{
  "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": 8.470880508422852,
      "learning_rate": 0.0,
      "loss": 3.5382,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 8.909177780151367,
      "learning_rate": 2e-05,
      "loss": 3.4532,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 7.695003986358643,
      "learning_rate": 4e-05,
      "loss": 3.4989,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 4.702130317687988,
      "learning_rate": 6e-05,
      "loss": 3.0727,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.1741292476654053,
      "learning_rate": 8e-05,
      "loss": 2.8012,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 2.041757583618164,
      "learning_rate": 0.0001,
      "loss": 2.7376,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.622029423713684,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.604,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.1719176769256592,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.451,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.2090308666229248,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.3664,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.2097088098526,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.1701,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.1369860172271729,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.219,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.2339004278182983,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.2113,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.246859073638916,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.0942,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 0.9878728985786438,
      "learning_rate": 7.647058823529411e-05,
      "loss": 1.9954,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.058945655822754,
      "learning_rate": 7.352941176470589e-05,
      "loss": 2.0023,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.043708086013794,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.936,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.1459572315216064,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.9311,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.0087627172470093,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.8924,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.041082739830017,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.8733,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.0150171518325806,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.8484,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 0.9878617525100708,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.8999,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.0472187995910645,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.8641,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.049538016319275,
      "learning_rate": 5e-05,
      "loss": 1.8808,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.0137228965759277,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8137,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 0.9878528118133545,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.8895,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3761823177337646,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.7638,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 1.0509991645812988,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.7973,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 0.9965255260467529,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.7637,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.1132783889770508,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.6971,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.100830316543579,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.6422,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 1.0036139488220215,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.6041,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.0887032747268677,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.6402,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.2407240867614746,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.5913,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 1.0142990350723267,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.6117,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.076665997505188,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.7519,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.144922137260437,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6825,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.1244444847106934,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.6658,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.0084117650985718,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6346,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4113011360168457,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.6726,
      "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": 4251074854576128.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}