{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8764721993974254,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021911804984935633,
      "grad_norm": 0.14338380098342896,
      "learning_rate": 7.6e-05,
      "loss": 0.578131914138794,
      "step": 20
    },
    {
      "epoch": 0.043823609969871266,
      "grad_norm": 0.043006837368011475,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.3712817430496216,
      "step": 40
    },
    {
      "epoch": 0.0657354149548069,
      "grad_norm": 0.05703941732645035,
      "learning_rate": 0.00019994633460515538,
      "loss": 0.3367295265197754,
      "step": 60
    },
    {
      "epoch": 0.08764721993974253,
      "grad_norm": 0.04901430010795593,
      "learning_rate": 0.00019944327493951773,
      "loss": 0.3087886571884155,
      "step": 80
    },
    {
      "epoch": 0.10955902492467817,
      "grad_norm": 0.06868838518857956,
      "learning_rate": 0.00019841332314076855,
      "loss": 0.3139586210250854,
      "step": 100
    },
    {
      "epoch": 0.1314708299096138,
      "grad_norm": 0.07925613969564438,
      "learning_rate": 0.00019686193632504338,
      "loss": 0.28915910720825194,
      "step": 120
    },
    {
      "epoch": 0.15338263489454945,
      "grad_norm": 0.07879550755023956,
      "learning_rate": 0.00019479733438965667,
      "loss": 0.2889900207519531,
      "step": 140
    },
    {
      "epoch": 0.17529443987948506,
      "grad_norm": 0.06741970777511597,
      "learning_rate": 0.00019223045646064212,
      "loss": 0.27687640190124513,
      "step": 160
    },
    {
      "epoch": 0.1972062448644207,
      "grad_norm": 0.062402546405792236,
      "learning_rate": 0.00018917490293267973,
      "loss": 0.2929875135421753,
      "step": 180
    },
    {
      "epoch": 0.21911804984935634,
      "grad_norm": 0.07164579629898071,
      "learning_rate": 0.00018564686340850708,
      "loss": 0.2802800893783569,
      "step": 200
    },
    {
      "epoch": 0.21911804984935634,
      "eval_loss": 0.2665560841560364,
      "eval_runtime": 78.0807,
      "eval_samples_per_second": 4.278,
      "eval_steps_per_second": 1.076,
      "step": 200
    },
    {
      "epoch": 0.24102985483429198,
      "grad_norm": 0.06281758099794388,
      "learning_rate": 0.0001816650309196209,
      "loss": 0.2850670576095581,
      "step": 220
    },
    {
      "epoch": 0.2629416598192276,
      "grad_norm": 0.05580520257353783,
      "learning_rate": 0.000177250502882765,
      "loss": 0.2707890510559082,
      "step": 240
    },
    {
      "epoch": 0.28485346480416324,
      "grad_norm": 0.0578630194067955,
      "learning_rate": 0.0001724266693169772,
      "loss": 0.2684861898422241,
      "step": 260
    },
    {
      "epoch": 0.3067652697890989,
      "grad_norm": 0.056395046412944794,
      "learning_rate": 0.0001672190889134691,
      "loss": 0.27494494915008544,
      "step": 280
    },
    {
      "epoch": 0.3286770747740345,
      "grad_norm": 0.06928149610757828,
      "learning_rate": 0.00016165535361497218,
      "loss": 0.27622313499450685,
      "step": 300
    },
    {
      "epoch": 0.35058887975897013,
      "grad_norm": 0.06063492223620415,
      "learning_rate": 0.00015576494242206508,
      "loss": 0.26791768074035643,
      "step": 320
    },
    {
      "epoch": 0.3725006847439058,
      "grad_norm": 0.052748970687389374,
      "learning_rate": 0.00014957906520107845,
      "loss": 0.2828014373779297,
      "step": 340
    },
    {
      "epoch": 0.3944124897288414,
      "grad_norm": 0.05597842484712601,
      "learning_rate": 0.00014313049732114715,
      "loss": 0.27218098640441896,
      "step": 360
    },
    {
      "epoch": 0.416324294713777,
      "grad_norm": 0.054700642824172974,
      "learning_rate": 0.0001364534059965735,
      "loss": 0.258621072769165,
      "step": 380
    },
    {
      "epoch": 0.4382360996987127,
      "grad_norm": 0.06639006733894348,
      "learning_rate": 0.00012958316925461085,
      "loss": 0.26321959495544434,
      "step": 400
    },
    {
      "epoch": 0.4382360996987127,
      "eval_loss": 0.25228193402290344,
      "eval_runtime": 76.7593,
      "eval_samples_per_second": 4.351,
      "eval_steps_per_second": 1.094,
      "step": 400
    },
    {
      "epoch": 0.4601479046836483,
