{
  "best_global_step": 13992,
  "best_metric": 3.7217817306518555,
  "best_model_checkpoint": "sindhibert_session2/checkpoint-13992",
  "epoch": 2.748397868735728,
  "eval_steps": 1272,
  "global_step": 13992,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019642988680727773,
      "grad_norm": 16.122173309326172,
      "learning_rate": 9.900000000000002e-06,
      "loss": 36.5051904296875,
      "step": 100
    },
    {
      "epoch": 0.039285977361455546,
      "grad_norm": 18.11626434326172,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 36.368505859375,
      "step": 200
    },
    {
      "epoch": 0.05892896604218332,
      "grad_norm": 18.927509307861328,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 36.45832275390625,
      "step": 300
    },
    {
      "epoch": 0.07857195472291109,
      "grad_norm": 18.480167388916016,
      "learning_rate": 3.99e-05,
      "loss": 36.31460693359375,
      "step": 400
    },
    {
      "epoch": 0.09821494340363886,
      "grad_norm": 19.010652542114258,
      "learning_rate": 4.99e-05,
      "loss": 36.24136962890625,
      "step": 500
    },
    {
      "epoch": 0.11785793208436664,
      "grad_norm": 19.11362075805664,
      "learning_rate": 4.966492926284438e-05,
      "loss": 36.54402587890625,
      "step": 600
    },
    {
      "epoch": 0.1375009207650944,
      "grad_norm": 19.41926383972168,
      "learning_rate": 4.93264739727882e-05,
      "loss": 36.28423095703125,
      "step": 700
    },
    {
      "epoch": 0.15714390944582218,
      "grad_norm": 20.20358657836914,
      "learning_rate": 4.898801868273201e-05,
      "loss": 36.2180615234375,
      "step": 800
    },
    {
      "epoch": 0.17678689812654996,
      "grad_norm": 18.598957061767578,
      "learning_rate": 4.864956339267583e-05,
      "loss": 36.1883984375,
      "step": 900
    },
    {
      "epoch": 0.19642988680727771,
      "grad_norm": 18.320087432861328,
      "learning_rate": 4.831110810261965e-05,
      "loss": 36.0933837890625,
      "step": 1000
    },
    {
      "epoch": 0.2160728754880055,
      "grad_norm": 21.353364944458008,
      "learning_rate": 4.797265281256346e-05,
      "loss": 35.95175048828125,
      "step": 1100
    },
    {
      "epoch": 0.23571586416873327,
      "grad_norm": 19.709365844726562,
      "learning_rate": 4.763419752250728e-05,
      "loss": 35.99169921875,
      "step": 1200
    },
    {
      "epoch": 0.24985881601885726,
      "eval_loss": 4.386976718902588,
      "eval_runtime": 41.9212,
      "eval_samples_per_second": 477.086,
      "eval_steps_per_second": 14.909,
      "step": 1272
    },
    {
      "epoch": 0.255358852849461,
      "grad_norm": 17.78667449951172,
      "learning_rate": 4.729574223245109e-05,
      "loss": 35.86061279296875,
      "step": 1300
    },
    {
      "epoch": 0.2750018415301888,
      "grad_norm": 21.036474227905273,
      "learning_rate": 4.695728694239491e-05,
      "loss": 35.78255859375,
      "step": 1400
    },
    {
      "epoch": 0.2946448302109166,
      "grad_norm": 19.002052307128906,
      "learning_rate": 4.661883165233873e-05,
      "loss": 35.5993408203125,
      "step": 1500
    },
    {
      "epoch": 0.31428781889164437,
      "grad_norm": 19.828800201416016,
      "learning_rate": 4.6280376362282543e-05,
      "loss": 35.70918701171875,
      "step": 1600
    },
    {
      "epoch": 0.33393080757237215,
      "grad_norm": 17.12042236328125,
      "learning_rate": 4.594192107222636e-05,
      "loss": 35.58583251953125,
      "step": 1700
    },
