{
  "best_global_step": 6522,
  "best_metric": 3.4418444633483887,
  "best_model_checkpoint": "sindhibert_session6r/checkpoint-6522",
  "epoch": 2.0,
  "eval_steps": 3261,
  "global_step": 6522,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030672494440610383,
      "grad_norm": 5.580650806427002,
      "learning_rate": 1.2659846547314581e-06,
      "loss": 14.62664794921875,
      "step": 100
    },
    {
      "epoch": 0.061344988881220766,
      "grad_norm": 5.809163570404053,
      "learning_rate": 2.544757033248082e-06,
      "loss": 14.634923095703124,
      "step": 200
    },
    {
      "epoch": 0.09201748332183114,
      "grad_norm": 5.849374294281006,
      "learning_rate": 3.8235294117647055e-06,
      "loss": 14.635355224609375,
      "step": 300
    },
    {
      "epoch": 0.12268997776244153,
      "grad_norm": 5.751659870147705,
      "learning_rate": 4.999978994815915e-06,
      "loss": 14.59581298828125,
      "step": 400
    },
    {
      "epoch": 0.1533624722030519,
      "grad_norm": 5.633106708526611,
      "learning_rate": 4.996172776747675e-06,
      "loss": 14.598475341796876,
      "step": 500
    },
    {
      "epoch": 0.18403496664366228,
      "grad_norm": 5.498394012451172,
      "learning_rate": 4.9858139123513936e-06,
      "loss": 14.56541259765625,
      "step": 600
    },
    {
      "epoch": 0.2147074610842727,
      "grad_norm": 5.918303489685059,
      "learning_rate": 4.968929594446166e-06,
      "loss": 14.57242919921875,
      "step": 700
    },
    {
      "epoch": 0.24537995552488306,
      "grad_norm": 5.2229814529418945,
      "learning_rate": 4.945564145670534e-06,
      "loss": 14.53744873046875,
      "step": 800
    },
    {
      "epoch": 0.27605244996549344,
      "grad_norm": 5.516529560089111,
      "learning_rate": 4.9157789021321375e-06,
      "loss": 14.531802978515625,
      "step": 900
    },
    {
      "epoch": 0.3067249444061038,
      "grad_norm": 5.460958003997803,
      "learning_rate": 4.879652052395696e-06,
      "loss": 14.5186328125,
      "step": 1000
    },
    {
      "epoch": 0.3373974388467142,
      "grad_norm": 5.609668731689453,
      "learning_rate": 4.837278432231982e-06,
      "loss": 14.51820068359375,
      "step": 1100
    },
    {
      "epoch": 0.36806993328732457,
      "grad_norm": 5.466991424560547,
      "learning_rate": 4.788769275666605e-06,
      "loss": 14.477803955078125,
      "step": 1200
    },
    {
      "epoch": 0.398742427727935,
      "grad_norm": 5.586793899536133,
      "learning_rate": 4.7342519229820996e-06,
      "loss": 14.506885986328125,
      "step": 1300
    },
    {
      "epoch": 0.4294149221685454,
      "grad_norm": 5.488733768463135,
      "learning_rate": 4.673869486439846e-06,
      "loss": 14.464423828125,
      "step": 1400
    },
    {
      "epoch": 0.46008741660915575,
      "grad_norm": 5.8738017082214355,
      "learning_rate": 4.60778047459934e-06,
      "loss": 14.470579833984376,
      "step": 1500
    },
    {
      "epoch": 0.49075991104976613,
      "grad_norm": 5.592001438140869,
      "learning_rate": 4.536158376220971e-06,
      "loss": 14.42775146484375,
      "step": 1600
    },
    {
      "epoch": 0.5214324054903765,
      "grad_norm": 5.235401153564453,
      "learning_rate": 4.459191204844634e-06,
      "loss": 14.42791259765625,
      "step": 1700
    },
    {
      "epoch": 0.5521048999309869,
      "grad_norm": 5.959557056427002,
      "learning_rate": 4.377081005239665e-06,
      "loss": 14.444658203125,
      "step": 1800
    },
    {
      "epoch": 0.5827773943715973,
      "grad_norm": 5.362053394317627,
      "learning_rate": 4.2900433230217155e-06,
      "loss": 14.463519287109374,
      "step": 1900
    },
    {
      "epoch": 0.6134498888122076,
      "grad_norm": 5.445187568664551,
      "learning_rate": 4.198306638828863e-06,
      "loss": 14.472896728515625,
      "step": 2000
    },
    {
      "epoch": 0.644122383252818,
      "grad_norm": 5.700764179229736,
      "learning_rate": 4.102111768542294e-06,
      "loss": 14.44870849609375,
      "step": 2100
    },
    {
      "epoch": 0.6747948776934284,
      "grad_norm": 5.197051525115967,
      "learning_rate": 4.001711231126012e-06,
      "loss": 14.42983642578125,
      "step": 2200
