{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9702457956015524,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0129366106080207,
      "grad_norm": 59.0,
      "learning_rate": 6.129032258064517e-06,
      "loss": 4.853952407836914,
      "step": 20
    },
    {
      "epoch": 0.0258732212160414,
      "grad_norm": 24.625,
      "learning_rate": 1.2580645161290324e-05,
      "loss": 1.9714622497558594,
      "step": 40
    },
    {
      "epoch": 0.03880983182406209,
      "grad_norm": 21.875,
      "learning_rate": 1.903225806451613e-05,
      "loss": 1.4243444442749023,
      "step": 60
    },
    {
      "epoch": 0.0517464424320828,
      "grad_norm": 19.125,
      "learning_rate": 2.548387096774194e-05,
      "loss": 1.2418301582336426,
      "step": 80
    },
    {
      "epoch": 0.0646830530401035,
      "grad_norm": 16.875,
      "learning_rate": 2.9999703715352533e-05,
      "loss": 1.1907646179199218,
      "step": 100
    },
    {
      "epoch": 0.07761966364812418,
      "grad_norm": 17.75,
      "learning_rate": 2.9994436758334273e-05,
      "loss": 1.1301493644714355,
      "step": 120
    },
    {
      "epoch": 0.09055627425614489,
      "grad_norm": 14.75,
      "learning_rate": 2.99825883590465e-05,
      "loss": 1.0869491577148438,
      "step": 140
    },
    {
      "epoch": 0.1034928848641656,
      "grad_norm": 14.8125,
      "learning_rate": 2.996416371805506e-05,
      "loss": 1.110787582397461,
      "step": 160
    },
    {
      "epoch": 0.11642949547218628,
      "grad_norm": 13.8125,
      "learning_rate": 2.993917092240671e-05,
      "loss": 1.0729108810424806,
      "step": 180
    },
    {
      "epoch": 0.129366106080207,
      "grad_norm": 14.875,
      "learning_rate": 2.9907620942079466e-05,
      "loss": 1.053565788269043,
      "step": 200
    },
    {
      "epoch": 0.1423027166882277,
      "grad_norm": 15.75,
      "learning_rate": 2.9869527625167625e-05,
      "loss": 1.0564311027526856,
      "step": 220
    },
    {
      "epoch": 0.15523932729624837,
      "grad_norm": 14.8125,
      "learning_rate": 2.9824907691803472e-05,
      "loss": 1.0384727478027345,
      "step": 240
    },
    {
      "epoch": 0.16817593790426907,
      "grad_norm": 15.375,
      "learning_rate": 2.9773780726818387e-05,
      "loss": 1.0262683868408202,
      "step": 260
    },
    {
      "epoch": 0.18111254851228978,
      "grad_norm": 13.625,
      "learning_rate": 2.9716169171146555e-05,
      "loss": 1.0013815879821777,
      "step": 280
    },
    {
      "epoch": 0.19404915912031048,
      "grad_norm": 14.5625,
      "learning_rate": 2.9652098311975067e-05,
      "loss": 0.9780637741088867,
      "step": 300
    },
    {
      "epoch": 0.2069857697283312,
      "grad_norm": 14.9375,
      "learning_rate": 2.958159627164474e-05,
      "loss": 1.0026420593261718,
      "step": 320
    },
    {
      "epoch": 0.21992238033635186,
      "grad_norm": 14.9375,
      "learning_rate": 2.950469399530648e-05,
      "loss": 0.9584225654602051,
      "step": 340
    },
    {
      "epoch": 0.23285899094437257,
      "grad_norm": 15.5625,
      "learning_rate": 2.9421425237338687e-05,
      "loss": 0.9502490043640137,
      "step": 360
    },
    {
      "epoch": 0.24579560155239327,
      "grad_norm": 15.3125,
      "learning_rate": 2.9331826546531567e-05,
      "loss": 0.9553407669067383,
      "step": 380
    },
    {
      "epoch": 0.258732212160414,
      "grad_norm": 13.3125,
      "learning_rate": 2.923593725004495e-05,