    {
      "epoch": 0.3535737962530999,
      "grad_norm": 19.869712829589844,
      "learning_rate": 4.560346578217018e-05,
      "loss": 35.3600537109375,
      "step": 1800
    },
    {
      "epoch": 0.3732167849338277,
      "grad_norm": 18.914470672607422,
      "learning_rate": 4.5265010492113994e-05,
      "loss": 35.34132080078125,
      "step": 1900
    },
    {
      "epoch": 0.39285977361455543,
      "grad_norm": 18.888940811157227,
      "learning_rate": 4.4926555202057814e-05,
      "loss": 35.33590576171875,
      "step": 2000
    },
    {
      "epoch": 0.4125027622952832,
      "grad_norm": 20.27227783203125,
      "learning_rate": 4.4588099912001626e-05,
      "loss": 35.22805908203125,
      "step": 2100
    },
    {
      "epoch": 0.432145750976011,
      "grad_norm": 15.550501823425293,
      "learning_rate": 4.424964462194544e-05,
      "loss": 35.256953125,
      "step": 2200
    },
    {
      "epoch": 0.45178873965673877,
      "grad_norm": 17.671451568603516,
      "learning_rate": 4.391118933188926e-05,
      "loss": 35.056826171875,
      "step": 2300
    },
    {
      "epoch": 0.47143172833746655,
      "grad_norm": 18.74838638305664,
      "learning_rate": 4.357273404183308e-05,
      "loss": 34.9271826171875,
      "step": 2400
    },
    {
      "epoch": 0.49107471701819433,
      "grad_norm": 20.912931442260742,
      "learning_rate": 4.323427875177689e-05,
      "loss": 34.793916015625,
      "step": 2500
    },
    {
      "epoch": 0.4997176320377145,
      "eval_loss": 4.270185947418213,
      "eval_runtime": 41.8695,
      "eval_samples_per_second": 477.675,
      "eval_steps_per_second": 14.927,
      "step": 2544
    },
    {
      "epoch": 0.510717705698922,
      "grad_norm": 18.11321258544922,
      "learning_rate": 4.289582346172071e-05,
      "loss": 34.97314453125,
      "step": 2600
    },
    {
      "epoch": 0.5303606943796498,
      "grad_norm": 19.38896942138672,
      "learning_rate": 4.255736817166453e-05,
      "loss": 34.873974609375,
      "step": 2700
    },
    {
      "epoch": 0.5500036830603776,
      "grad_norm": 19.479278564453125,
      "learning_rate": 4.221891288160834e-05,
      "loss": 34.713251953125,
      "step": 2800
    },
    {
      "epoch": 0.5696466717411054,
      "grad_norm": 19.849210739135742,
      "learning_rate": 4.188045759155216e-05,
      "loss": 34.66454833984375,
      "step": 2900
    },
    {
      "epoch": 0.5892896604218332,
      "grad_norm": 19.59630012512207,
      "learning_rate": 4.154200230149597e-05,
      "loss": 34.546259765625,
      "step": 3000
    },
    {
      "epoch": 0.608932649102561,
      "grad_norm": 18.32138442993164,
      "learning_rate": 4.120354701143979e-05,
      "loss": 34.460576171875,
      "step": 3100
    },
    {
      "epoch": 0.6285756377832887,
      "grad_norm": 17.825464248657227,
      "learning_rate": 4.086509172138361e-05,
      "loss": 34.3186962890625,
      "step": 3200
    },
    {
      "epoch": 0.6482186264640165,
      "grad_norm": 19.180105209350586,
      "learning_rate": 4.052663643132742e-05,
      "loss": 34.40132080078125,
      "step": 3300
    },
    {
      "epoch": 0.6678616151447443,
      "grad_norm": 18.498641967773438,
      "learning_rate": 4.018818114127124e-05,
      "loss": 34.2248828125,
      "step": 3400
    },
    {
      "epoch": 0.6875046038254721,
      "grad_norm": 19.08323097229004,
      "learning_rate": 3.984972585121506e-05,
      "loss": 33.97822265625,
      "step": 3500
    },
    {
      "epoch": 0.7071475925061999,
