{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 9.209723472595215,
      "learning_rate": 0.0,
      "loss": 3.5424,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 9.498395919799805,
      "learning_rate": 2e-05,
      "loss": 3.481,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 8.83831787109375,
      "learning_rate": 4e-05,
      "loss": 3.4841,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 4.935218811035156,
      "learning_rate": 6e-05,
      "loss": 3.0814,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.2126102447509766,
      "learning_rate": 8e-05,
      "loss": 2.8296,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 2.1195733547210693,
      "learning_rate": 0.0001,
      "loss": 2.7133,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.8262771368026733,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.579,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.311913013458252,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.3829,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.2566421031951904,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.3577,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.3401048183441162,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.2833,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.1766916513442993,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.2743,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.386022686958313,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.219,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2940161228179932,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.1315,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 1.248589038848877,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.1076,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.053521752357483,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.9793,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.137381911277771,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.9979,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.154334306716919,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.9405,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.0989599227905273,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.8191,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.2083455324172974,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.8658,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.0666149854660034,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.927,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.1307358741760254,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.8982,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.121038794517517,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.913,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.0859190225601196,
      "learning_rate": 5e-05,
      "loss": 1.8906,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.0020114183425903,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8989,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 0.9956335425376892,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.9273,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2560831308364868,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.854,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 0.9763074517250061,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.753,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 0.9106507301330566,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.7721,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.100119709968567,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.7811,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.0469927787780762,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.7812,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 1.0803287029266357,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.719,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.0942535400390625,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.6422,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.0966131687164307,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.7327,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 1.033278465270996,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.6454,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.041293978691101,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.7156,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.0854636430740356,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6899,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.2054672241210938,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.6712,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.0341607332229614,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6657,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.3775967359542847,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.7625,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4144660359124992.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}