      "grad_norm": 0.04828259348869324,
      "learning_rate": 0.00012255618848785378,
      "loss": 0.2582087993621826,
      "step": 420
    },
    {
      "epoch": 0.48205970966858397,
      "grad_norm": 0.09414570778608322,
      "learning_rate": 0.0001154096955844091,
      "loss": 0.26802127361297606,
      "step": 440
    },
    {
      "epoch": 0.5039715146535196,
      "grad_norm": 0.06418801099061966,
      "learning_rate": 0.00010818155565775443,
      "loss": 0.2587978601455688,
      "step": 460
    },
    {
      "epoch": 0.5258833196384552,
      "grad_norm": 0.059086013585329056,
      "learning_rate": 0.0001009100664215028,
      "loss": 0.26389484405517577,
      "step": 480
    },
    {
      "epoch": 0.5477951246233909,
      "grad_norm": 0.05814081430435181,
      "learning_rate": 9.363375527207111e-05,
      "loss": 0.2642557144165039,
      "step": 500
    },
    {
      "epoch": 0.5697069296083265,
      "grad_norm": 0.060968417674303055,
      "learning_rate": 8.639117515439248e-05,
      "loss": 0.2558141708374023,
      "step": 520
    },
    {
      "epoch": 0.5916187345932621,
      "grad_norm": 0.04676595702767372,
      "learning_rate": 7.92207002922618e-05,
      "loss": 0.25071308612823484,
      "step": 540
    },
    {
      "epoch": 0.6135305395781978,
      "grad_norm": 0.055148206651210785,
      "learning_rate": 7.216032286562122e-05,
      "loss": 0.25150718688964846,
      "step": 560
    },
    {
      "epoch": 0.6354423445631334,
      "grad_norm": 0.05283847823739052,
      "learning_rate": 6.524745171207339e-05,
      "loss": 0.2621228933334351,
      "step": 580
    },
    {
      "epoch": 0.657354149548069,
      "grad_norm": 0.05972014740109444,
      "learning_rate": 5.851871411918743e-05,
      "loss": 0.262609076499939,
      "step": 600
    },
    {
      "epoch": 0.657354149548069,
      "eval_loss": 0.24315646290779114,
      "eval_runtime": 76.7442,
      "eval_samples_per_second": 4.352,
      "eval_steps_per_second": 1.095,
      "step": 600
    },
    {
      "epoch": 0.6792659545330046,
      "grad_norm": 0.0542420968413353,
      "learning_rate": 5.20097617577839e-05,
      "loss": 0.24464335441589355,
      "step": 620
    },
    {
      "epoch": 0.7011777595179403,
      "grad_norm": 0.05391804128885269,
      "learning_rate": 4.5755081784446306e-05,
      "loss": 0.23991961479187013,
      "step": 640
    },
    {
      "epoch": 0.7230895645028759,
      "grad_norm": 0.067460797727108,
      "learning_rate": 3.978781411411705e-05,
      "loss": 0.25521044731140136,
      "step": 660
    },
    {
      "epoch": 0.7450013694878116,
      "grad_norm": 0.060182541608810425,
      "learning_rate": 3.413957583094358e-05,
      "loss": 0.25919690132141116,
      "step": 680
    },
    {
      "epoch": 0.7669131744727472,
      "grad_norm": 0.05970674753189087,
      "learning_rate": 2.8840293667720653e-05,
      "loss": 0.25497357845306395,
      "step": 700
    },
    {
      "epoch": 0.7888249794576828,
      "grad_norm": 0.05807078629732132,
      "learning_rate": 2.3918045441521718e-05,
      "loss": 0.2616193532943726,
      "step": 720
    },
    {
      "epoch": 0.8107367844426184,
      "grad_norm": 0.07185934484004974,
      "learning_rate": 1.9398911285660816e-05,
      "loss": 0.25238714218139646,
      "step": 740
    },
    {
      "epoch": 0.832648589427554,
      "grad_norm": 0.05691298842430115,
      "learning_rate": 1.5306835466219738e-05,
      "loss": 0.25438358783721926,
      "step": 760
    },
    {
      "epoch": 0.8545603944124898,
      "grad_norm": 0.05606130138039589,
      "learning_rate": 1.1663499515294762e-05,
      "loss": 0.23820433616638184,
      "step": 780
    },
    {
      "epoch": 0.8764721993974254,
      "grad_norm": 0.05140916630625725,
      "learning_rate": 8.488207353155986e-06,
      "loss": 0.26239197254180907,
      "step": 800
    },
    {
      "epoch": 0.8764721993974254,
      "eval_loss": 0.23945921659469604,
      "eval_runtime": 76.7615,
      "eval_samples_per_second": 4.351,
      "eval_steps_per_second": 1.094,
      "step": 800
    }
  ],
  "logging_steps": 20,
  "max_steps": 913,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.475205602097205e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}