      "grad_norm": 20.13410758972168,
      "learning_rate": 3.9511270561158874e-05,
      "loss": 34.1056494140625,
      "step": 3600
    },
    {
      "epoch": 0.7267905811869276,
      "grad_norm": 18.82459259033203,
      "learning_rate": 3.917281527110269e-05,
      "loss": 34.2245947265625,
      "step": 3700
    },
    {
      "epoch": 0.7464335698676554,
      "grad_norm": 17.352100372314453,
      "learning_rate": 3.8834359981046505e-05,
      "loss": 34.04242919921875,
      "step": 3800
    },
    {
      "epoch": 0.7495764480565718,
      "eval_loss": 4.178581237792969,
      "eval_runtime": 42.0642,
      "eval_samples_per_second": 475.463,
      "eval_steps_per_second": 14.858,
      "step": 3816
    },
    {
      "epoch": 0.7660765585483832,
      "grad_norm": 19.103435516357422,
      "learning_rate": 3.849590469099032e-05,
      "loss": 34.01751708984375,
      "step": 3900
    },
    {
      "epoch": 0.7857195472291109,
      "grad_norm": 18.045913696289062,
      "learning_rate": 3.815744940093414e-05,
      "loss": 33.90669921875,
      "step": 4000
    },
    {
      "epoch": 0.8053625359098386,
      "grad_norm": 18.76168441772461,
      "learning_rate": 3.7818994110877956e-05,
      "loss": 33.872587890625,
      "step": 4100
    },
    {
      "epoch": 0.8250055245905664,
      "grad_norm": 16.547574996948242,
      "learning_rate": 3.748053882082177e-05,
      "loss": 33.8643359375,
      "step": 4200
    },
    {
      "epoch": 0.8446485132712942,
      "grad_norm": 18.636455535888672,
      "learning_rate": 3.714208353076559e-05,
      "loss": 33.7685595703125,
      "step": 4300
    },
    {
      "epoch": 0.864291501952022,
      "grad_norm": 18.742900848388672,
      "learning_rate": 3.68036282407094e-05,
      "loss": 33.53510009765625,
      "step": 4400
    },
    {
      "epoch": 0.8839344906327498,
      "grad_norm": 20.976703643798828,
      "learning_rate": 3.646517295065322e-05,
      "loss": 33.42730224609375,
      "step": 4500
    },
    {
      "epoch": 0.9035774793134775,
      "grad_norm": 18.552316665649414,
      "learning_rate": 3.612671766059704e-05,
      "loss": 33.53127197265625,
      "step": 4600
    },
    {
      "epoch": 0.9232204679942053,
      "grad_norm": 21.41478157043457,
      "learning_rate": 3.578826237054085e-05,
      "loss": 33.41383544921875,
      "step": 4700
    },
    {
      "epoch": 0.9428634566749331,
      "grad_norm": 19.785966873168945,
      "learning_rate": 3.544980708048467e-05,
      "loss": 33.38103271484375,
      "step": 4800
    },
    {
      "epoch": 0.9625064453556609,
      "grad_norm": 17.69455337524414,
      "learning_rate": 3.511135179042849e-05,
      "loss": 33.4733447265625,
      "step": 4900
    },
    {
      "epoch": 0.9821494340363887,
      "grad_norm": 20.246673583984375,
      "learning_rate": 3.47728965003723e-05,
      "loss": 33.4089208984375,
      "step": 5000
    },
    {
      "epoch": 0.999435264075429,
      "eval_loss": 4.0612263679504395,
      "eval_runtime": 42.4302,
      "eval_samples_per_second": 471.362,
      "eval_steps_per_second": 14.73,
      "step": 5088
    },
    {
      "epoch": 1.0017678689812655,
      "grad_norm": 19.691932678222656,
      "learning_rate": 3.443444121031612e-05,
      "loss": 33.1838037109375,
      "step": 5100
    },
    {
      "epoch": 1.0214108576619934,
      "grad_norm": 18.13388442993164,
      "learning_rate": 3.409598592025994e-05,
      "loss": 33.21130859375,
      "step": 5200
    },
    {
      "epoch": 1.041053846342721,
