{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 0.19419066607952118,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.0888,
      "step": 5
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 0.0060990070924162865,
      "learning_rate": 1.2e-05,
      "loss": 0.0785,
      "step": 10
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.011376941576600075,
      "learning_rate": 1.866666666666667e-05,
      "loss": 0.0757,
      "step": 15
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 2.0510334968566895,
      "learning_rate": 1.9954719225730847e-05,
      "loss": 0.1455,
      "step": 20
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 0.048179708421230316,
      "learning_rate": 1.9771468659711595e-05,
      "loss": 0.249,
      "step": 25
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.1557886153459549,
      "learning_rate": 1.9450008187146685e-05,
      "loss": 0.0786,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.09699074178934097,
      "learning_rate": 1.8994884619106034e-05,
      "loss": 0.0771,
      "step": 35
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 0.012417234480381012,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 0.0761,
      "step": 40
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.10855792462825775,
      "learning_rate": 1.771119719745388e-05,
      "loss": 0.0758,
      "step": 45
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 0.10554474592208862,
      "learning_rate": 1.6900790114821122e-05,
      "loss": 0.0762,
      "step": 50
    },
    {
      "epoch": 0.3741496598639456,
      "grad_norm": 0.08427968621253967,
      "learning_rate": 1.599277666511347e-05,
      "loss": 0.0762,
      "step": 55
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.14054857194423676,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0755,
      "step": 60
    },
    {
      "epoch": 0.4421768707482993,
      "grad_norm": 0.06138243526220322,
      "learning_rate": 1.3936502181619415e-05,
      "loss": 0.0737,
      "step": 65
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.06466853618621826,
      "learning_rate": 1.2817325568414299e-05,
      "loss": 0.0752,
      "step": 70
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 0.13903750479221344,
      "learning_rate": 1.1658300052543742e-05,
      "loss": 0.0756,
      "step": 75
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 0.10078471899032593,
      "learning_rate": 1.0475819158237426e-05,
      "loss": 0.0743,
      "step": 80
    },
    {
      "epoch": 0.5782312925170068,
      "grad_norm": 0.10367649793624878,
      "learning_rate": 9.286608168007678e-06,
      "loss": 0.0771,
      "step": 85
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 0.06360036879777908,
      "learning_rate": 8.107487556395902e-06,
      "loss": 0.0755,
      "step": 90
    },
    {
      "epoch": 0.6462585034013606,
      "grad_norm": 0.03832394629716873,
      "learning_rate": 6.955135077300932e-06,
      "loss": 0.0738,
      "step": 95
    },
    {
      "epoch": 0.6802721088435374,
      "grad_norm": 0.002442193916067481,
      "learning_rate": 5.845849869981137e-06,
      "loss": 0.0731,
      "step": 100
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.012490343302488327,
      "learning_rate": 4.795321920269279e-06,
      "loss": 0.073,
      "step": 105
    },
    {
      "epoch": 0.7482993197278912,
      "grad_norm": 0.003825731808319688,
      "learning_rate": 3.818410137793947e-06,
      "loss": 0.0732,
      "step": 110
    },
    {
      "epoch": 0.782312925170068,
      "grad_norm": 0.006658583413809538,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.0734,
      "step": 115
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.00992305763065815,
      "learning_rate": 2.1394690525721275e-06,
      "loss": 0.0728,
      "step": 120
    },
    {
      "epoch": 0.8503401360544217,
      "grad_norm": 0.01818728633224964,
      "learning_rate": 1.4611870797885196e-06,
      "loss": 0.0728,
      "step": 125
    },
    {
      "epoch": 0.8843537414965986,
      "grad_norm": 0.00845139566808939,
      "learning_rate": 9.036800464548157e-07,
      "loss": 0.0734,
      "step": 130
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 0.058558348566293716,
      "learning_rate": 4.7483346064139513e-07,
      "loss": 0.073,
      "step": 135
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.05383609980344772,
      "learning_rate": 1.8071302737293294e-07,
      "loss": 0.0728,
      "step": 140
    },
    {
      "epoch": 0.9863945578231292,
      "grad_norm": 0.00498389033600688,
      "learning_rate": 2.547885389746485e-08,
      "loss": 0.0733,
      "step": 145
    },
    {
      "epoch": 1.0,
      "step": 147,
      "total_flos": 2.4132193734570803e+17,
      "train_loss": 0.08361149036965403,
      "train_runtime": 1113.8618,
      "train_samples_per_second": 16.871,
      "train_steps_per_second": 0.132
    }
  ],
  "logging_steps": 5,
  "max_steps": 147,
  "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": 2.4132193734570803e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}