015,
"loss": 2.4263381958007812,
"step": 1228
},
{
"epoch": 0.16002341806117967,
"grad_norm": 0.11733849346637726,
"learning_rate": 0.0015,
"loss": 2.527388572692871,
"step": 1230
},
{
"epoch": 0.16028361874095395,
"grad_norm": 0.11473846435546875,
"learning_rate": 0.0015,
"loss": 2.457369804382324,
"step": 1232
},
{
"epoch": 0.16054381942072823,
"grad_norm": 0.16299386322498322,
"learning_rate": 0.0015,
"loss": 2.4419190883636475,
"step": 1234
},
{
"epoch": 0.16080402010050251,
"grad_norm": 0.1583544909954071,
"learning_rate": 0.0015,
"loss": 2.4358086585998535,
"step": 1236
},
{
"epoch": 0.1610642207802768,
"grad_norm": 0.11408533900976181,
"learning_rate": 0.0015,
"loss": 2.431692600250244,
"step": 1238
},
{
"epoch": 0.16132442146005108,
"grad_norm": 0.24136263132095337,
"learning_rate": 0.0015,
"loss": 2.461775302886963,
"step": 1240
},
{
"epoch": 0.16158462213982533,
"grad_norm": 0.11955428868532181,
"learning_rate": 0.0015,
"loss": 2.428358793258667,
"step": 1242
},
{
"epoch": 0.1618448228195996,
"grad_norm": 0.11306291073560715,
"learning_rate": 0.0015,
"loss": 2.4026038646698,
"step": 1244
},
{
"epoch": 0.1621050234993739,
"grad_norm": 0.16501212120056152,
"learning_rate": 0.0015,
"loss": 2.4538371562957764,
"step": 1246
},
{
"epoch": 0.16236522417914817,
"grad_norm": 0.1519465297460556,
"learning_rate": 0.0015,
"loss": 2.375150203704834,
"step": 1248
},
{
"epoch": 0.16262542485892245,
"grad_norm": 0.11929146945476532,
"learning_rate": 0.0015,
"loss": 2.386366844177246,
"step": 1250
},
{
"epoch": 0.16288562553869673,
"grad_norm": 0.13667862117290497,
"learning_rate": 0.0015,
"loss": 2.4182510375976562,
"step": 1252
},
{
"epoch": 0.16314582621847099,
"grad_norm": 0.12089703977108002,
"learning_rate": 0.0015,
"loss": 2.419919013977051,
"step": 1254
},
{
"epoch": 0.16340602689824527,
"grad_norm": 0.15514126420021057,
"learning_rate": 0.0015,
"loss": 2.4567313194274902,
"step": 1256
},
{
"epoch": 0.16366622757801955,
"grad_norm": 0.11216102540493011,
"learning_rate": 0.0015,
"loss": 2.4364237785339355,
"step": 1258
},
{
"epoch": 0.16392642825779383,
"grad_norm": 0.10649251192808151,
"learning_rate": 0.0015,
"loss": 2.3996036052703857,
"step": 1260
},
{
"epoch": 0.1641866289375681,
"grad_norm": 0.10178853571414948,
"learning_rate": 0.0015,
"loss": 2.3935763835906982,
"step": 1262
},
{
"epoch": 0.1644468296173424,
"grad_norm": 0.13471631705760956,
"learning_rate": 0.0015,
"loss": 2.445880889892578,
"step": 1264
},
{
"epoch": 0.16470703029711664,
"grad_norm": 0.10506339371204376,
"learning_rate": 0.0015,
"loss": 2.4339776039123535,
"step": 1266
},
{
"epoch": 0.16496723097689092,
"grad_norm": 0.11138959228992462,
"learning_rate": 0.0015,
"loss": 2.4713330268859863,
"step": 1268
},
{
"epoch": 0.1652274316566652,
"grad_norm": 0.10945623368024826,
"learning_rate": 0.0015,
"loss": 2.402653694152832,
"step": 1270
},
{
"epoch": 0.16548763233643948,
"grad_norm": 0.10930269956588745,
"learning_rate": 0.0015,
"loss": 2.385347843170166,
"step": 1272
},
{
"epoch": 0.16574783301621376,
"grad_norm": 0.11622707545757294,
"learning_rate": 0.0015,
"loss": 2.4838743209838867,
"step": 1274
},
{
"epoch": 0.16600803369598804,
"grad_norm": 0.12191583961248398,
"learning_rate": 0.0015,
"loss": 2.361172914505005,
"step": 1276
},
{
"epoch": 0.1662682343757623,
"grad_norm": 0.12226612120866776,
"learning_rate": 0.0015,
"loss": 2.484133243560791,
"step": 1278
},
{
"epoch": 0.16652843505553658,
"grad_norm": 0.16671867668628693,
"learning_rate": 0.0015,
"loss": 2.403444290161133,
"step": 1280
},
{
"epoch": 0.16678863573531086,
