{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9955423476968797,
  "eval_steps": 500,
  "global_step": 756,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0396235760277365,
      "grad_norm": 27.41085149828123,
      "learning_rate": 5e-06,
      "loss": 1.0725,
      "step": 10
    },
    {
      "epoch": 0.079247152055473,
      "grad_norm": 21.426346851591315,
      "learning_rate": 5e-06,
      "loss": 0.9867,
      "step": 20
    },
    {
      "epoch": 0.1188707280832095,
      "grad_norm": 0.8214529838984242,
      "learning_rate": 5e-06,
      "loss": 0.9489,
      "step": 30
    },
    {
      "epoch": 0.158494304110946,
      "grad_norm": 0.8934541351618693,
      "learning_rate": 5e-06,
      "loss": 0.9168,
      "step": 40
    },
    {
      "epoch": 0.1981178801386825,
      "grad_norm": 0.6396922311734878,
      "learning_rate": 5e-06,
      "loss": 0.903,
      "step": 50
    },
    {
      "epoch": 0.237741456166419,
      "grad_norm": 0.8318834132473311,
      "learning_rate": 5e-06,
      "loss": 0.884,
      "step": 60
    },
    {
      "epoch": 0.27736503219415554,
      "grad_norm": 0.6283992782157446,
      "learning_rate": 5e-06,
      "loss": 0.8732,
      "step": 70
    },
    {
      "epoch": 0.316988608221892,
      "grad_norm": 0.6596849388425453,
      "learning_rate": 5e-06,
      "loss": 0.8701,
      "step": 80
    },
    {
      "epoch": 0.35661218424962854,
      "grad_norm": 0.6758187675410737,
      "learning_rate": 5e-06,
      "loss": 0.8641,
      "step": 90
    },
    {
      "epoch": 0.396235760277365,
      "grad_norm": 1.0513265622155463,
      "learning_rate": 5e-06,
      "loss": 0.8597,
      "step": 100
    },
    {
      "epoch": 0.43585933630510154,
      "grad_norm": 0.5790780273693242,
      "learning_rate": 5e-06,
      "loss": 0.8538,
      "step": 110
    },
    {
      "epoch": 0.475482912332838,
      "grad_norm": 0.5821582037832116,
      "learning_rate": 5e-06,
      "loss": 0.8493,
      "step": 120
    },
    {
      "epoch": 0.5151064883605745,
      "grad_norm": 0.6354797019513801,
      "learning_rate": 5e-06,
      "loss": 0.8491,
      "step": 130
    },
    {
      "epoch": 0.5547300643883111,
      "grad_norm": 0.74047379799972,
      "learning_rate": 5e-06,
      "loss": 0.8519,
      "step": 140
    },
    {
      "epoch": 0.5943536404160475,
      "grad_norm": 0.6926741472374109,
      "learning_rate": 5e-06,
      "loss": 0.8388,
      "step": 150
    },
    {
      "epoch": 0.633977216443784,
      "grad_norm": 0.5805929955993835,
      "learning_rate": 5e-06,
      "loss": 0.842,
      "step": 160
    },
    {
      "epoch": 0.6736007924715206,
      "grad_norm": 0.6028836834161021,
      "learning_rate": 5e-06,
      "loss": 0.8381,
      "step": 170
    },
    {
      "epoch": 0.7132243684992571,
      "grad_norm": 0.5654340386019846,
      "learning_rate": 5e-06,
      "loss": 0.8341,
      "step": 180
    },
    {
      "epoch": 0.7528479445269936,
      "grad_norm": 0.5723158352099399,
      "learning_rate": 5e-06,
      "loss": 0.8375,
      "step": 190
    },
    {
      "epoch": 0.79247152055473,
      "grad_norm": 0.5198688688930553,
      "learning_rate": 5e-06,
      "loss": 0.8381,
      "step": 200
    },
    {
      "epoch": 0.8320950965824666,
      "grad_norm": 0.6050739761187648,
      "learning_rate": 5e-06,
      "loss": 0.8342,
      "step": 210
    },
    {
      "epoch": 0.8717186726102031,
      "grad_norm": 0.5397219218505803,
      "learning_rate": 5e-06,
      "loss": 0.8308,
      "step": 220
    },
    {
      "epoch": 0.9113422486379396,
      "grad_norm": 0.5613324111744644,
      "learning_rate": 5e-06,
      "loss": 0.8302,
      "step": 230
    },
    {
      "epoch": 0.950965824665676,
      "grad_norm": 0.5372566937252206,
      "learning_rate": 5e-06,
      "loss": 0.8272,
      "step": 240
    },
    {
      "epoch": 0.9905894006934126,
      "grad_norm": 0.4784741594645362,
      "learning_rate": 5e-06,
      "loss": 0.8269,
      "step": 250
    },
    {
      "epoch": 0.9985141158989599,
      "eval_loss": 0.8291837573051453,
      "eval_runtime": 271.0608,
      "eval_samples_per_second": 25.083,
      "eval_steps_per_second": 0.395,
      "step": 252
    },
    {
      "epoch": 1.030212976721149,
