{
  "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": 8.399100303649902,
      "learning_rate": 0.0,
      "loss": 3.4769,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 8.483515739440918,
      "learning_rate": 2e-05,
      "loss": 3.3033,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 7.9899373054504395,
      "learning_rate": 4e-05,
      "loss": 3.3847,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 5.445839881896973,
      "learning_rate": 6e-05,
      "loss": 2.9659,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.2083046436309814,
      "learning_rate": 8e-05,
      "loss": 2.6905,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.9826908111572266,
      "learning_rate": 0.0001,
      "loss": 2.534,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.8764874935150146,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.4716,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.3708795309066772,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.3627,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.3119926452636719,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.2397,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.2743617296218872,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.1333,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.1760859489440918,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.0975,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.1169344186782837,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.0631,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.16274094581604,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.0147,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 1.0153965950012207,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.0834,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 0.9314503073692322,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.8984,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 0.9333633184432983,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.8462,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.0826770067214966,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.9037,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.1457035541534424,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.7865,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.1258127689361572,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.7464,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.1179546117782593,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.7625,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 0.9962314367294312,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.8666,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.1161456108093262,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.8212,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 0.946094274520874,
      "learning_rate": 5e-05,
      "loss": 1.8137,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 0.9646325707435608,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8109,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 0.9120578169822693,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.8435,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1808918714523315,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.7133,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 0.8297111392021179,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.7821,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 0.8673017024993896,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.6985,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 0.9691831469535828,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.6545,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 0.9301393628120422,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.6854,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 0.9261943101882935,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.5342,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 0.9456276297569275,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.5435,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 0.9902423620223999,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.6343,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 0.9334891438484192,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.5587,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 0.994159996509552,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.6071,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.0059574842453003,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6916,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 0.9957348108291626,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.5349,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.0079549551010132,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6993,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2976068258285522,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.6626,
      "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": 4348410599789568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}