{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3888888888888888,
  "eval_steps": 50,
  "global_step": 100,
  "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
    }
  ],
  "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": 589411381149696.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}