{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015641769143410204,
  "eval_steps": 334,
  "global_step": 501,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.1221096094631145e-05,
      "eval_loss": 2.5151805877685547,
      "eval_runtime": 12858.7571,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 1
    },
    {
      "epoch": 0.0003122109609463114,
      "grad_norm": 1.6301891803741455,
      "learning_rate": 0.0002,
      "loss": 1.2603,
      "step": 10
    },
    {
      "epoch": 0.0006244219218926228,
      "grad_norm": 2.2189297676086426,
      "learning_rate": 0.00019994965423831854,
      "loss": 0.8201,
      "step": 20
    },
    {
      "epoch": 0.0009366328828389343,
      "grad_norm": 1.6551645994186401,
      "learning_rate": 0.00019979866764718843,
      "loss": 0.7913,
      "step": 30
    },
    {
      "epoch": 0.0012488438437852456,
      "grad_norm": 4.437395095825195,
      "learning_rate": 0.00019954719225730847,
      "loss": 1.2831,
      "step": 40
    },
    {
      "epoch": 0.001561054804731557,
      "grad_norm": 7.653807163238525,
      "learning_rate": 0.00019919548128307954,
      "loss": 1.6268,
      "step": 50
    },
    {
      "epoch": 0.0018732657656778686,
      "grad_norm": 1.2926839590072632,
      "learning_rate": 0.00019874388886763944,
      "loss": 1.1779,
      "step": 60
    },
    {
      "epoch": 0.00218547672662418,
      "grad_norm": 1.5756969451904297,
      "learning_rate": 0.00019819286972627066,
      "loss": 0.6204,
      "step": 70
    },
    {
      "epoch": 0.002497687687570491,
      "grad_norm": 1.8183478116989136,
      "learning_rate": 0.00019754297868854073,
      "loss": 0.8666,
      "step": 80
    },
    {
      "epoch": 0.0028098986485168027,
      "grad_norm": 4.023663520812988,
      "learning_rate": 0.00019679487013963564,
      "loss": 1.1012,
      "step": 90
    },
    {
      "epoch": 0.003122109609463114,
      "grad_norm": 3.675027847290039,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.3794,
      "step": 100
    },
    {
      "epoch": 0.0034343205704094257,
      "grad_norm": 1.1626209020614624,
      "learning_rate": 0.00019500711177409454,
      "loss": 1.1787,
      "step": 110
    },
    {
      "epoch": 0.003746531531355737,
      "grad_norm": 1.4152737855911255,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.471,
      "step": 120
    },
    {
      "epoch": 0.004058742492302049,
      "grad_norm": 2.0098798274993896,
      "learning_rate": 0.00019283679330160726,
      "loss": 0.9037,
      "step": 130
    },
    {
      "epoch": 0.00437095345324836,
      "grad_norm": 2.845428943634033,
      "learning_rate": 0.00019161084574320696,
      "loss": 1.2114,
      "step": 140
    },
    {
      "epoch": 0.004683164414194672,
      "grad_norm": 5.3034749031066895,
      "learning_rate": 0.00019029265382866214,
      "loss": 1.397,
      "step": 150
    },
    {
      "epoch": 0.004995375375140982,
      "grad_norm": 1.5945558547973633,
      "learning_rate": 0.00018888354486549237,
      "loss": 1.145,
      "step": 160
    },
    {
      "epoch": 0.005307586336087294,
      "grad_norm": 1.1813420057296753,
      "learning_rate": 0.00018738493770697852,
      "loss": 0.5603,
      "step": 170
    },
    {
      "epoch": 0.005619797297033605,
      "grad_norm": 2.35960054397583,
      "learning_rate": 0.00018579834132349772,
      "loss": 0.8248,
      "step": 180
    },
    {
      "epoch": 0.005932008257979917,
      "grad_norm": 2.443915605545044,
      "learning_rate": 0.00018412535328311814,
      "loss": 1.1141,
      "step": 190
    },
    {
      "epoch": 0.006244219218926228,
      "grad_norm": 5.689703941345215,
      "learning_rate": 0.0001823676581429833,
      "loss": 1.2009,
      "step": 200
    },
    {
      "epoch": 0.00655643017987254,
      "grad_norm": 1.4314906597137451,
      "learning_rate": 0.00018052702575310588,
      "loss": 1.1061,
      "step": 210
    },
    {
      "epoch": 0.006868641140818851,
      "grad_norm": 0.6448104977607727,
      "learning_rate": 0.00017860530947427875,
      "loss": 0.4016,
      "step": 220
    },
    {
      "epoch": 0.007180852101765163,
      "grad_norm": 2.0396196842193604,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.8709,
      "step": 230
    },
    {
      "epoch": 0.007493063062711474,
      "grad_norm": 2.5875227451324463,
      "learning_rate": 0.0001745264449675755,
      "loss": 1.1121,
      "step": 240
    },
    {
      "epoch": 0.007805274023657786,
      "grad_norm": 3.9609525203704834,
      "learning_rate": 0.00017237340381050703,
      "loss": 1.251,
      "step": 250
    },
    {