      "grad_norm": 18.41756248474121,
      "learning_rate": 3.375753063020375e-05,
      "loss": 33.07806396484375,
      "step": 5300
    },
    {
      "epoch": 1.060696835023449,
      "grad_norm": 18.85491943359375,
      "learning_rate": 3.3419075340147566e-05,
      "loss": 32.95417724609375,
      "step": 5400
    },
    {
      "epoch": 1.0803398237041766,
      "grad_norm": 20.03909683227539,
      "learning_rate": 3.3080620050091385e-05,
      "loss": 32.93142822265625,
      "step": 5500
    },
    {
      "epoch": 1.0999828123849045,
      "grad_norm": 19.49604606628418,
      "learning_rate": 3.27421647600352e-05,
      "loss": 32.9296630859375,
      "step": 5600
    },
    {
      "epoch": 1.1196258010656321,
      "grad_norm": 21.259004592895508,
      "learning_rate": 3.2403709469979017e-05,
      "loss": 32.85189453125,
      "step": 5700
    },
    {
      "epoch": 1.1392687897463598,
      "grad_norm": 19.597267150878906,
      "learning_rate": 3.206525417992283e-05,
      "loss": 32.82923583984375,
      "step": 5800
    },
    {
      "epoch": 1.1589117784270877,
      "grad_norm": 20.224699020385742,
      "learning_rate": 3.172679888986665e-05,
      "loss": 32.7767626953125,
      "step": 5900
    },
    {
      "epoch": 1.1785547671078154,
      "grad_norm": 18.452495574951172,
      "learning_rate": 3.138834359981047e-05,
      "loss": 32.6592626953125,
      "step": 6000
    },
    {
      "epoch": 1.1981977557885433,
      "grad_norm": 19.971717834472656,
      "learning_rate": 3.104988830975428e-05,
      "loss": 32.80323974609375,
      "step": 6100
    },
    {
      "epoch": 1.217840744469271,
      "grad_norm": 17.584882736206055,
      "learning_rate": 3.07114330196981e-05,
      "loss": 32.6551416015625,
      "step": 6200
    },
    {
      "epoch": 1.2374837331499988,
      "grad_norm": 19.49502944946289,
      "learning_rate": 3.0372977729641915e-05,
      "loss": 32.73489990234375,
      "step": 6300
    },
    {
      "epoch": 1.2492695263584355,
      "eval_loss": 3.9626989364624023,
      "eval_runtime": 41.8921,
      "eval_samples_per_second": 477.418,
      "eval_steps_per_second": 14.919,
      "step": 6360
    },
    {
      "epoch": 1.2571267218307265,
      "grad_norm": 20.214130401611328,
      "learning_rate": 3.0034522439585734e-05,
      "loss": 32.55817138671875,
      "step": 6400
    },
    {
      "epoch": 1.2767697105114544,
      "grad_norm": 20.668527603149414,
      "learning_rate": 2.969606714952955e-05,
      "loss": 32.53630615234375,
      "step": 6500
    },
    {
      "epoch": 1.296412699192182,
      "grad_norm": 18.479408264160156,
      "learning_rate": 2.9357611859473366e-05,
      "loss": 32.464462890625,
      "step": 6600
    },
    {
      "epoch": 1.31605568787291,
      "grad_norm": 19.027793884277344,
      "learning_rate": 2.9019156569417182e-05,
      "loss": 32.48625244140625,
      "step": 6700
    },
    {
      "epoch": 1.3356986765536376,
      "grad_norm": 19.871105194091797,
      "learning_rate": 2.8680701279361e-05,
      "loss": 32.41595947265625,
      "step": 6800
    },
    {
      "epoch": 1.3553416652343655,
      "grad_norm": 19.916994094848633,
      "learning_rate": 2.8342245989304817e-05,
      "loss": 32.11419921875,
      "step": 6900
    },
    {
      "epoch": 1.3749846539150932,
      "grad_norm": 21.212909698486328,
      "learning_rate": 2.8003790699248633e-05,
      "loss": 32.30314453125,
      "step": 7000
    },
    {
      "epoch": 1.3946276425958208,
