{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9696969696969697,
  "eval_steps": 500,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.08310938404347,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.5976,
      "step": 1
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.2015655639458453,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.5737,
      "step": 5
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.5529484610069302,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.4242,
      "step": 10
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.44235368767500005,
      "learning_rate": 0.0002,
      "loss": 2.2287,
      "step": 15
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.34186780209717693,
      "learning_rate": 0.00019929278846732884,
      "loss": 2.1199,
      "step": 20
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.2690393065112005,
      "learning_rate": 0.00019718115683235417,
      "loss": 1.963,
      "step": 25
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.2895526654213361,
      "learning_rate": 0.0001936949724999762,
      "loss": 1.9819,
      "step": 30
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 0.21284939456784369,
      "learning_rate": 0.00018888354486549237,
      "loss": 1.9367,
      "step": 35
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.220661039014496,
      "learning_rate": 0.00018281492787113708,
      "loss": 1.9123,
      "step": 40
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.25800435226254403,
      "learning_rate": 0.00017557495743542585,
      "loss": 1.8955,
      "step": 45
    },
    {
      "epoch": 0.98989898989899,
      "eval_loss": 1.8462597131729126,
      "eval_runtime": 164.2887,
      "eval_samples_per_second": 38.475,
      "eval_steps_per_second": 2.41,
      "step": 49
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 0.21280470872825646,
      "learning_rate": 0.00016726603737012529,
      "loss": 1.9023,
      "step": 50
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2281964993767009,
      "learning_rate": 0.00015800569095711982,
      "loss": 1.8291,
      "step": 55
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.2468620521645798,
      "learning_rate": 0.0001479248986720057,
      "loss": 1.8448,
      "step": 60
    },
    {
      "epoch": 1.3131313131313131,
      "grad_norm": 0.24256005211247963,
      "learning_rate": 0.00013716624556603274,
      "loss": 1.8667,
      "step": 65
    },
    {
      "epoch": 1.4141414141414141,
      "grad_norm": 0.22252607581763362,
      "learning_rate": 0.00012588190451025207,
      "loss": 1.8213,
      "step": 70
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.2742840702900069,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.8122,
      "step": 75
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.25494953140215326,
      "learning_rate": 0.00010237976975461075,
      "loss": 1.8726,
      "step": 80
    },
    {
      "epoch": 1.7171717171717171,
      "grad_norm": 0.2657201331656562,
      "learning_rate": 9.049439566958175e-05,
      "loss": 1.8425,
      "step": 85
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.2700733549650734,
      "learning_rate": 7.874347104470234e-05,
      "loss": 1.8205,
      "step": 90
    },
    {
      "epoch": 1.9191919191919191,
      "grad_norm": 0.28284460248100685,
      "learning_rate": 6.729320366825784e-05,
      "loss": 1.8698,
      "step": 95
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.7677603960037231,
      "eval_runtime": 177.7383,
      "eval_samples_per_second": 35.564,
      "eval_steps_per_second": 2.228,
      "step": 99
    },
    {
      "epoch": 2.0202020202020203,
      "grad_norm": 0.28052694585968674,
      "learning_rate": 5.630554876306407e-05,
      "loss": 1.8412,
      "step": 100
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 0.30253313940579424,
      "learning_rate": 4.593591825444028e-05,
      "loss": 1.7843,
      "step": 105
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.2919901233198437,
      "learning_rate": 3.6330982588091186e-05,
      "loss": 1.8085,
      "step": 110
    },
    {
      "epoch": 2.323232323232323,
      "grad_norm": 0.2985415087687047,
      "learning_rate": 2.7626596189492983e-05,
      "loss": 1.7548,
      "step": 115
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.31809894547826195,
      "learning_rate": 1.994587590756397e-05,
      "loss": 1.758,
      "step": 120
    },
    {
      "epoch": 2.525252525252525,
      "grad_norm": 0.31151542636398494,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.7844,
      "step": 125
    },
    {
      "epoch": 2.6262626262626263,
      "grad_norm": 0.3034143797714973,
      "learning_rate": 8.073969641833445e-06,
      "loss": 1.7975,
      "step": 130
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.28778283893396456,
      "learning_rate": 4.050702638550275e-06,
      "loss": 1.7661,
      "step": 135
    },
    {
      "epoch": 2.8282828282828283,
      "grad_norm": 0.2907166952704868,
      "learning_rate": 1.3845646281813507e-06,
      "loss": 1.7619,
      "step": 140
    },
    {
      "epoch": 2.929292929292929,
      "grad_norm": 0.31772634861484544,
      "learning_rate": 1.1326608169920372e-07,
      "loss": 1.8282,
      "step": 145
    },
    {
      "epoch": 2.9696969696969697,
      "eval_loss": 1.7491472959518433,
      "eval_runtime": 161.8737,
      "eval_samples_per_second": 39.049,
      "eval_steps_per_second": 2.446,
      "step": 147
    },
    {
      "epoch": 2.9696969696969697,
      "step": 147,
      "total_flos": 706816481427456.0,
      "train_loss": 1.9096906704156578,
      "train_runtime": 1619.2688,
      "train_samples_per_second": 11.711,
      "train_steps_per_second": 0.091
    }
  ],
  "logging_steps": 5,
  "max_steps": 147,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 706816481427456.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}