{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9696969696969697,
  "eval_steps": 1,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 2.088834762573242,
      "learning_rate": 8.333333333333333e-07,
      "loss": 5.4688,
      "step": 1
    },
    {
      "epoch": 0.04040404040404041,
      "eval_loss": 5.470384120941162,
      "eval_runtime": 4.8066,
      "eval_samples_per_second": 34.536,
      "eval_steps_per_second": 0.624,
      "step": 1
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 2.0961971282958984,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 5.4731,
      "step": 2
    },
    {
      "epoch": 0.08080808080808081,
      "eval_loss": 5.4689249992370605,
      "eval_runtime": 4.8593,
      "eval_samples_per_second": 34.161,
      "eval_steps_per_second": 0.617,
      "step": 2
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.0940349102020264,
      "learning_rate": 2.5e-06,
      "loss": 5.4803,
      "step": 3
    },
    {
      "epoch": 0.12121212121212122,
      "eval_loss": 5.467825412750244,
      "eval_runtime": 4.9081,
      "eval_samples_per_second": 33.822,
      "eval_steps_per_second": 0.611,
      "step": 3
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 2.095174551010132,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 5.5119,
      "step": 4
    },
    {
      "epoch": 0.16161616161616163,
      "eval_loss": 5.465516567230225,
      "eval_runtime": 4.8615,
      "eval_samples_per_second": 34.146,
      "eval_steps_per_second": 0.617,
      "step": 4
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 2.1109118461608887,
      "learning_rate": 4.166666666666667e-06,
      "loss": 5.4662,
      "step": 5
    },
    {
      "epoch": 0.20202020202020202,
      "eval_loss": 5.4626851081848145,
      "eval_runtime": 4.844,
      "eval_samples_per_second": 34.27,
      "eval_steps_per_second": 0.619,
      "step": 5
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.1030592918395996,
      "learning_rate": 5e-06,
      "loss": 5.4691,
      "step": 6
    },
    {
      "epoch": 0.24242424242424243,
      "eval_loss": 5.45806884765625,
      "eval_runtime": 4.8388,
      "eval_samples_per_second": 34.306,
      "eval_steps_per_second": 0.62,
      "step": 6
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 2.1202447414398193,
      "learning_rate": 5.833333333333334e-06,
      "loss": 5.4851,
      "step": 7
    },
    {
      "epoch": 0.2828282828282828,
      "eval_loss": 5.449892520904541,
      "eval_runtime": 4.8431,
      "eval_samples_per_second": 34.276,
      "eval_steps_per_second": 0.619,
      "step": 7
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 2.090963363647461,
      "learning_rate": 6.666666666666667e-06,
      "loss": 5.4228,
      "step": 8
    },
    {
      "epoch": 0.32323232323232326,
      "eval_loss": 5.442515850067139,
      "eval_runtime": 4.8605,
      "eval_samples_per_second": 34.153,
      "eval_steps_per_second": 0.617,
      "step": 8
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.112323760986328,
      "learning_rate": 7.500000000000001e-06,
      "loss": 5.4715,
      "step": 9
    },
    {
      "epoch": 0.36363636363636365,
      "eval_loss": 5.4345855712890625,
      "eval_runtime": 4.8796,
      "eval_samples_per_second": 34.019,
      "eval_steps_per_second": 0.615,
      "step": 9
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 2.1456995010375977,
      "learning_rate": 8.333333333333334e-06,
      "loss": 5.4211,
      "step": 10
    },
    {
      "epoch": 0.40404040404040403,
      "eval_loss": 5.424546718597412,
      "eval_runtime": 4.9274,
      "eval_samples_per_second": 33.689,
      "eval_steps_per_second": 0.609,
      "step": 10
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.1602349281311035,
      "learning_rate": 9.166666666666666e-06,
      "loss": 5.4301,
      "step": 11
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 5.41035795211792,
      "eval_runtime": 4.9819,
      "eval_samples_per_second": 33.32,
      "eval_steps_per_second": 0.602,
      "step": 11
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 2.1762421131134033,
      "learning_rate": 1e-05,
      "loss": 5.4158,
      "step": 12
    },
    {
      "epoch": 0.48484848484848486,