      "grad_norm": 25.216768264770508,
      "learning_rate": 2.7665335409192445e-05,
      "loss": 32.19344482421875,
      "step": 7100
    },
    {
      "epoch": 1.4142706312765487,
      "grad_norm": 19.619844436645508,
      "learning_rate": 2.732688011913626e-05,
      "loss": 32.30953125,
      "step": 7200
    },
    {
      "epoch": 1.4339136199572766,
      "grad_norm": 21.061376571655273,
      "learning_rate": 2.6988424829080077e-05,
      "loss": 32.3416162109375,
      "step": 7300
    },
    {
      "epoch": 1.4535566086380043,
      "grad_norm": 18.674562454223633,
      "learning_rate": 2.6649969539023896e-05,
      "loss": 32.2662744140625,
      "step": 7400
    },
    {
      "epoch": 1.473199597318732,
      "grad_norm": 18.776655197143555,
      "learning_rate": 2.6311514248967712e-05,
      "loss": 32.07302978515625,
      "step": 7500
    },
    {
      "epoch": 1.4928425859994598,
      "grad_norm": 19.0480899810791,
      "learning_rate": 2.5973058958911528e-05,
      "loss": 32.19434326171875,
      "step": 7600
    },
    {
      "epoch": 1.4991283423772928,
      "eval_loss": 3.9200026988983154,
      "eval_runtime": 42.1732,
      "eval_samples_per_second": 474.235,
      "eval_steps_per_second": 14.82,
      "step": 7632
    },
    {
      "epoch": 1.5124855746801877,
      "grad_norm": 18.192241668701172,
      "learning_rate": 2.5634603668855344e-05,
      "loss": 32.0382470703125,
      "step": 7700
    },
    {
      "epoch": 1.5321285633609154,
      "grad_norm": 21.64850425720215,
      "learning_rate": 2.5296148378799163e-05,
      "loss": 32.0071484375,
      "step": 7800
    },
    {
      "epoch": 1.551771552041643,
      "grad_norm": 21.07256507873535,
      "learning_rate": 2.495769308874298e-05,
      "loss": 32.02736328125,
      "step": 7900
    },
    {
      "epoch": 1.5714145407223707,
      "grad_norm": 18.811485290527344,
      "learning_rate": 2.4619237798686794e-05,
      "loss": 32.18232666015625,
      "step": 8000
    },
    {
      "epoch": 1.5910575294030986,
      "grad_norm": 20.226411819458008,
      "learning_rate": 2.428078250863061e-05,
      "loss": 31.81751220703125,
      "step": 8100
    },
    {
      "epoch": 1.6107005180838265,
      "grad_norm": 21.44918441772461,
      "learning_rate": 2.394232721857443e-05,
      "loss": 31.89043212890625,
      "step": 8200
    },
    {
      "epoch": 1.6303435067645542,
      "grad_norm": 19.660367965698242,
      "learning_rate": 2.3603871928518245e-05,
      "loss": 31.95683349609375,
      "step": 8300
    },
    {
      "epoch": 1.6499864954452819,
      "grad_norm": 19.144596099853516,
      "learning_rate": 2.3265416638462058e-05,
      "loss": 31.867197265625,
      "step": 8400
    },
    {
      "epoch": 1.6696294841260098,
      "grad_norm": 18.604026794433594,
      "learning_rate": 2.2926961348405877e-05,
      "loss": 31.78265380859375,
      "step": 8500
    },
    {
      "epoch": 1.6892724728067376,
      "grad_norm": 19.978652954101562,
      "learning_rate": 2.2588506058349693e-05,
      "loss": 31.79925048828125,
      "step": 8600
    },
    {
      "epoch": 1.7089154614874653,
      "grad_norm": 18.18141746520996,
      "learning_rate": 2.225005076829351e-05,
      "loss": 31.853974609375,
      "step": 8700
    },
    {
      "epoch": 1.728558450168193,
      "grad_norm": 17.99820899963379,
      "learning_rate": 2.1911595478237325e-05,
      "loss": 31.75265625,
      "step": 8800
    },
    {
      "epoch": 1.7482014388489209,
      "grad_norm": 20.680606842041016,
