{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 4149,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024102193299590263,
      "grad_norm": 0.1189291775226593,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4342,
      "step": 100
    },
    {
      "epoch": 0.048204386599180526,
      "grad_norm": 0.13796567916870117,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4322,
      "step": 200
    },
    {
      "epoch": 0.07230657989877079,
      "grad_norm": 0.19356612861156464,
      "learning_rate": 6e-06,
      "loss": 2.4096,
      "step": 300
    },
    {
      "epoch": 0.09640877319836105,
      "grad_norm": 0.2834133803844452,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.407,
      "step": 400
    },
    {
      "epoch": 0.12051096649795132,
      "grad_norm": 0.3791491389274597,
      "learning_rate": 1e-05,
      "loss": 2.3248,
      "step": 500
    },
    {
      "epoch": 0.14461315979754158,
      "grad_norm": 0.4329169988632202,
      "learning_rate": 1.2e-05,
      "loss": 2.2811,
      "step": 600
    },
    {
      "epoch": 0.16871535309713184,
      "grad_norm": 0.46981674432754517,
      "learning_rate": 1.4e-05,
      "loss": 2.305,
      "step": 700
    },
    {
      "epoch": 0.1928175463967221,
      "grad_norm": 0.5296657085418701,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.3034,
      "step": 800
    },
    {
      "epoch": 0.21691973969631237,
      "grad_norm": 0.5638027191162109,
      "learning_rate": 1.8e-05,
      "loss": 2.2357,
      "step": 900
    },
    {
      "epoch": 0.24102193299590263,
      "grad_norm": 0.5962812900543213,
      "learning_rate": 2e-05,
      "loss": 2.2149,
      "step": 1000
    },
    {
      "epoch": 0.26512412629549287,
      "grad_norm": 0.6268550753593445,
      "learning_rate": 1.9950276214176393e-05,
      "loss": 2.1829,
      "step": 1100
    },
    {
      "epoch": 0.28922631959508316,
      "grad_norm": 0.7216062545776367,
      "learning_rate": 1.9801599347680883e-05,
      "loss": 2.1726,
      "step": 1200
    },
    {
      "epoch": 0.3133285128946734,
      "grad_norm": 0.6300708651542664,
      "learning_rate": 1.9555447955846792e-05,
      "loss": 2.1723,
      "step": 1300
    },
    {
      "epoch": 0.3374307061942637,
      "grad_norm": 0.7944507598876953,
      "learning_rate": 1.921426995449166e-05,
      "loss": 2.1556,
      "step": 1400
    },
    {
      "epoch": 0.3615328994938539,
      "grad_norm": 0.8489624261856079,
      "learning_rate": 1.8781458275988913e-05,
      "loss": 2.1597,
      "step": 1500
    },
    {
      "epoch": 0.3856350927934442,
      "grad_norm": 0.7369367480278015,
      "learning_rate": 1.826131712737932e-05,
      "loss": 2.1143,
      "step": 1600
    },
    {
      "epoch": 0.40973728609303445,
      "grad_norm": 0.7708919644355774,
      "learning_rate": 1.7659019186077174e-05,
      "loss": 2.1062,
      "step": 1700
    },
    {
      "epoch": 0.43383947939262474,
      "grad_norm": 0.8765296936035156,
      "learning_rate": 1.6980554158849546e-05,
      "loss": 2.1099,
      "step": 1800
    },
    {
      "epoch": 0.457941672692215,
      "grad_norm": 0.8643397092819214,
      "learning_rate": 1.6232669215636963e-05,
      "loss": 2.0938,
      "step": 1900
    },
    {
      "epoch": 0.48204386599180526,
      "grad_norm": 0.7830623984336853,
      "learning_rate": 1.5422801890586833e-05,
      "loss": 2.052,
      "step": 2000
    },
    {
      "epoch": 0.5061460592913956,
      "grad_norm": 1.1112042665481567,
      "learning_rate": 1.4559006117582424e-05,
      "loss": 2.1028,
      "step": 2100
    },
    {
      "epoch": 0.5302482525909857,
      "grad_norm": 1.3099650144577026,
      "learning_rate": 1.3649872135826173e-05,
