{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1111111111111112,
  "eval_steps": 30,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 0.7641538977622986,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4714,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.05706603452563286,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0194,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.007792987395077944,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0044,
      "step": 30
    },
    {
      "epoch": 0.06666666666666667,
      "eval_loss": 0.004266363102942705,
      "eval_runtime": 215.0719,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 30
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.013519592583179474,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0041,
      "step": 40
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.017202626913785934,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.004,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.009044675156474113,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0039,
      "step": 60
    },
    {
      "epoch": 0.13333333333333333,
      "eval_loss": 0.003868637140840292,
      "eval_runtime": 214.9966,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 60
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 0.007734662853181362,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0039,
      "step": 70
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.00847636815160513,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0038,
      "step": 80
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.010983753949403763,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0039,
      "step": 90
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.0037890244275331497,
      "eval_runtime": 215.057,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.232,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.039544351398944855,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0038,
      "step": 100
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 0.011466417461633682,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0038,
      "step": 110
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.020617613568902016,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0038,
      "step": 120
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.0038526125717908144,
      "eval_runtime": 214.983,
      "eval_samples_per_second": 9.303,
      "eval_steps_per_second": 0.233,
      "step": 120
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 0.012847725301980972,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0038,
      "step": 130
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.02477414160966873,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0038,
      "step": 140
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.014771663583815098,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0038,
      "step": 150
    },
    {
      "epoch": 0.3333333333333333,
      "eval_loss": 0.003661703085526824,
      "eval_runtime": 215.005,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 150
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.017922697588801384,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0037,
      "step": 160
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 0.033902786672115326,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0036,
      "step": 170
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.020672762766480446,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0036,
      "step": 180
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.0034463535994291306,
      "eval_runtime": 215.0519,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.233,
      "step": 180
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 0.021494735032320023,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0035,
      "step": 190
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.03562169522047043,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0032,
      "step": 200
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 0.014103920198976994,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0034,
      "step": 210
    },
    {
      "epoch": 0.4666666666666667,
      "eval_loss": 0.003306599799543619,
      "eval_runtime": 215.0517,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.233,
      "step": 210
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.019676154479384422,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0032,
      "step": 220
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 0.011821040883660316,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0034,
      "step": 230
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.010281533934175968,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0028,
      "step": 240
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 0.0027289013378322124,
      "eval_runtime": 215.069,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 240
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.0231550931930542,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0028,
      "step": 250
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.02239130064845085,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0029,
      "step": 260
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.022564468905329704,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0026,
      "step": 270
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.002367404056712985,
      "eval_runtime": 215.0087,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 270
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.01638098619878292,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0024,
      "step": 280
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 0.03278963640332222,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0024,
      "step": 290
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.03586648404598236,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0022,
      "step": 300
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.002185327000916004,
      "eval_runtime": 215.0432,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.233,
      "step": 300
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 0.018881576135754585,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0022,
      "step": 310
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.062055736780166626,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0019,
      "step": 320
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 0.02213781699538231,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0025,
      "step": 330
    },
    {
      "epoch": 0.7333333333333333,
      "eval_loss": 0.002024175366386771,
      "eval_runtime": 215.0776,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 330
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.030647626146674156,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0021,
      "step": 340
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.02288457192480564,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.002,
      "step": 350
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.021721992641687393,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0019,
      "step": 360
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.0019156673224642873,
      "eval_runtime": 215.0243,
      "eval_samples_per_second": 9.301,
      "eval_steps_per_second": 0.233,
      "step": 360
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 0.028448602184653282,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0018,
      "step": 370
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.017557110637426376,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0018,
      "step": 380
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 0.026540469378232956,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0021,
      "step": 390
    },
    {
      "epoch": 0.8666666666666667,
      "eval_loss": 0.0018348968587815762,
      "eval_runtime": 214.9922,
      "eval_samples_per_second": 9.303,
      "eval_steps_per_second": 0.233,
      "step": 390
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.015121403150260448,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0016,
      "step": 400
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 0.035505831241607666,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0016,
      "step": 410
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.0437658354640007,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0017,
      "step": 420
    },
    {
      "epoch": 0.9333333333333333,
      "eval_loss": 0.001731859752908349,
      "eval_runtime": 215.067,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 420
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 0.02948390692472458,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0018,
      "step": 430
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.031176254153251648,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0017,
      "step": 440
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.020768124610185623,
      "learning_rate": 5e-05,
      "loss": 0.0017,
      "step": 450
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.0017366266110911965,
      "eval_runtime": 215.0611,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.232,
      "step": 450
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 0.01959955506026745,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0016,
      "step": 460
    },
    {
      "epoch": 1.0444444444444445,
      "grad_norm": 0.028036223724484444,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0017,
      "step": 470
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.017765428870916367,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0017,
      "step": 480
    },
    {
      "epoch": 1.0666666666666667,
      "eval_loss": 0.0016992929158732295,
      "eval_runtime": 215.0184,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 480
    },
    {
      "epoch": 1.0888888888888888,
      "grad_norm": 0.023638742044568062,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0017,
      "step": 490
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.042691878974437714,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0017,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 900,
  "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": 1.8448427159723704e+18,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}