      "learning_rate": 2.1573140188181144e-05,
      "loss": 31.6561328125,
      "step": 8900
    },
    {
      "epoch": 1.74898715839615,
      "eval_loss": 3.863434076309204,
      "eval_runtime": 42.0055,
      "eval_samples_per_second": 476.128,
      "eval_steps_per_second": 14.879,
      "step": 8904
    },
    {
      "epoch": 1.7678444275296488,
      "grad_norm": 20.50802993774414,
      "learning_rate": 2.123468489812496e-05,
      "loss": 31.6072265625,
      "step": 9000
    },
    {
      "epoch": 1.7874874162103764,
      "grad_norm": 21.482328414916992,
      "learning_rate": 2.0896229608068775e-05,
      "loss": 31.7250537109375,
      "step": 9100
    },
    {
      "epoch": 1.807130404891104,
      "grad_norm": 19.20509910583496,
      "learning_rate": 2.055777431801259e-05,
      "loss": 31.58796875,
      "step": 9200
    },
    {
      "epoch": 1.826773393571832,
      "grad_norm": 21.03694725036621,
      "learning_rate": 2.0219319027956407e-05,
      "loss": 31.68398193359375,
      "step": 9300
    },
    {
      "epoch": 1.8464163822525599,
      "grad_norm": 18.272459030151367,
      "learning_rate": 1.9880863737900223e-05,
      "loss": 31.53086181640625,
      "step": 9400
    },
    {
      "epoch": 1.8660593709332876,
      "grad_norm": 19.046916961669922,
      "learning_rate": 1.9542408447844042e-05,
      "loss": 31.525322265625,
      "step": 9500
    },
    {
      "epoch": 1.8857023596140152,
      "grad_norm": 21.118305206298828,
      "learning_rate": 1.9203953157787858e-05,
      "loss": 31.52841552734375,
      "step": 9600
    },
    {
      "epoch": 1.905345348294743,
      "grad_norm": 18.861080169677734,
      "learning_rate": 1.8865497867731674e-05,
      "loss": 31.4529345703125,
      "step": 9700
    },
    {
      "epoch": 1.9249883369754708,
      "grad_norm": 20.4729061126709,
      "learning_rate": 1.852704257767549e-05,
      "loss": 31.35305419921875,
      "step": 9800
    },
    {
      "epoch": 1.9446313256561987,
      "grad_norm": 17.702392578125,
      "learning_rate": 1.818858728761931e-05,
      "loss": 31.5552734375,
      "step": 9900
    },
    {
      "epoch": 1.9642743143369263,
      "grad_norm": 21.927942276000977,
      "learning_rate": 1.785013199756312e-05,
      "loss": 31.42951416015625,
      "step": 10000
    },
    {
      "epoch": 1.983917303017654,
      "grad_norm": 19.895252227783203,
      "learning_rate": 1.7511676707506937e-05,
      "loss": 31.416962890625,
      "step": 10100
    },
    {
      "epoch": 1.998845974415007,
      "eval_loss": 3.819389820098877,
      "eval_runtime": 41.9176,
      "eval_samples_per_second": 477.126,
      "eval_steps_per_second": 14.91,
      "step": 10176
    },
    {
      "epoch": 2.003535737962531,
      "grad_norm": 20.209577560424805,
      "learning_rate": 1.7173221417450756e-05,
      "loss": 31.25757568359375,
      "step": 10200
    },
    {
      "epoch": 2.0231787266432586,
      "grad_norm": 19.49869155883789,
      "learning_rate": 1.6834766127394572e-05,
      "loss": 31.14395263671875,
      "step": 10300
    },
    {
      "epoch": 2.0428217153239867,
      "grad_norm": 20.60426139831543,
      "learning_rate": 1.6496310837338388e-05,
      "loss": 31.38017333984375,
      "step": 10400
    },
    {
      "epoch": 2.0624647040047144,
      "grad_norm": 19.177818298339844,
      "learning_rate": 1.6157855547282204e-05,
      "loss": 31.20944091796875,
      "step": 10500
    },
    {
      "epoch": 2.082107692685442,
      "grad_norm": 20.949337005615234,