      "loss": 0.9429496765136719,
      "step": 400
    },
    {
      "epoch": 0.2716688227684347,
      "grad_norm": 14.125,
      "learning_rate": 2.913379943614659e-05,
      "loss": 0.9173901557922364,
      "step": 420
    },
    {
      "epoch": 0.2846054333764554,
      "grad_norm": 13.5,
      "learning_rate": 2.902545793573855e-05,
      "loss": 0.9086675643920898,
      "step": 440
    },
    {
      "epoch": 0.2975420439844761,
      "grad_norm": 13.5,
      "learning_rate": 2.891096030267975e-05,
      "loss": 0.9309076309204102,
      "step": 460
    },
    {
      "epoch": 0.31047865459249674,
      "grad_norm": 13.8125,
      "learning_rate": 2.8790356792913394e-05,
      "loss": 0.9496879577636719,
      "step": 480
    },
    {
      "epoch": 0.32341526520051744,
      "grad_norm": 14.125,
      "learning_rate": 2.8663700342408317e-05,
      "loss": 0.9192771911621094,
      "step": 500
    },
    {
      "epoch": 0.32341526520051744,
      "eval_loss": 0.9593508243560791,
      "eval_runtime": 3.5871,
      "eval_samples_per_second": 278.777,
      "eval_steps_per_second": 17.563,
      "step": 500
    },
    {
      "epoch": 0.33635187580853815,
      "grad_norm": 15.0625,
      "learning_rate": 2.8531046543924058e-05,
      "loss": 0.8811090469360352,
      "step": 520
    },
    {
      "epoch": 0.34928848641655885,
      "grad_norm": 15.3125,
      "learning_rate": 2.8392453622609753e-05,
      "loss": 0.9051164627075196,
      "step": 540
    },
    {
      "epoch": 0.36222509702457956,
      "grad_norm": 13.0625,
      "learning_rate": 2.8247982410447645e-05,
      "loss": 0.8812146186828613,
      "step": 560
    },
    {
      "epoch": 0.37516170763260026,
      "grad_norm": 12.0625,
      "learning_rate": 2.809769631955236e-05,
      "loss": 0.8581778526306152,
      "step": 580
    },
    {
      "epoch": 0.38809831824062097,
      "grad_norm": 13.9375,
      "learning_rate": 2.7941661314337705e-05,
      "loss": 0.8675400733947753,
      "step": 600
    },
    {
      "epoch": 0.40103492884864167,
      "grad_norm": 13.125,
      "learning_rate": 2.7779945882563206e-05,
      "loss": 0.9004356384277343,
      "step": 620
    },
    {
      "epoch": 0.4139715394566624,
      "grad_norm": 12.25,
      "learning_rate": 2.7612621005273056e-05,
      "loss": 0.873634147644043,
      "step": 640
    },
    {
      "epoch": 0.4269081500646831,
      "grad_norm": 14.1875,
      "learning_rate": 2.743976012564074e-05,
      "loss": 0.8460257530212403,
      "step": 660
    },
    {
      "epoch": 0.4398447606727037,
      "grad_norm": 13.4375,
      "learning_rate": 2.726143911673294e-05,
      "loss": 0.8405647277832031,
      "step": 680
    },
    {
      "epoch": 0.45278137128072443,
      "grad_norm": 16.875,
      "learning_rate": 2.7077736248206893e-05,
      "loss": 0.8453819274902343,
      "step": 700
    },
    {
      "epoch": 0.46571798188874514,
      "grad_norm": 13.9375,
      "learning_rate": 2.6888732151955844e-05,
      "loss": 0.8592178344726562,
      "step": 720
    },
    {
      "epoch": 0.47865459249676584,
      "grad_norm": 12.5625,
      "learning_rate": 2.6694509786717633e-05,
      "loss": 0.8476343154907227,
      "step": 740
    },
    {
      "epoch": 0.49159120310478654,
      "grad_norm": 12.75,
      "learning_rate": 2.6495154401662e-05,
      "loss": 0.8473175048828125,
      "step": 760
    },
    {
      "epoch": 0.5045278137128072,
      "grad_norm": 11.375,