      "loss": 2.0898,
      "step": 2200
    },
    {
      "epoch": 0.554350445890576,
      "grad_norm": 0.9661689400672913,
      "learning_rate": 1.2704441061996842e-05,
      "loss": 2.036,
      "step": 2300
    },
    {
      "epoch": 0.5784526391901663,
      "grad_norm": 0.8178704977035522,
      "learning_rate": 1.1732114978539648e-05,
      "loss": 2.0622,
      "step": 2400
    },
    {
      "epoch": 0.6025548324897566,
      "grad_norm": 0.8422364592552185,
      "learning_rate": 1.0742563432239503e-05,
      "loss": 2.0805,
      "step": 2500
    },
    {
      "epoch": 0.6266570257893468,
      "grad_norm": 0.980856716632843,
      "learning_rate": 9.745627272926332e-06,
      "loss": 2.0643,
      "step": 2600
    },
    {
      "epoch": 0.6507592190889371,
      "grad_norm": 0.8345414996147156,
      "learning_rate": 8.751220788613237e-06,
      "loss": 2.0526,
      "step": 2700
    },
    {
      "epoch": 0.6748614123885274,
      "grad_norm": 0.8472179770469666,
      "learning_rate": 7.769233110309735e-06,
      "loss": 2.0522,
      "step": 2800
    },
    {
      "epoch": 0.6989636056881177,
      "grad_norm": 0.8088483810424805,
      "learning_rate": 6.809429867015307e-06,
      "loss": 2.1132,
      "step": 2900
    },
    {
      "epoch": 0.7230657989877078,
      "grad_norm": 0.9939411878585815,
      "learning_rate": 5.881356068910429e-06,
      "loss": 2.0592,
      "step": 3000
    },
    {
      "epoch": 0.7471679922872981,
      "grad_norm": 1.0879184007644653,
      "learning_rate": 4.994241184548192e-06,
      "loss": 1.9955,
      "step": 3100
    },
    {
      "epoch": 0.7712701855868884,
      "grad_norm": 1.0115540027618408,
      "learning_rate": 4.1569073560307905e-06,
      "loss": 2.0433,
      "step": 3200
    },
    {
      "epoch": 0.7953723788864787,
      "grad_norm": 0.9652523398399353,
      "learning_rate": 3.3776816649486378e-06,
      "loss": 2.0405,
      "step": 3300
    },
    {
      "epoch": 0.8194745721860689,
      "grad_norm": 0.9643158316612244,
      "learning_rate": 2.6643133215760586e-06,
      "loss": 2.0431,
      "step": 3400
    },
    {
      "epoch": 0.8435767654856592,
      "grad_norm": 0.9680646657943726,
      "learning_rate": 2.0238966008568905e-06,
      "loss": 2.0118,
      "step": 3500
    },
    {
      "epoch": 0.8676789587852495,
      "grad_norm": 0.9375040531158447,
      "learning_rate": 1.4628002915629202e-06,
      "loss": 2.062,
      "step": 3600
    },
    {
      "epoch": 0.8917811520848398,
      "grad_norm": 0.9199696183204651,
      "learning_rate": 9.866043602360909e-07,
      "loss": 2.0442,
      "step": 3700
    },
    {
      "epoch": 0.91588334538443,
      "grad_norm": 0.7687466144561768,
      "learning_rate": 6.000444597762811e-07,
      "loss": 2.0474,
      "step": 3800
    },
    {
      "epoch": 0.9399855386840202,
      "grad_norm": 1.007958173751831,
      "learning_rate": 3.069648345231813e-07,
      "loss": 2.0126,
      "step": 3900
    },
    {
      "epoch": 0.9640877319836105,
      "grad_norm": 0.9788452982902527,
      "learning_rate": 1.1028009017986174e-07,
      "loss": 2.0637,
      "step": 4000
    },
    {
      "epoch": 0.9881899252832008,
      "grad_norm": 1.100760817527771,
      "learning_rate": 1.1946208766822066e-08,
      "loss": 2.0634,
      "step": 4100
    },
    {
      "epoch": 1.0,
      "step": 4149,
      "total_flos": 7.557299011584e+16,
      "train_loss": 2.140284038331314,
      "train_runtime": 1100.1009,
      "train_samples_per_second": 7.543,
      "train_steps_per_second": 3.771
    }
  ],
  "logging_steps": 100,
  "max_steps": 4149,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.557299011584e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}