"grad_norm": 0.11180184781551361,
"learning_rate": 0.0015,
"loss": 2.4213948249816895,
"step": 1282
},
{
"epoch": 0.16704883641508514,
"grad_norm": 0.14298300445079803,
"learning_rate": 0.0015,
"loss": 2.460801124572754,
"step": 1284
},
{
"epoch": 0.16730903709485942,
"grad_norm": 0.21743375062942505,
"learning_rate": 0.0015,
"loss": 2.424553394317627,
"step": 1286
},
{
"epoch": 0.16756923777463367,
"grad_norm": 0.1232086643576622,
"learning_rate": 0.0015,
"loss": 2.4497733116149902,
"step": 1288
},
{
"epoch": 0.16782943845440795,
"grad_norm": 0.11134848743677139,
"learning_rate": 0.0015,
"loss": 2.403141498565674,
"step": 1290
},
{
"epoch": 0.16808963913418223,
"grad_norm": 0.15922418236732483,
"learning_rate": 0.0015,
"loss": 2.3140456676483154,
"step": 1292
},
{
"epoch": 0.16834983981395651,
"grad_norm": 0.1884986311197281,
"learning_rate": 0.0015,
"loss": 2.4354138374328613,
"step": 1294
},
{
"epoch": 0.1686100404937308,
"grad_norm": 0.11944177746772766,
"learning_rate": 0.0015,
"loss": 2.427903652191162,
"step": 1296
},
{
"epoch": 0.16887024117350508,
"grad_norm": 0.2099335789680481,
"learning_rate": 0.0015,
"loss": 2.5288753509521484,
"step": 1298
},
{
"epoch": 0.16913044185327933,
"grad_norm": 0.108861044049263,
"learning_rate": 0.0015,
"loss": 2.431715488433838,
"step": 1300
},
{
"epoch": 0.1693906425330536,
"grad_norm": 0.1470099240541458,
"learning_rate": 0.0015,
"loss": 2.455397367477417,
"step": 1302
},
{
"epoch": 0.1696508432128279,
"grad_norm": 0.10982918739318848,
"learning_rate": 0.0015,
"loss": 2.4648571014404297,
"step": 1304
},
{
"epoch": 0.16991104389260217,
"grad_norm": 0.18002374470233917,
"learning_rate": 0.0015,
"loss": 2.3659491539001465,
"step": 1306
},
{
"epoch": 0.17017124457237645,
"grad_norm": 0.11057405173778534,
"learning_rate": 0.0015,
"loss": 2.4196794033050537,
"step": 1308
},
{
"epoch": 0.17043144525215073,
"grad_norm": 0.11353861540555954,
"learning_rate": 0.0015,
"loss": 2.393937587738037,
"step": 1310
},
{
"epoch": 0.17069164593192498,
"grad_norm": 0.11239606887102127,
"learning_rate": 0.0015,
"loss": 2.359034538269043,
"step": 1312
},
{
"epoch": 0.17095184661169927,
"grad_norm": 0.14231309294700623,
"learning_rate": 0.0015,
"loss": 2.4108057022094727,
"step": 1314
},
{
"epoch": 0.17121204729147355,
"grad_norm": 0.19448791444301605,
"learning_rate": 0.0015,
"loss": 2.477170944213867,
"step": 1316
},
{
"epoch": 0.17147224797124783,
"grad_norm": 0.1748061627149582,
"learning_rate": 0.0015,
"loss": 2.4192404747009277,
"step": 1318
},
{
"epoch": 0.1717324486510221,
"grad_norm": 0.13385999202728271,
"learning_rate": 0.0015,
"loss": 2.45928692817688,
"step": 1320
},
{
"epoch": 0.1719926493307964,
"grad_norm": 0.09599027782678604,
"learning_rate": 0.0015,
"loss": 2.411952018737793,
"step": 1322
},
{
"epoch": 0.17225285001057064,
"grad_norm": 0.19161750376224518,
"learning_rate": 0.0015,
"loss": 2.405963182449341,
"step": 1324
},
{
"epoch": 0.17251305069034492,
"grad_norm": 0.13632002472877502,
"learning_rate": 0.0015,
"loss": 2.405630588531494,
"step": 1326
},
{
"epoch": 0.1727732513701192,
"grad_norm": 0.10875320434570312,
"learning_rate": 0.0015,
"loss": 2.400637626647949,
"step": 1328
},
{
"epoch": 0.17303345204989348,
"grad_norm": 0.1277407705783844,
"learning_rate": 0.0015,
"loss": 2.497649908065796,
"step": 1330
},
{
"epoch": 0.17329365272966776,
"grad_norm": 0.11995089799165726,
"learning_rate": 0.0015,
"loss": 2.36509108543396,
"step": 1332
},
{
"epoch": 0.17355385340944204,
"grad_norm": 0.1417117416858673,
"learning_rate": 0.0015,
"loss": 2.41786527633667,
"step": 1334
},
{