      "learning_rate": 2.6290753498972524e-05,
      "loss": 0.8494660377502441,
      "step": 780
    },
    {
      "epoch": 0.517464424320828,
      "grad_norm": 15.3125,
      "learning_rate": 2.608139679543967e-05,
      "loss": 0.8422477722167969,
      "step": 800
    },
    {
      "epoch": 0.5304010349288486,
      "grad_norm": 11.75,
      "learning_rate": 2.5867176183081807e-05,
      "loss": 0.8139877319335938,
      "step": 820
    },
    {
      "epoch": 0.5433376455368694,
      "grad_norm": 12.5,
      "learning_rate": 2.5648185688811447e-05,
      "loss": 0.8268013954162597,
      "step": 840
    },
    {
      "epoch": 0.55627425614489,
      "grad_norm": 13.0,
      "learning_rate": 2.5424521433164417e-05,
      "loss": 0.8338586807250976,
      "step": 860
    },
    {
      "epoch": 0.5692108667529108,
      "grad_norm": 12.6875,
      "learning_rate": 2.5196281588110092e-05,
      "loss": 0.8048771858215332,
      "step": 880
    },
    {
      "epoch": 0.5821474773609314,
      "grad_norm": 13.5,
      "learning_rate": 2.4963566333961215e-05,
      "loss": 0.7965430736541748,
      "step": 900
    },
    {
      "epoch": 0.5950840879689522,
      "grad_norm": 12.125,
      "learning_rate": 2.4726477815402184e-05,
      "loss": 0.8183444976806641,
      "step": 920
    },
    {
      "epoch": 0.6080206985769728,
      "grad_norm": 14.8125,
      "learning_rate": 2.4485120096655135e-05,
      "loss": 0.8242772102355957,
      "step": 940
    },
    {
      "epoch": 0.6209573091849935,
      "grad_norm": 13.625,
      "learning_rate": 2.4239599115803503e-05,
      "loss": 0.7966475486755371,
      "step": 960
    },
    {
      "epoch": 0.6338939197930142,
      "grad_norm": 12.4375,
      "learning_rate": 2.3990022638293057e-05,
      "loss": 0.8260826110839844,
      "step": 980
    },
    {
      "epoch": 0.6468305304010349,
      "grad_norm": 11.625,
      "learning_rate": 2.3736500209630912e-05,
      "loss": 0.8220609664916992,
      "step": 1000
    },
    {
      "epoch": 0.6468305304010349,
      "eval_loss": 0.84493088722229,
      "eval_runtime": 3.5809,
      "eval_samples_per_second": 279.256,
      "eval_steps_per_second": 17.593,
      "step": 1000
    },
    {
      "epoch": 0.6597671410090556,
      "grad_norm": 12.9375,
      "learning_rate": 2.347914310730319e-05,
      "loss": 0.7900243759155273,
      "step": 1020
    },
    {
      "epoch": 0.6727037516170763,
      "grad_norm": 13.125,
      "learning_rate": 2.321806429193248e-05,
      "loss": 0.8057157516479492,
      "step": 1040
    },
    {
      "epoch": 0.685640362225097,
      "grad_norm": 14.625,
      "learning_rate": 2.2953378357696538e-05,
      "loss": 0.8044325828552246,
      "step": 1060
    },
    {
      "epoch": 0.6985769728331177,
      "grad_norm": 13.75,
      "learning_rate": 2.2685201482029947e-05,
      "loss": 0.7539340019226074,
      "step": 1080
    },
    {
      "epoch": 0.7115135834411385,
      "grad_norm": 12.5,
      "learning_rate": 2.2413651374630893e-05,
      "loss": 0.8080535888671875,
      "step": 1100
    },
    {
      "epoch": 0.7244501940491591,
      "grad_norm": 13.6875,
      "learning_rate": 2.213884722579535e-05,
      "loss": 0.7553905963897705,
      "step": 1120
    },
    {
      "epoch": 0.7373868046571799,
      "grad_norm": 13.6875,
      "learning_rate": 2.1860909654101394e-05,
      "loss": 0.7784384250640869,
      "step": 1140
    },
    {
      "epoch": 0.7503234152652005,
