{
  "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": 2.1771256923675537,
      "learning_rate": 0.0,
      "loss": 2.9552,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 1.9881774187088013,
      "learning_rate": 2e-05,
      "loss": 2.9192,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 1.7272872924804688,
      "learning_rate": 4e-05,
      "loss": 2.9117,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 1.8218345642089844,
      "learning_rate": 6e-05,
      "loss": 2.8895,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.6144229173660278,
      "learning_rate": 8e-05,
      "loss": 2.7776,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.4913206100463867,
      "learning_rate": 0.0001,
      "loss": 2.7254,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.5326149463653564,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.6575,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.363348126411438,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.4802,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.279327630996704,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.4609,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.481676459312439,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.4929,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.3925163745880127,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.4714,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.4846415519714355,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.4263,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7030328512191772,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.3784,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 1.2274811267852783,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.3738,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.2362170219421387,
      "learning_rate": 7.352941176470589e-05,
      "loss": 2.2533,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.3006786108016968,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.2568,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.326129674911499,
      "learning_rate": 6.764705882352942e-05,
      "loss": 2.2476,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.223816156387329,
      "learning_rate": 6.470588235294118e-05,
      "loss": 2.1276,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.2358795404434204,
      "learning_rate": 6.176470588235295e-05,
      "loss": 2.1277,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.2873972654342651,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.2558,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.3089426755905151,
      "learning_rate": 5.588235294117647e-05,
      "loss": 2.1956,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.1772621870040894,
      "learning_rate": 5.294117647058824e-05,
      "loss": 2.1671,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.2248624563217163,
      "learning_rate": 5e-05,
      "loss": 2.2105,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.1209758520126343,
      "learning_rate": 4.705882352941177e-05,
      "loss": 2.1628,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 1.0809253454208374,
      "learning_rate": 4.411764705882353e-05,
      "loss": 2.1846,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4269254207611084,
      "learning_rate": 4.11764705882353e-05,
      "loss": 2.1611,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 1.0492329597473145,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 2.0413,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 1.0544239282608032,
      "learning_rate": 3.529411764705883e-05,
      "loss": 2.0618,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.2331007719039917,
      "learning_rate": 3.235294117647059e-05,
      "loss": 2.1633,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.2372910976409912,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 2.1143,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 1.177882194519043,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.9923,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.1148498058319092,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 2.0018,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.1493771076202393,
      "learning_rate": 2.058823529411765e-05,
      "loss": 2.0589,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 1.1797679662704468,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.9919,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.1385939121246338,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 2.0353,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.139145851135254,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.0152,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.1550567150115967,
      "learning_rate": 8.823529411764707e-06,
      "loss": 2.0115,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.186667799949646,
      "learning_rate": 5.882352941176471e-06,
      "loss": 2.0066,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5287202596664429,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 2.0844,
      "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": 1712090038886400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}