      "grad_norm": 0.87740197973562,
      "learning_rate": 5e-06,
      "loss": 0.8491,
      "step": 260
    },
    {
      "epoch": 1.0698365527488856,
      "grad_norm": 0.5678119260366427,
      "learning_rate": 5e-06,
      "loss": 0.785,
      "step": 270
    },
    {
      "epoch": 1.1094601287766221,
      "grad_norm": 0.6337004334606812,
      "learning_rate": 5e-06,
      "loss": 0.7887,
      "step": 280
    },
    {
      "epoch": 1.1490837048043585,
      "grad_norm": 0.6986139436792874,
      "learning_rate": 5e-06,
      "loss": 0.7862,
      "step": 290
    },
    {
      "epoch": 1.188707280832095,
      "grad_norm": 0.5874593683473379,
      "learning_rate": 5e-06,
      "loss": 0.7793,
      "step": 300
    },
    {
      "epoch": 1.2283308568598317,
      "grad_norm": 0.7975693973340302,
      "learning_rate": 5e-06,
      "loss": 0.7795,
      "step": 310
    },
    {
      "epoch": 1.267954432887568,
      "grad_norm": 0.5846939921280547,
      "learning_rate": 5e-06,
      "loss": 0.7798,
      "step": 320
    },
    {
      "epoch": 1.3075780089153046,
      "grad_norm": 0.7654979422005525,
      "learning_rate": 5e-06,
      "loss": 0.7832,
      "step": 330
    },
    {
      "epoch": 1.3472015849430412,
      "grad_norm": 0.6496190339072363,
      "learning_rate": 5e-06,
      "loss": 0.7835,
      "step": 340
    },
    {
      "epoch": 1.3868251609707776,
      "grad_norm": 0.7019021685342436,
      "learning_rate": 5e-06,
      "loss": 0.7841,
      "step": 350
    },
    {
      "epoch": 1.4264487369985142,
      "grad_norm": 0.697904784471384,
      "learning_rate": 5e-06,
      "loss": 0.7809,
      "step": 360
    },
    {
      "epoch": 1.4660723130262507,
      "grad_norm": 0.6140987998837893,
      "learning_rate": 5e-06,
      "loss": 0.7839,
      "step": 370
    },
    {
      "epoch": 1.505695889053987,
      "grad_norm": 0.6176502513567036,
      "learning_rate": 5e-06,
      "loss": 0.78,
      "step": 380
    },
    {
      "epoch": 1.5453194650817235,
      "grad_norm": 0.6195463728584585,
      "learning_rate": 5e-06,
      "loss": 0.7812,
      "step": 390
    },
    {
      "epoch": 1.5849430411094603,
      "grad_norm": 0.5860977422231922,
      "learning_rate": 5e-06,
      "loss": 0.7855,
      "step": 400
    },
    {
      "epoch": 1.6245666171371966,
      "grad_norm": 0.6058978073304615,
      "learning_rate": 5e-06,
      "loss": 0.7826,
      "step": 410
    },
    {
      "epoch": 1.664190193164933,
      "grad_norm": 0.5726428056331896,
      "learning_rate": 5e-06,
      "loss": 0.7767,
      "step": 420
    },
    {
      "epoch": 1.7038137691926698,
      "grad_norm": 0.6255990916494661,
      "learning_rate": 5e-06,
      "loss": 0.7776,
      "step": 430
    },
    {
      "epoch": 1.7434373452204062,
      "grad_norm": 0.621833549178633,
      "learning_rate": 5e-06,
      "loss": 0.7786,
      "step": 440
    },
    {
      "epoch": 1.7830609212481425,
      "grad_norm": 0.5435896897432534,
      "learning_rate": 5e-06,
      "loss": 0.7775,
      "step": 450
    },
    {
      "epoch": 1.8226844972758791,
      "grad_norm": 0.7495004498554898,
      "learning_rate": 5e-06,
      "loss": 0.7759,
      "step": 460
    },
    {
      "epoch": 1.8623080733036157,
      "grad_norm": 0.5987267949701414,
      "learning_rate": 5e-06,
      "loss": 0.778,
      "step": 470
    },
    {
      "epoch": 1.901931649331352,
      "grad_norm": 0.6388662201965061,
      "learning_rate": 5e-06,
      "loss": 0.7728,
      "step": 480
    },
    {
      "epoch": 1.9415552253590886,
      "grad_norm": 0.5711439995135582,
      "learning_rate": 5e-06,
      "loss": 0.7817,
      "step": 490
    },
    {
      "epoch": 1.9811788013868252,
      "grad_norm": 0.617975937550618,
      "learning_rate": 5e-06,
      "loss": 0.7778,
      "step": 500
    },
    {
      "epoch": 1.9970282317979198,
      "eval_loss": 0.8146935701370239,
      "eval_runtime": 271.9619,
      "eval_samples_per_second": 25.0,
      "eval_steps_per_second": 0.393,
      "step": 504
    },
    {
      "epoch": 2.0208023774145616,
      "grad_norm": 0.6930015338867856,
      "learning_rate": 5e-06,
      "loss": 0.8016,
      "step": 510
    },
    {
      "epoch": 2.060425953442298,
      "grad_norm": 0.6358377946223995,