      "learning_rate": 1.5819400257226023e-05,
      "loss": 31.2146240234375,
      "step": 10600
    },
    {
      "epoch": 2.1017506813661697,
      "grad_norm": 19.25591468811035,
      "learning_rate": 1.548094496716984e-05,
      "loss": 31.202607421875,
      "step": 10700
    },
    {
      "epoch": 2.121393670046898,
      "grad_norm": 18.960092544555664,
      "learning_rate": 1.5142489677113653e-05,
      "loss": 31.14611572265625,
      "step": 10800
    },
    {
      "epoch": 2.1410366587276255,
      "grad_norm": 18.479068756103516,
      "learning_rate": 1.4804034387057469e-05,
      "loss": 31.26153564453125,
      "step": 10900
    },
    {
      "epoch": 2.160679647408353,
      "grad_norm": 21.587387084960938,
      "learning_rate": 1.4465579097001287e-05,
      "loss": 31.1222998046875,
      "step": 11000
    },
    {
      "epoch": 2.180322636089081,
      "grad_norm": 17.947052001953125,
      "learning_rate": 1.4127123806945102e-05,
      "loss": 31.08917236328125,
      "step": 11100
    },
    {
      "epoch": 2.199965624769809,
      "grad_norm": 19.169307708740234,
      "learning_rate": 1.378866851688892e-05,
      "loss": 31.0661474609375,
      "step": 11200
    },
    {
      "epoch": 2.2196086134505366,
      "grad_norm": 16.882522583007812,
      "learning_rate": 1.3450213226832736e-05,
      "loss": 30.9886328125,
      "step": 11300
    },
    {
      "epoch": 2.2392516021312643,
      "grad_norm": 19.624177932739258,
      "learning_rate": 1.3111757936776553e-05,
      "loss": 30.93468505859375,
      "step": 11400
    },
    {
      "epoch": 2.2486802366980134,
      "eval_loss": 3.786958694458008,
      "eval_runtime": 41.8524,
      "eval_samples_per_second": 477.869,
      "eval_steps_per_second": 14.933,
      "step": 11448
    },
    {
      "epoch": 2.258894590811992,
      "grad_norm": 20.477542877197266,
      "learning_rate": 1.2773302646720369e-05,
      "loss": 31.00721923828125,
      "step": 11500
    },
    {
      "epoch": 2.2785375794927196,
      "grad_norm": 19.928098678588867,
      "learning_rate": 1.2434847356664185e-05,
      "loss": 30.95269775390625,
      "step": 11600
    },
    {
      "epoch": 2.2981805681734477,
      "grad_norm": 19.002788543701172,
      "learning_rate": 1.2096392066608003e-05,
      "loss": 30.908701171875,
      "step": 11700
    },
    {
      "epoch": 2.3178235568541754,
      "grad_norm": 20.50242805480957,
      "learning_rate": 1.1757936776551818e-05,
      "loss": 30.96546142578125,
      "step": 11800
    },
    {
      "epoch": 2.337466545534903,
      "grad_norm": 20.48063850402832,
      "learning_rate": 1.1419481486495634e-05,
      "loss": 30.9563623046875,
      "step": 11900
    },
    {
      "epoch": 2.3571095342156307,
      "grad_norm": 19.522266387939453,
      "learning_rate": 1.108102619643945e-05,
      "loss": 30.85960205078125,
      "step": 12000
    },
    {
      "epoch": 2.376752522896359,
      "grad_norm": 21.33004379272461,
      "learning_rate": 1.0742570906383268e-05,
      "loss": 30.829111328125,
      "step": 12100
    },
    {
      "epoch": 2.3963955115770865,
      "grad_norm": 20.311534881591797,
      "learning_rate": 1.0404115616327083e-05,
      "loss": 30.93859619140625,
      "step": 12200
    },
    {
      "epoch": 2.416038500257814,
      "grad_norm": 20.128795623779297,
      "learning_rate": 1.00656603262709e-05,
      "loss": 30.750810546875,
      "step": 12300
    },
    {
      "epoch": 2.435681488938542,
      "grad_norm": 22.28921890258789,