      "epoch": 0.008117484984604097,
      "grad_norm": 1.2032607793807983,
      "learning_rate": 0.00017014748877063214,
      "loss": 1.1823,
      "step": 260
    },
    {
      "epoch": 0.008429695945550408,
      "grad_norm": 1.186848521232605,
      "learning_rate": 0.00016785094115571322,
      "loss": 0.6219,
      "step": 270
    },
    {
      "epoch": 0.00874190690649672,
      "grad_norm": 1.85453462600708,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.5809,
      "step": 280
    },
    {
      "epoch": 0.009054117867443031,
      "grad_norm": 2.0443332195281982,
      "learning_rate": 0.00016305526670845226,
      "loss": 1.2146,
      "step": 290
    },
    {
      "epoch": 0.009366328828389343,
      "grad_norm": 7.1448516845703125,
      "learning_rate": 0.00016056096871376667,
      "loss": 1.2524,
      "step": 300
    },
    {
      "epoch": 0.009678539789335654,
      "grad_norm": 1.334848165512085,
      "learning_rate": 0.00015800569095711982,
      "loss": 1.1966,
      "step": 310
    },
    {
      "epoch": 0.009990750750281965,
      "grad_norm": 0.4558267295360565,
      "learning_rate": 0.00015539200638661104,
      "loss": 0.589,
      "step": 320
    },
    {
      "epoch": 0.010302961711228277,
      "grad_norm": 1.8344190120697021,
      "learning_rate": 0.00015272254676105025,
      "loss": 0.5806,
      "step": 330
    },
    {
      "epoch": 0.010427846095606801,
      "eval_loss": 0.9566133618354797,
      "eval_runtime": 13592.0734,
      "eval_samples_per_second": 2.095,
      "eval_steps_per_second": 2.095,
      "step": 334
    },
    {
      "epoch": 0.010615172672174588,
      "grad_norm": 1.9632649421691895,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0551,
      "step": 340
    },
    {
      "epoch": 0.0109273836331209,
      "grad_norm": 4.136826992034912,
      "learning_rate": 0.0001472271074772683,
      "loss": 1.0784,
      "step": 350
    },
    {
      "epoch": 0.01123959459406721,
      "grad_norm": 1.1779104471206665,
      "learning_rate": 0.00014440666126057744,
      "loss": 1.1613,
      "step": 360
    },
    {
      "epoch": 0.011551805555013523,
      "grad_norm": 0.8325644731521606,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.5119,
      "step": 370
    },
    {
      "epoch": 0.011864016515959834,
      "grad_norm": 1.6711801290512085,
      "learning_rate": 0.00013863451256931287,
      "loss": 0.6156,
      "step": 380
    },
    {
      "epoch": 0.012176227476906146,
      "grad_norm": 2.293975353240967,
      "learning_rate": 0.00013568862215918717,
      "loss": 1.0706,
      "step": 390
    },
    {
      "epoch": 0.012488438437852457,
      "grad_norm": 2.2785656452178955,
      "learning_rate": 0.00013270679633174218,
      "loss": 1.2872,
      "step": 400
    },
    {
      "epoch": 0.012800649398798769,
      "grad_norm": 1.2502048015594482,
      "learning_rate": 0.0001296920375328275,
      "loss": 1.0768,
      "step": 410
    },
    {
      "epoch": 0.01311286035974508,
      "grad_norm": 0.7812928557395935,
      "learning_rate": 0.00012664738136900348,
      "loss": 0.5199,
      "step": 420
    },
    {
      "epoch": 0.01342507132069139,
      "grad_norm": 2.0176918506622314,
      "learning_rate": 0.00012357589355094275,
      "loss": 0.8125,
      "step": 430
    },
    {
      "epoch": 0.013737282281637703,
      "grad_norm": 2.014697313308716,
      "learning_rate": 0.00012048066680651908,
      "loss": 1.0261,
      "step": 440
    },
    {
      "epoch": 0.014049493242584013,
      "grad_norm": 3.0161404609680176,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.1352,
      "step": 450
    },
    {
      "epoch": 0.014361704203530326,
      "grad_norm": 1.1186920404434204,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.1374,
      "step": 460
    },
    {
      "epoch": 0.014673915164476636,
      "grad_norm": 0.9820886850357056,
      "learning_rate": 0.00011108381999010111,
      "loss": 0.5135,
      "step": 470
    },
    {
      "epoch": 0.014986126125422949,
      "grad_norm": 2.8473262786865234,
      "learning_rate": 0.00010792499568567884,
      "loss": 0.8812,
      "step": 480
    },
    {
      "epoch": 0.01529833708636926,
      "grad_norm": 2.1481053829193115,
      "learning_rate": 0.00010475819158237425,
      "loss": 1.0178,
      "step": 490
    },
    {
      "epoch": 0.015610548047315572,
      "grad_norm": 1.20015287399292,
      "learning_rate": 0.00010158659638348081,
      "loss": 1.0468,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 167,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.824081922120745e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}