    },
    {
      "epoch": 0.7054673721340388,
      "grad_norm": 5.519675254821777,
      "learning_rate": 3.897368585745059e-06,
      "loss": 14.4178271484375,
      "step": 2300
    },
    {
      "epoch": 0.7361398665746491,
      "grad_norm": 5.8170647621154785,
      "learning_rate": 3.789357739902342e-06,
      "loss": 14.38358642578125,
      "step": 2400
    },
    {
      "epoch": 0.7668123610152595,
      "grad_norm": 5.513352394104004,
      "learning_rate": 3.6779622304102957e-06,
      "loss": 14.41911376953125,
      "step": 2500
    },
    {
      "epoch": 0.79748485545587,
      "grad_norm": 5.644667625427246,
      "learning_rate": 3.5634744790848436e-06,
      "loss": 14.40310791015625,
      "step": 2600
    },
    {
      "epoch": 0.8281573498964804,
      "grad_norm": 5.676363945007324,
      "learning_rate": 3.4461950251155457e-06,
      "loss": 14.40308349609375,
      "step": 2700
    },
    {
      "epoch": 0.8588298443370908,
      "grad_norm": 5.251427173614502,
      "learning_rate": 3.326431736127017e-06,
      "loss": 14.39386474609375,
      "step": 2800
    },
    {
      "epoch": 0.8895023387777011,
      "grad_norm": 5.631777286529541,
      "learning_rate": 3.2044990000026366e-06,
      "loss": 14.374044189453125,
      "step": 2900
    },
    {
      "epoch": 0.9201748332183115,
      "grad_norm": 5.5782670974731445,
      "learning_rate": 3.080716899592065e-06,
      "loss": 14.37978515625,
      "step": 3000
    },
    {
      "epoch": 0.9508473276589219,
      "grad_norm": 5.784708023071289,
      "learning_rate": 2.9554103724690526e-06,
      "loss": 14.3670703125,
      "step": 3100
    },
    {
      "epoch": 0.9815198220995323,
      "grad_norm": 5.501222610473633,
      "learning_rate": 2.8289083579452043e-06,
      "loss": 14.374014892578124,
      "step": 3200
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.45804762840271,
      "eval_runtime": 13.1436,
      "eval_samples_per_second": 641.376,
      "eval_steps_per_second": 10.043,
      "step": 3261
    },
    {
      "epoch": 1.011962272831838,
      "grad_norm": 5.622377872467041,
      "learning_rate": 2.7015429335788844e-06,
      "loss": 14.245347900390625,
      "step": 3300
    },
    {
      "epoch": 1.0426347672724485,
      "grad_norm": 5.506319522857666,
      "learning_rate": 2.57364844344598e-06,
      "loss": 14.36246826171875,
      "step": 3400
    },
    {
      "epoch": 1.0733072617130588,
      "grad_norm": 5.29400634765625,
      "learning_rate": 2.4455606204608764e-06,
      "loss": 14.3725537109375,
      "step": 3500
    },
    {
      "epoch": 1.1039797561536693,
      "grad_norm": 5.597475528717041,
      "learning_rate": 2.3176157050516264e-06,
      "loss": 14.357423095703124,
      "step": 3600
    },
    {
      "epoch": 1.1346522505942795,
      "grad_norm": 5.25772762298584,
      "learning_rate": 2.1901495625028606e-06,
      "loss": 14.315875244140624,
      "step": 3700
    },
    {
      "epoch": 1.16532474503489,
      "grad_norm": 5.585110187530518,
      "learning_rate": 2.063496801283472e-06,
      "loss": 14.327174072265626,
      "step": 3800
    },
    {
      "epoch": 1.1959972394755003,
      "grad_norm": 5.402249813079834,
      "learning_rate": 1.9379898946735452e-06,
      "loss": 14.34656494140625,
      "step": 3900
    },
    {
      "epoch": 1.2266697339161108,
      "grad_norm": 5.390650749206543,
      "learning_rate": 1.8139583079963144e-06,
      "loss": 14.36371826171875,
      "step": 4000
    },
    {
      "epoch": 1.257342228356721,
      "grad_norm": 5.242497444152832,
      "learning_rate": 1.6917276337462466e-06,
      "loss": 14.323082275390625,
      "step": 4100
    },
    {
      "epoch": 1.2880147227973315,
      "grad_norm": 5.234506130218506,
      "learning_rate": 1.5716187368835971e-06,
      "loss": 14.337457275390625,
      "step": 4200
    },
    {
      "epoch": 1.3186872172379418,
      "grad_norm": 5.626885890960693,
      "learning_rate": 1.4539469125391031e-06,
      "loss": 14.354864501953125,
      "step": 4300
    },
    {
      "epoch": 1.3493597116785523,
      "grad_norm": 5.311978816986084,
      "learning_rate": 1.3390210583399215e-06,
      "loss": 14.32729248046875,
      "step": 4400
    },
    {