      "learning_rate": 9.727205036214717e-06,
      "loss": 30.714560546875,
      "step": 12400
    },
    {
      "epoch": 2.4553244776192695,
      "grad_norm": 24.13454818725586,
      "learning_rate": 9.388749746158533e-06,
      "loss": 30.87623779296875,
      "step": 12500
    },
    {
      "epoch": 2.4749674662999976,
      "grad_norm": 20.58381462097168,
      "learning_rate": 9.05029445610235e-06,
      "loss": 30.60492431640625,
      "step": 12600
    },
    {
      "epoch": 2.4946104549807253,
      "grad_norm": 20.045475006103516,
      "learning_rate": 8.711839166046164e-06,
      "loss": 30.8008154296875,
      "step": 12700
    },
    {
      "epoch": 2.498539052716871,
      "eval_loss": 3.7586019039154053,
      "eval_runtime": 42.0034,
      "eval_samples_per_second": 476.152,
      "eval_steps_per_second": 14.88,
      "step": 12720
    },
    {
      "epoch": 2.514253443661453,
      "grad_norm": 19.53034210205078,
      "learning_rate": 8.373383875989982e-06,
      "loss": 30.7534326171875,
      "step": 12800
    },
    {
      "epoch": 2.533896432342181,
      "grad_norm": 20.510520935058594,
      "learning_rate": 8.0349285859338e-06,
      "loss": 30.7755859375,
      "step": 12900
    },
    {
      "epoch": 2.5535394210229088,
      "grad_norm": 20.725147247314453,
      "learning_rate": 7.696473295877615e-06,
      "loss": 30.9005029296875,
      "step": 13000
    },
    {
      "epoch": 2.5731824097036364,
      "grad_norm": 20.11240577697754,
      "learning_rate": 7.358018005821431e-06,
      "loss": 30.81609130859375,
      "step": 13100
    },
    {
      "epoch": 2.592825398384364,
      "grad_norm": 19.01041603088379,
      "learning_rate": 7.019562715765248e-06,
      "loss": 30.70421142578125,
      "step": 13200
    },
    {
      "epoch": 2.6124683870650918,
      "grad_norm": 20.232532501220703,
      "learning_rate": 6.681107425709064e-06,
      "loss": 30.7105322265625,
      "step": 13300
    },
    {
      "epoch": 2.63211137574582,
      "grad_norm": 21.33913803100586,
      "learning_rate": 6.342652135652881e-06,
      "loss": 30.76764892578125,
      "step": 13400
    },
    {
      "epoch": 2.6517543644265475,
      "grad_norm": 19.718833923339844,
      "learning_rate": 6.004196845596697e-06,
      "loss": 30.75705078125,
      "step": 13500
    },
    {
      "epoch": 2.671397353107275,
      "grad_norm": 20.983705520629883,
      "learning_rate": 5.665741555540514e-06,
      "loss": 30.66492431640625,
      "step": 13600
    },
    {
      "epoch": 2.691040341788003,
      "grad_norm": 18.726970672607422,
      "learning_rate": 5.3272862654843295e-06,
      "loss": 30.72262451171875,
      "step": 13700
    },
    {
      "epoch": 2.710683330468731,
      "grad_norm": 21.197751998901367,
      "learning_rate": 4.988830975428146e-06,
      "loss": 30.6771728515625,
      "step": 13800
    },
    {
      "epoch": 2.7303263191494587,
      "grad_norm": 21.318998336791992,
      "learning_rate": 4.650375685371963e-06,
      "loss": 30.52608642578125,
      "step": 13900
    },
    {
      "epoch": 2.748397868735728,
      "eval_loss": 3.7217817306518555,
      "eval_runtime": 41.8977,
      "eval_samples_per_second": 477.353,
      "eval_steps_per_second": 14.917,
      "step": 13992
    }
  ],
  "logging_steps": 100,
  "max_steps": 15273,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1272,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.427785384950231e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}