{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06691201070592172,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033456005352960856,
      "eval_loss": 0.528853178024292,
      "eval_runtime": 39.5233,
      "eval_samples_per_second": 127.393,
      "eval_steps_per_second": 15.94,
      "step": 1
    },
    {
      "epoch": 0.0016728002676480427,
      "grad_norm": 0.0893344134092331,
      "learning_rate": 5e-05,
      "loss": 0.5191,
      "step": 5
    },
    {
      "epoch": 0.0033456005352960855,
      "grad_norm": 0.12134993076324463,
      "learning_rate": 0.0001,
      "loss": 0.584,
      "step": 10
    },
    {
      "epoch": 0.005018400802944129,
      "grad_norm": 0.08858965337276459,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5242,
      "step": 15
    },
    {
      "epoch": 0.006691201070592171,
      "grad_norm": 0.09778374433517456,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.5202,
      "step": 20
    },
    {
      "epoch": 0.008364001338240215,
      "grad_norm": 0.10649651288986206,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4911,
      "step": 25
    },
    {
      "epoch": 0.010036801605888258,
      "grad_norm": 0.06970233470201492,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3985,
      "step": 30
    },
    {
      "epoch": 0.0117096018735363,
      "grad_norm": 0.0955878272652626,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.43,
      "step": 35
    },
    {
      "epoch": 0.013382402141184342,
      "grad_norm": 0.060985565185546875,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4198,
      "step": 40
    },
    {
      "epoch": 0.015055202408832385,
      "grad_norm": 0.0769026130437851,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.4067,
      "step": 45
    },
    {
      "epoch": 0.01672800267648043,
      "grad_norm": 0.1008349359035492,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3662,
      "step": 50
    },
    {
      "epoch": 0.01672800267648043,
      "eval_loss": 0.34106191992759705,
      "eval_runtime": 39.432,
      "eval_samples_per_second": 127.688,
      "eval_steps_per_second": 15.977,
      "step": 50
    },
    {
      "epoch": 0.01840080294412847,
      "grad_norm": 0.07255814969539642,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3496,
      "step": 55
    },
    {
      "epoch": 0.020073603211776515,
      "grad_norm": 0.10015455633401871,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.328,
      "step": 60
    },
    {
      "epoch": 0.021746403479424557,
      "grad_norm": 0.07114718109369278,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3169,
      "step": 65
    },
    {
      "epoch": 0.0234192037470726,
      "grad_norm": 0.07913073152303696,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3134,
      "step": 70
    },
    {
      "epoch": 0.025092004014720642,
      "grad_norm": 0.1750458925962448,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.2852,
      "step": 75
    },
    {
      "epoch": 0.026764804282368684,
      "grad_norm": 0.061932601034641266,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.2737,
      "step": 80
    },
    {
      "epoch": 0.02843760455001673,
      "grad_norm": 0.06881576776504517,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2502,
      "step": 85
    },
    {
      "epoch": 0.03011040481766477,
      "grad_norm": 0.062322817742824554,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2659,
      "step": 90
    },
    {
      "epoch": 0.031783205085312814,
      "grad_norm": 0.06230627000331879,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2645,
      "step": 95
    },
    {
      "epoch": 0.03345600535296086,
      "grad_norm": 0.11283061653375626,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2267,
      "step": 100
    },
    {
      "epoch": 0.03345600535296086,
      "eval_loss": 0.23386509716510773,
      "eval_runtime": 39.348,
      "eval_samples_per_second": 127.961,
      "eval_steps_per_second": 16.011,
      "step": 100
    },
    {
      "epoch": 0.0351288056206089,
      "grad_norm": 0.0672779530286789,
      "learning_rate": 5e-05,
      "loss": 0.2497,
      "step": 105
    },
    {
      "epoch": 0.03680160588825694,
      "grad_norm": 0.06097684055566788,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.2516,
      "step": 110
    },
    {
      "epoch": 0.038474406155904986,
      "grad_norm": 0.06827884912490845,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2279,
      "step": 115
    },
    {
      "epoch": 0.04014720642355303,
      "grad_norm": 0.0606272853910923,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2541,
      "step": 120
    },
    {
      "epoch": 0.04182000669120107,
      "grad_norm": 0.14288191497325897,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.1806,
      "step": 125
    },
    {
      "epoch": 0.04349280695884911,
      "grad_norm": 0.052643969655036926,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.246,
      "step": 130
    },
    {
      "epoch": 0.04516560722649716,
      "grad_norm": 0.06944818049669266,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2419,
      "step": 135
    },
    {
      "epoch": 0.0468384074941452,
      "grad_norm": 0.06182454898953438,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2159,
      "step": 140
    },
    {
      "epoch": 0.04851120776179324,
      "grad_norm": 0.06247089058160782,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2275,
      "step": 145
    },
    {
      "epoch": 0.050184008029441285,
      "grad_norm": 0.1229231059551239,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.1912,
      "step": 150
    },
    {
      "epoch": 0.050184008029441285,
      "eval_loss": 0.2059282809495926,
      "eval_runtime": 39.4366,
      "eval_samples_per_second": 127.673,
      "eval_steps_per_second": 15.975,
      "step": 150
    },
    {
      "epoch": 0.05185680829708933,
      "grad_norm": 0.06170298531651497,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.2107,
      "step": 155
    },
    {
      "epoch": 0.05352960856473737,
      "grad_norm": 0.06112481653690338,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.2021,
      "step": 160
    },
    {
      "epoch": 0.05520240883238541,
      "grad_norm": 0.060423221439123154,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2191,
      "step": 165
    },
    {
      "epoch": 0.05687520910003346,
      "grad_norm": 0.05647290125489235,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2134,
      "step": 170
    },
    {
      "epoch": 0.0585480093676815,
      "grad_norm": 0.10841598361730576,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.212,
      "step": 175
    },
    {
      "epoch": 0.06022080963532954,
      "grad_norm": 0.05532608553767204,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.2154,
      "step": 180
    },
    {
      "epoch": 0.061893609902977584,
      "grad_norm": 0.06235940009355545,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1993,
      "step": 185
    },
    {
      "epoch": 0.06356641017062563,
      "grad_norm": 0.06464989483356476,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1926,
      "step": 190
    },
    {
      "epoch": 0.06523921043827367,
      "grad_norm": 0.06490304321050644,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2289,
      "step": 195
    },
    {
      "epoch": 0.06691201070592172,
      "grad_norm": 0.10941293835639954,
      "learning_rate": 0.0,
      "loss": 0.1909,
      "step": 200
    },
    {
      "epoch": 0.06691201070592172,
      "eval_loss": 0.20260320603847504,
      "eval_runtime": 39.2566,
      "eval_samples_per_second": 128.259,
      "eval_steps_per_second": 16.048,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.670528771293184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}