{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.090909090909091,
  "eval_steps": 50,
  "global_step": 41,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.7111204266548157,
      "learning_rate": 1e-05,
      "loss": 2.5763,
      "step": 1
    },
    {
      "epoch": 0.07272727272727272,
      "eval_loss": 2.782656192779541,
      "eval_runtime": 1.0853,
      "eval_samples_per_second": 21.192,
      "eval_steps_per_second": 5.528,
      "step": 1
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 1.106281042098999,
      "learning_rate": 2e-05,
      "loss": 2.6614,
      "step": 2
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 1.7965294122695923,
      "learning_rate": 3e-05,
      "loss": 3.1936,
      "step": 3
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.7506732940673828,
      "learning_rate": 4e-05,
      "loss": 2.5231,
      "step": 4
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.1378496885299683,
      "learning_rate": 5e-05,
      "loss": 2.6493,
      "step": 5
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 1.4849205017089844,
      "learning_rate": 6e-05,
      "loss": 3.0814,
      "step": 6
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.5388326644897461,
      "learning_rate": 7e-05,
      "loss": 2.4552,
      "step": 7
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.8350285887718201,
      "learning_rate": 8e-05,
      "loss": 2.7186,
      "step": 8
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 1.1119364500045776,
      "learning_rate": 9e-05,
      "loss": 2.8151,
      "step": 9
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.5692049860954285,
      "learning_rate": 0.0001,
      "loss": 2.3878,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7665489912033081,
      "learning_rate": 9.974346616959476e-05,
      "loss": 2.5004,
      "step": 11
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 1.0629138946533203,
      "learning_rate": 9.897649706262473e-05,
      "loss": 2.6267,
      "step": 12
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 1.0229064226150513,
      "learning_rate": 9.770696282000244e-05,
      "loss": 2.3946,
      "step": 13
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 2.01250958442688,
      "learning_rate": 9.594789058101153e-05,
      "loss": 4.4228,
      "step": 14
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 0.9252060651779175,
      "learning_rate": 9.371733080722911e-05,
      "loss": 2.2896,
      "step": 15
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.779765009880066,
      "learning_rate": 9.103817206036382e-05,
      "loss": 2.5117,
      "step": 16
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.8884384036064148,
      "learning_rate": 8.793790613463955e-05,
      "loss": 2.2099,
      "step": 17
    },
    {
      "epoch": 1.3454545454545455,
      "grad_norm": 1.0297373533248901,
      "learning_rate": 8.444834595378434e-05,
      "loss": 2.0512,
      "step": 18
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 1.113632082939148,
      "learning_rate": 8.060529912738315e-05,
      "loss": 2.3172,
      "step": 19
    },
    {
      "epoch": 1.490909090909091,
      "grad_norm": 1.2006114721298218,
      "learning_rate": 7.644820051634812e-05,
      "loss": 2.2296,
      "step": 20
    },
    {
      "epoch": 1.5636363636363635,
      "grad_norm": 0.9560397863388062,
      "learning_rate": 7.201970757788172e-05,
      "loss": 2.1197,
      "step": 21
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 1.185219645500183,
      "learning_rate": 6.736526264224101e-05,
      "loss": 2.1382,
      "step": 22
    },
    {
      "epoch": 1.709090909090909,
      "grad_norm": 0.6703472137451172,
      "learning_rate": 6.253262661293604e-05,
      "loss": 2.237,
      "step": 23
    },
    {
      "epoch": 1.7818181818181817,
      "grad_norm": 0.5953474640846252,
      "learning_rate": 5.757138887522884e-05,
      "loss": 1.9626,
      "step": 24
    },
    {
      "epoch": 1.8545454545454545,
      "grad_norm": 0.9367973804473877,
      "learning_rate": 5.2532458441935636e-05,
      "loss": 2.1922,
      "step": 25
    },
    {
      "epoch": 1.9272727272727272,
      "grad_norm": 0.6184181571006775,
      "learning_rate": 4.746754155806437e-05,
      "loss": 2.2879,
      "step": 26
    },
    {
      "epoch": 2.036363636363636,
      "grad_norm": 1.5241204500198364,
      "learning_rate": 4.2428611124771184e-05,
      "loss": 3.4858,
      "step": 27
    },
    {
      "epoch": 2.109090909090909,
      "grad_norm": 0.5431642532348633,
      "learning_rate": 3.746737338706397e-05,
      "loss": 1.8842,
      "step": 28
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.8803680539131165,
      "learning_rate": 3.263473735775899e-05,
      "loss": 1.9186,
      "step": 29
    },
    {
      "epoch": 2.2545454545454544,
      "grad_norm": 0.7640741467475891,
      "learning_rate": 2.798029242211828e-05,
      "loss": 2.1441,
      "step": 30
    },
    {
      "epoch": 2.327272727272727,
      "grad_norm": 0.4969829320907593,
      "learning_rate": 2.3551799483651894e-05,
      "loss": 1.6597,
      "step": 31
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.7915704250335693,
      "learning_rate": 1.9394700872616855e-05,
      "loss": 1.9966,
      "step": 32
    },
    {
      "epoch": 2.4727272727272727,
      "grad_norm": 0.5742689371109009,
      "learning_rate": 1.555165404621567e-05,
      "loss": 1.9501,
      "step": 33
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.5611478686332703,
      "learning_rate": 1.2062093865360458e-05,
      "loss": 1.8512,
      "step": 34
    },
    {
      "epoch": 2.618181818181818,
      "grad_norm": 0.8697972297668457,
      "learning_rate": 8.961827939636196e-06,
      "loss": 1.9542,
      "step": 35
    },
    {
      "epoch": 2.690909090909091,
      "grad_norm": 0.7828204035758972,
      "learning_rate": 6.282669192770896e-06,
      "loss": 2.3979,
      "step": 36
    },
    {
      "epoch": 2.7636363636363637,
      "grad_norm": 0.7101818919181824,
      "learning_rate": 4.05210941898847e-06,
      "loss": 1.8374,
      "step": 37
    },
    {
      "epoch": 2.8363636363636364,
      "grad_norm": 0.8289034962654114,
      "learning_rate": 2.2930371799975594e-06,
      "loss": 1.9316,
      "step": 38
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.6910982728004456,
      "learning_rate": 1.0235029373752758e-06,
      "loss": 1.956,
      "step": 39
    },
    {
      "epoch": 3.018181818181818,
      "grad_norm": 1.4117423295974731,
      "learning_rate": 2.5653383040524227e-07,
      "loss": 3.4805,
      "step": 40
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.6039517521858215,
      "learning_rate": 0.0,
      "loss": 1.7894,
      "step": 41
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3332420841373696e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}