      "learning_rate": 5e-06,
      "loss": 0.7316,
      "step": 520
    },
    {
      "epoch": 2.1000495294700348,
      "grad_norm": 0.8278609254484581,
      "learning_rate": 5e-06,
      "loss": 0.7265,
      "step": 530
    },
    {
      "epoch": 2.139673105497771,
      "grad_norm": 0.6962674479421791,
      "learning_rate": 5e-06,
      "loss": 0.7311,
      "step": 540
    },
    {
      "epoch": 2.1792966815255075,
      "grad_norm": 0.6727207101976576,
      "learning_rate": 5e-06,
      "loss": 0.7294,
      "step": 550
    },
    {
      "epoch": 2.2189202575532443,
      "grad_norm": 0.5817825946787325,
      "learning_rate": 5e-06,
      "loss": 0.7307,
      "step": 560
    },
    {
      "epoch": 2.2585438335809807,
      "grad_norm": 0.6436375631599169,
      "learning_rate": 5e-06,
      "loss": 0.7325,
      "step": 570
    },
    {
      "epoch": 2.298167409608717,
      "grad_norm": 0.9292364267574976,
      "learning_rate": 5e-06,
      "loss": 0.7352,
      "step": 580
    },
    {
      "epoch": 2.337790985636454,
      "grad_norm": 0.9489749212265489,
      "learning_rate": 5e-06,
      "loss": 0.7317,
      "step": 590
    },
    {
      "epoch": 2.37741456166419,
      "grad_norm": 0.7240317017944226,
      "learning_rate": 5e-06,
      "loss": 0.7274,
      "step": 600
    },
    {
      "epoch": 2.4170381376919265,
      "grad_norm": 0.6501433881507601,
      "learning_rate": 5e-06,
      "loss": 0.7301,
      "step": 610
    },
    {
      "epoch": 2.4566617137196634,
      "grad_norm": 0.8099751855974757,
      "learning_rate": 5e-06,
      "loss": 0.734,
      "step": 620
    },
    {
      "epoch": 2.4962852897473997,
      "grad_norm": 0.6496005537182832,
      "learning_rate": 5e-06,
      "loss": 0.7361,
      "step": 630
    },
    {
      "epoch": 2.535908865775136,
      "grad_norm": 0.5493051299286916,
      "learning_rate": 5e-06,
      "loss": 0.7327,
      "step": 640
    },
    {
      "epoch": 2.5755324418028724,
      "grad_norm": 0.5890719222816667,
      "learning_rate": 5e-06,
      "loss": 0.7346,
      "step": 650
    },
    {
      "epoch": 2.6151560178306092,
      "grad_norm": 0.5341897077649945,
      "learning_rate": 5e-06,
      "loss": 0.7314,
      "step": 660
    },
    {
      "epoch": 2.6547795938583456,
      "grad_norm": 0.5921523513579053,
      "learning_rate": 5e-06,
      "loss": 0.7352,
      "step": 670
    },
    {
      "epoch": 2.6944031698860824,
      "grad_norm": 0.5890344658716773,
      "learning_rate": 5e-06,
      "loss": 0.7328,
      "step": 680
    },
    {
      "epoch": 2.734026745913819,
      "grad_norm": 0.5886927133745706,
      "learning_rate": 5e-06,
      "loss": 0.7353,
      "step": 690
    },
    {
      "epoch": 2.773650321941555,
      "grad_norm": 0.7084337230865917,
      "learning_rate": 5e-06,
      "loss": 0.7359,
      "step": 700
    },
    {
      "epoch": 2.8132738979692915,
      "grad_norm": 0.6320863625704357,
      "learning_rate": 5e-06,
      "loss": 0.7289,
      "step": 710
    },
    {
      "epoch": 2.8528974739970283,
      "grad_norm": 0.6406803421798857,
      "learning_rate": 5e-06,
      "loss": 0.7321,
      "step": 720
    },
    {
      "epoch": 2.8925210500247647,
      "grad_norm": 0.5985842168545841,
      "learning_rate": 5e-06,
      "loss": 0.7363,
      "step": 730
    },
    {
      "epoch": 2.9321446260525015,
      "grad_norm": 0.5878885552435451,
      "learning_rate": 5e-06,
      "loss": 0.7317,
      "step": 740
    },
    {
      "epoch": 2.971768202080238,
      "grad_norm": 0.7738327584141713,
      "learning_rate": 5e-06,
      "loss": 0.7327,
      "step": 750
    },
    {
      "epoch": 2.9955423476968797,
      "eval_loss": 0.8128942847251892,
      "eval_runtime": 272.1686,
      "eval_samples_per_second": 24.981,
      "eval_steps_per_second": 0.393,
      "step": 756
    },
    {
      "epoch": 2.9955423476968797,
      "step": 756,
      "total_flos": 1266118777896960.0,
      "train_loss": 0.7958845669630343,
      "train_runtime": 44860.7812,
      "train_samples_per_second": 8.638,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 756,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1266118777896960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}