      "epoch": 1.3800322061191626,
      "grad_norm": 5.375194072723389,
      "learning_rate": 1.2271428635294922e-06,
      "loss": 14.337626953125,
      "step": 4500
    },
    {
      "epoch": 1.410704700559773,
      "grad_norm": 5.57642936706543,
      "learning_rate": 1.118606017009978e-06,
      "loss": 14.334080810546874,
      "step": 4600
    },
    {
      "epoch": 1.4413771950003835,
      "grad_norm": 5.510963439941406,
      "learning_rate": 1.0136954363862126e-06,
      "loss": 14.33389404296875,
      "step": 4700
    },
    {
      "epoch": 1.4720496894409938,
      "grad_norm": 5.4500041007995605,
      "learning_rate": 9.126865200349847e-07,
      "loss": 14.31758056640625,
      "step": 4800
    },
    {
      "epoch": 1.502722183881604,
      "grad_norm": 5.399460792541504,
      "learning_rate": 8.158444241630245e-07,
      "loss": 14.280606689453125,
      "step": 4900
    },
    {
      "epoch": 1.5333946783222145,
      "grad_norm": 5.639800071716309,
      "learning_rate": 7.234233667514868e-07,
      "loss": 14.342408447265624,
      "step": 5000
    },
    {
      "epoch": 1.564067172762825,
      "grad_norm": 5.429558277130127,
      "learning_rate": 6.356659602141116e-07,
      "loss": 14.314246826171875,
      "step": 5100
    },
    {
      "epoch": 1.5947396672034353,
      "grad_norm": 5.131410598754883,
      "learning_rate": 5.528025745209039e-07,
      "loss": 14.32427978515625,
      "step": 5200
    },
    {
      "epoch": 1.6254121616440456,
      "grad_norm": 5.480471611022949,
      "learning_rate": 4.7505073245916774e-07,
      "loss": 14.32928466796875,
      "step": 5300
    },
    {
      "epoch": 1.656084656084656,
      "grad_norm": 5.693525791168213,
      "learning_rate": 4.026145386193914e-07,
      "loss": 14.34359375,
      "step": 5400
    },
    {
      "epoch": 1.6867571505252665,
      "grad_norm": 5.723335266113281,
      "learning_rate": 3.3568414360493075e-07,
      "loss": 14.31550537109375,
      "step": 5500
    },
    {
      "epoch": 1.7174296449658768,
      "grad_norm": 5.319007873535156,
      "learning_rate": 2.7443524487199333e-07,
      "loss": 14.32018310546875,
      "step": 5600
    },
    {
      "epoch": 1.7481021394064873,
      "grad_norm": 5.462660312652588,
      "learning_rate": 2.1902862551024112e-07,
      "loss": 14.333775634765624,
      "step": 5700
    },
    {
      "epoch": 1.7787746338470978,
      "grad_norm": 5.3777546882629395,
      "learning_rate": 1.6960973217476778e-07,
      "loss": 14.32505126953125,
      "step": 5800
    },
    {
      "epoch": 1.809447128287708,
      "grad_norm": 5.701692581176758,
      "learning_rate": 1.2630829327738987e-07,
      "loss": 14.33883056640625,
      "step": 5900
    },
    {
      "epoch": 1.8401196227283183,
      "grad_norm": 5.285277843475342,
      "learning_rate": 8.92379784395514e-08,
      "loss": 14.3292626953125,
      "step": 6000
    },
    {
      "epoch": 1.8707921171689288,
      "grad_norm": 5.558449745178223,
      "learning_rate": 5.849610010078499e-08,
      "loss": 14.3488134765625,
      "step": 6100
    },
    {
      "epoch": 1.9014646116095393,
      "grad_norm": 5.662689685821533,
      "learning_rate": 3.416335806604443e-08,
      "loss": 14.28878173828125,
      "step": 6200
    },
    {
      "epoch": 1.9321371060501495,
      "grad_norm": 5.507394790649414,
      "learning_rate": 1.630362766248256e-08,
      "loss": 14.3447216796875,
      "step": 6300
    },
    {
      "epoch": 1.9628096004907598,
      "grad_norm": 5.682081699371338,
      "learning_rate": 4.963792061784822e-09,
      "loss": 14.32853515625,
      "step": 6400
    },
    {
      "epoch": 1.9934820949313703,
      "grad_norm": 5.3612589836120605,
      "learning_rate": 1.736192082227306e-10,
      "loss": 14.27859130859375,
      "step": 6500
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.4418444633483887,
      "eval_runtime": 13.1653,
      "eval_samples_per_second": 640.317,
      "eval_steps_per_second": 10.026,
      "step": 6522
    }
  ],
  "logging_steps": 100,
  "max_steps": 6522,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 3261,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.393516896094925e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}