{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7777777777777777,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 28.03362215670935,
      "learning_rate": 5e-07,
      "loss": 1.6525,
      "step": 5
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 15.104101542150465,
      "learning_rate": 1e-06,
      "loss": 1.5085,
      "step": 10
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 8.033686730596932,
      "learning_rate": 9.985471028179154e-07,
      "loss": 1.2944,
      "step": 15
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 5.527358615393283,
      "learning_rate": 9.94196854912548e-07,
      "loss": 1.2274,
      "step": 20
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 5.639639905741326,
      "learning_rate": 9.869745381355905e-07,
      "loss": 1.1796,
      "step": 25
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 4.841439267473979,
      "learning_rate": 9.769221256218162e-07,
      "loss": 1.162,
      "step": 30
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 5.031380897521579,
      "learning_rate": 9.64098037858483e-07,
      "loss": 1.1511,
      "step": 35
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.623507128763141,
      "learning_rate": 9.485768031694871e-07,
      "loss": 1.1321,
      "step": 40
    },
    {
      "epoch": 0.625,
      "grad_norm": 4.438078790320084,
      "learning_rate": 9.304486245873971e-07,
      "loss": 1.141,
      "step": 45
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 4.553312192573781,
      "learning_rate": 9.098188556305262e-07,
      "loss": 1.1353,
      "step": 50
    },
    {
      "epoch": 0.6944444444444444,
      "eval_loss": 1.1089767217636108,
      "eval_runtime": 36.7554,
      "eval_samples_per_second": 55.584,
      "eval_steps_per_second": 0.871,
      "step": 50
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 4.657055083923456,
      "learning_rate": 8.868073880316123e-07,
      "loss": 1.1085,
      "step": 55
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 4.899356041473821,
      "learning_rate": 8.615479549763755e-07,
      "loss": 1.1058,
      "step": 60
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 4.752445427346823,
      "learning_rate": 8.341873539012443e-07,
      "loss": 1.1054,
      "step": 65
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 4.9284072371353504,
      "learning_rate": 8.048845933670271e-07,
      "loss": 1.1129,
      "step": 70
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 4.916541328032108,
      "learning_rate": 7.738099689665539e-07,
      "loss": 1.0225,
      "step": 75
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 4.755137577065741,
      "learning_rate": 7.41144073636728e-07,
      "loss": 0.9791,
      "step": 80
    },
    {
      "epoch": 1.1805555555555556,
      "grad_norm": 5.211754164119227,
      "learning_rate": 7.070767481266492e-07,
      "loss": 0.9602,
      "step": 85
    },
    {
      "epoch": 1.25,
      "grad_norm": 5.068955447006314,
      "learning_rate": 6.718059777212565e-07,
      "loss": 0.9586,
      "step": 90
    },
    {
      "epoch": 1.3194444444444444,
      "grad_norm": 5.0242480045435896,
      "learning_rate": 6.355367416322778e-07,
      "loss": 0.9528,
      "step": 95
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 5.100859792567275,
      "learning_rate": 5.984798217433531e-07,
      "loss": 0.9543,
      "step": 100
    },
    {
      "epoch": 1.3888888888888888,
      "eval_loss": 1.0777673721313477,
      "eval_runtime": 36.2431,
      "eval_samples_per_second": 56.369,
      "eval_steps_per_second": 0.883,
      "step": 100
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 5.158449874528905,
      "learning_rate": 5.608505776324157e-07,
      "loss": 0.9546,
      "step": 105
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 5.0308140222864886,
      "learning_rate": 5.228676949903973e-07,
      "loss": 0.9602,
      "step": 110
    },
    {
      "epoch": 1.5972222222222223,
      "grad_norm": 4.902344567141826,
      "learning_rate": 4.847519147099294e-07,
      "loss": 0.9547,
      "step": 115
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 5.1345646964010605,
      "learning_rate": 4.46724750030062e-07,
      "loss": 0.9369,
      "step": 120
    },
    {
      "epoch": 1.7361111111111112,
      "grad_norm": 5.243970140246485,
      "learning_rate": 4.0900719919241935e-07,
      "loss": 0.9455,
      "step": 125
    },
    {
      "epoch": 1.8055555555555556,
      "grad_norm": 4.923533966119208,
      "learning_rate": 3.7181846109031e-07,
      "loss": 0.9392,
      "step": 130
    },
    {
      "epoch": 1.875,
      "grad_norm": 4.905055116114625,
      "learning_rate": 3.353746613749093e-07,
      "loss": 0.9439,
      "step": 135
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 4.947955537361124,
      "learning_rate": 2.9988759642186093e-07,
      "loss": 0.9396,
      "step": 140
    },
    {
      "epoch": 2.013888888888889,
      "grad_norm": 5.937445383303241,
      "learning_rate": 2.655635024578483e-07,
      "loss": 0.9073,
      "step": 145
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 5.340090037535277,
      "learning_rate": 2.3260185700046292e-07,
      "loss": 0.8627,
      "step": 150
    },
    {
      "epoch": 2.0833333333333335,
      "eval_loss": 1.0668742656707764,
      "eval_runtime": 36.2443,
      "eval_samples_per_second": 56.367,
      "eval_steps_per_second": 0.883,
      "step": 150
    },
    {
      "epoch": 2.1527777777777777,
      "grad_norm": 5.393268774778699,
      "learning_rate": 2.0119421957691218e-07,
      "loss": 0.8666,
      "step": 155
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 5.388556278114857,
      "learning_rate": 1.7152311845883094e-07,
      "loss": 0.8574,
      "step": 160
    },
    {
      "epoch": 2.2916666666666665,
      "grad_norm": 5.732293363878604,
      "learning_rate": 1.4376098988303404e-07,
      "loss": 0.8581,
      "step": 165
    },
    {
      "epoch": 2.361111111111111,
      "grad_norm": 5.45272302861646,
      "learning_rate": 1.1806917592302761e-07,
      "loss": 0.8505,
      "step": 170
    },
    {
      "epoch": 2.4305555555555554,
      "grad_norm": 5.302389477646773,
      "learning_rate": 9.459698683523204e-08,
      "loss": 0.847,
      "step": 175
    },
    {
      "epoch": 2.5,
      "grad_norm": 5.366246438508766,
      "learning_rate": 7.348083332917926e-08,
      "loss": 0.8505,
      "step": 180
    },
    {
      "epoch": 2.5694444444444446,
      "grad_norm": 5.427530127252247,
      "learning_rate": 5.484343380457124e-08,
      "loss": 0.844,
      "step": 185
    },
    {
      "epoch": 2.638888888888889,
      "grad_norm": 5.2796646154487865,
      "learning_rate": 3.879310116241041e-08,
      "loss": 0.8417,
      "step": 190
    },
    {
      "epoch": 2.7083333333333335,
      "grad_norm": 5.36802540722628,
      "learning_rate": 2.5423113334966218e-08,
      "loss": 0.8382,
      "step": 195
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 5.431008385979752,
      "learning_rate": 1.4811171192794624e-08,
      "loss": 0.8551,
      "step": 200
    },
    {
      "epoch": 2.7777777777777777,
      "eval_loss": 1.0724252462387085,
      "eval_runtime": 36.3038,
      "eval_samples_per_second": 56.275,
      "eval_steps_per_second": 0.881,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1179056703799296.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}