{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0303030303030303,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.0779532194137573,
      "learning_rate": 9e-05,
      "loss": 0.5809,
      "step": 10
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.257666826248169,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2898,
      "step": 20
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.1526721715927124,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1944,
      "step": 30
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.740468442440033,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.1489,
      "step": 40
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.5122345089912415,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.1241,
      "step": 50
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.3294401168823242,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1162,
      "step": 60
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.3713489770889282,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.105,
      "step": 70
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.38999056816101074,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.102,
      "step": 80
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.313165545463562,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0917,
      "step": 90
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.2271764725446701,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0896,
      "step": 100
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.2582443356513977,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0906,
      "step": 110
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.28969135880470276,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0898,
      "step": 120
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 0.21474944055080414,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0858,
      "step": 130
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 0.17501652240753174,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0827,
      "step": 140
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.17531634867191315,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0835,
      "step": 150
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.1865883618593216,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0795,
      "step": 160
    },
    {
      "epoch": 2.5757575757575757,
      "grad_norm": 0.23194383084774017,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0871,
      "step": 170
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.15936115384101868,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0838,
      "step": 180
    },
    {
      "epoch": 2.878787878787879,
      "grad_norm": 0.18423740565776825,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0791,
      "step": 190
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 0.13376280665397644,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0796,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}