"epoch": 0.1738140540892163,
"grad_norm": 0.12198492139577866,
"learning_rate": 0.0015,
"loss": 2.42653226852417,
"step": 1336
},
{
"epoch": 0.17407425476899058,
"grad_norm": 0.16528841853141785,
"learning_rate": 0.0015,
"loss": 2.440850257873535,
"step": 1338
},
{
"epoch": 0.17433445544876486,
"grad_norm": 0.10439668595790863,
"learning_rate": 0.0015,
"loss": 2.2864136695861816,
"step": 1340
},
{
"epoch": 0.17459465612853914,
"grad_norm": 0.10300511121749878,
"learning_rate": 0.0015,
"loss": 2.3731436729431152,
"step": 1342
},
{
"epoch": 0.17485485680831342,
"grad_norm": 0.18186108767986298,
"learning_rate": 0.0015,
"loss": 2.388641357421875,
"step": 1344
},
{
"epoch": 0.1751150574880877,
"grad_norm": 0.10545193403959274,
"learning_rate": 0.0015,
"loss": 2.323863983154297,
"step": 1346
},
{
"epoch": 0.17537525816786195,
"grad_norm": 0.10705488920211792,
"learning_rate": 0.0015,
"loss": 2.488503932952881,
"step": 1348
},
{
"epoch": 0.17563545884763623,
"grad_norm": 0.11458684504032135,
"learning_rate": 0.0015,
"loss": 2.4604709148406982,
"step": 1350
},
{
"epoch": 0.17589565952741051,
"grad_norm": 0.11846322566270828,
"learning_rate": 0.0015,
"loss": 2.4203875064849854,
"step": 1352
},
{
"epoch": 0.1761558602071848,
"grad_norm": 0.10294774919748306,
"learning_rate": 0.0015,
"loss": 2.4126439094543457,
"step": 1354
},
{
"epoch": 0.17641606088695908,
"grad_norm": 0.11134915053844452,
"learning_rate": 0.0015,
"loss": 2.372790813446045,
"step": 1356
},
{
"epoch": 0.17667626156673336,
"grad_norm": 0.15922658145427704,
"learning_rate": 0.0015,
"loss": 2.4994258880615234,
"step": 1358
},
{
"epoch": 0.1769364622465076,
"grad_norm": 0.10634514689445496,
"learning_rate": 0.0015,
"loss": 2.4253621101379395,
"step": 1360
},
{
"epoch": 0.1771966629262819,
"grad_norm": 0.19085898995399475,
"learning_rate": 0.0015,
"loss": 2.5060479640960693,
"step": 1362
},
{
"epoch": 0.17745686360605617,
"grad_norm": 0.1864626705646515,
"learning_rate": 0.0015,
"loss": 2.4373955726623535,
"step": 1364
},
{
"epoch": 0.17771706428583045,
"grad_norm": 0.12415165454149246,
"learning_rate": 0.0015,
"loss": 2.433816909790039,
"step": 1366
},
{
"epoch": 0.17797726496560473,
"grad_norm": 0.1111738458275795,
"learning_rate": 0.0015,
"loss": 2.4260969161987305,
"step": 1368
},
{
"epoch": 0.178237465645379,
"grad_norm": 0.13230733573436737,
"learning_rate": 0.0015,
"loss": 2.432861804962158,
"step": 1370
},
{
"epoch": 0.17849766632515326,
"grad_norm": 0.13344313204288483,
"learning_rate": 0.0015,
"loss": 2.3097424507141113,
"step": 1372
},
{
"epoch": 0.17875786700492755,
"grad_norm": 0.11272049695253372,
"learning_rate": 0.0015,
"loss": 2.4169774055480957,
"step": 1374
},
{
"epoch": 0.17901806768470183,
"grad_norm": 0.14284023642539978,
"learning_rate": 0.0015,
"loss": 2.421970844268799,
"step": 1376
},
{
"epoch": 0.1792782683644761,
"grad_norm": 0.13425251841545105,
"learning_rate": 0.0015,
"loss": 2.4190189838409424,
"step": 1378
},
{
"epoch": 0.1795384690442504,
"grad_norm": 0.10962817072868347,
"learning_rate": 0.0015,
"loss": 2.4182591438293457,
"step": 1380
},
{
"epoch": 0.17979866972402467,
"grad_norm": 0.12920773029327393,
"learning_rate": 0.0015,
"loss": 2.424931526184082,
"step": 1382
},
{
"epoch": 0.18005887040379892,
"grad_norm": 0.15149635076522827,
"learning_rate": 0.0015,
"loss": 2.4042811393737793,
"step": 1384
}
],
"logging_steps": 2,
"max_steps": 6919,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1384,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.971626564799693e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}