      "grad_norm": 11.5625,
      "learning_rate": 2.1579960653466655e-05,
      "loss": 0.7598025798797607,
      "step": 1160
    },
    {
      "epoch": 0.7632600258732212,
      "grad_norm": 13.5625,
      "learning_rate": 2.129612353960202e-05,
      "loss": 0.7659223079681396,
      "step": 1180
    },
    {
      "epoch": 0.7761966364812419,
      "grad_norm": 14.0,
      "learning_rate": 2.1009522895885247e-05,
      "loss": 0.7532745361328125,
      "step": 1200
    },
    {
      "epoch": 0.7891332470892626,
      "grad_norm": 11.0,
      "learning_rate": 2.0720284518678106e-05,
      "loss": 0.772769832611084,
      "step": 1220
    },
    {
      "epoch": 0.8020698576972833,
      "grad_norm": 12.3125,
      "learning_rate": 2.042853536211115e-05,
      "loss": 0.7571600914001465,
      "step": 1240
    },
    {
      "epoch": 0.815006468305304,
      "grad_norm": 12.8125,
      "learning_rate": 2.0134403482360276e-05,
      "loss": 0.7337167739868165,
      "step": 1260
    },
    {
      "epoch": 0.8279430789133247,
      "grad_norm": 12.875,
      "learning_rate": 1.9838017981439626e-05,
      "loss": 0.7278430938720704,
      "step": 1280
    },
    {
      "epoch": 0.8408796895213454,
      "grad_norm": 12.0,
      "learning_rate": 1.9539508950535352e-05,
      "loss": 0.759502649307251,
      "step": 1300
    },
    {
      "epoch": 0.8538163001293662,
      "grad_norm": 12.375,
      "learning_rate": 1.9239007412905325e-05,
      "loss": 0.7547530651092529,
      "step": 1320
    },
    {
      "epoch": 0.8667529107373868,
      "grad_norm": 9.9375,
      "learning_rate": 1.8936645266369623e-05,
      "loss": 0.7525947093963623,
      "step": 1340
    },
    {
      "epoch": 0.8796895213454075,
      "grad_norm": 13.4375,
      "learning_rate": 1.8632555225417225e-05,
      "loss": 0.7163672924041748,
      "step": 1360
    },
    {
      "epoch": 0.8926261319534282,
      "grad_norm": 11.4375,
      "learning_rate": 1.832687076295422e-05,
      "loss": 0.7244317531585693,
      "step": 1380
    },
    {
      "epoch": 0.9055627425614489,
      "grad_norm": 12.1875,
      "learning_rate": 1.8019726051719128e-05,
      "loss": 0.7380789756774903,
      "step": 1400
    },
    {
      "epoch": 0.9184993531694696,
      "grad_norm": 14.375,
      "learning_rate": 1.7711255905391042e-05,
      "loss": 0.7752026557922364,
      "step": 1420
    },
    {
      "epoch": 0.9314359637774903,
      "grad_norm": 11.3125,
      "learning_rate": 1.7401595719416462e-05,
      "loss": 0.7437917709350585,
      "step": 1440
    },
    {
      "epoch": 0.944372574385511,
      "grad_norm": 12.4375,
      "learning_rate": 1.709088141158077e-05,
      "loss": 0.7368851184844971,
      "step": 1460
    },
    {
      "epoch": 0.9573091849935317,
      "grad_norm": 13.1875,
      "learning_rate": 1.6779249362350416e-05,
      "loss": 0.7322164535522461,
      "step": 1480
    },
    {
      "epoch": 0.9702457956015524,
      "grad_norm": 12.5,
      "learning_rate": 1.6466836355012052e-05,
      "loss": 0.7210765361785889,
      "step": 1500
    },
    {
      "epoch": 0.9702457956015524,
      "eval_loss": 0.7690591812133789,
      "eval_runtime": 3.5483,
      "eval_samples_per_second": 281.823,
      "eval_steps_per_second": 17.755,
      "step": 1500
    }
  ],
  "logging_steps": 20,
  "max_steps": 3092,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5769814126238106e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}