      "eval_loss": 5.400452613830566,
      "eval_runtime": 5.0737,
      "eval_samples_per_second": 32.718,
      "eval_steps_per_second": 0.591,
      "step": 12
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 2.2415969371795654,
      "learning_rate": 1.0833333333333334e-05,
      "loss": 5.3986,
      "step": 13
    },
    {
      "epoch": 0.5252525252525253,
      "eval_loss": 5.382190227508545,
      "eval_runtime": 4.9555,
      "eval_samples_per_second": 33.498,
      "eval_steps_per_second": 0.605,
      "step": 13
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 2.2669475078582764,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 5.428,
      "step": 14
    },
    {
      "epoch": 0.5656565656565656,
      "eval_loss": 5.3634443283081055,
      "eval_runtime": 4.9029,
      "eval_samples_per_second": 33.857,
      "eval_steps_per_second": 0.612,
      "step": 14
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.262896776199341,
      "learning_rate": 1.25e-05,
      "loss": 5.3741,
      "step": 15
    },
    {
      "epoch": 0.6060606060606061,
      "eval_loss": 5.347131729125977,
      "eval_runtime": 4.8934,
      "eval_samples_per_second": 33.923,
      "eval_steps_per_second": 0.613,
      "step": 15
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 2.3363702297210693,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 5.4134,
      "step": 16
    },
    {
      "epoch": 0.6464646464646465,
      "eval_loss": 5.321357250213623,
      "eval_runtime": 4.9027,
      "eval_samples_per_second": 33.859,
      "eval_steps_per_second": 0.612,
      "step": 16
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 2.3906755447387695,
      "learning_rate": 1.416666666666667e-05,
      "loss": 5.3305,
      "step": 17
    },
    {
      "epoch": 0.6868686868686869,
      "eval_loss": 5.292910099029541,
      "eval_runtime": 4.9268,
      "eval_samples_per_second": 33.693,
      "eval_steps_per_second": 0.609,
      "step": 17
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.44368839263916,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 5.3406,
      "step": 18
    },
    {
      "epoch": 0.7272727272727273,
      "eval_loss": 5.257543563842773,
      "eval_runtime": 4.9839,
      "eval_samples_per_second": 33.308,
      "eval_steps_per_second": 0.602,
      "step": 18
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 2.4937825202941895,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 5.3134,
      "step": 19
    },
    {
      "epoch": 0.7676767676767676,
      "eval_loss": 5.225679874420166,
      "eval_runtime": 5.1205,
      "eval_samples_per_second": 32.419,
      "eval_steps_per_second": 0.586,
      "step": 19
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 2.547194480895996,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.2303,
      "step": 20
    },
    {
      "epoch": 0.8080808080808081,
      "eval_loss": 5.183907985687256,
      "eval_runtime": 5.1208,
      "eval_samples_per_second": 32.417,
      "eval_steps_per_second": 0.586,
      "step": 20
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 2.5578083992004395,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 5.1255,
      "step": 21
    },
    {
      "epoch": 0.8484848484848485,
      "eval_loss": 5.136340141296387,
      "eval_runtime": 5.1161,
      "eval_samples_per_second": 32.446,
      "eval_steps_per_second": 0.586,
      "step": 21
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.6553032398223877,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 5.1376,
      "step": 22
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 5.085525035858154,
      "eval_runtime": 5.1496,
      "eval_samples_per_second": 32.236,
      "eval_steps_per_second": 0.583,
      "step": 22
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 2.733492374420166,
      "learning_rate": 1.916666666666667e-05,
      "loss": 5.1051,
      "step": 23
    },
    {
      "epoch": 0.9292929292929293,
      "eval_loss": 5.0193634033203125,
      "eval_runtime": 5.0473,
      "eval_samples_per_second": 32.889,
      "eval_steps_per_second": 0.594,
      "step": 23
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 2.765582799911499,
      "learning_rate": 2e-05,
      "loss": 5.0082,
      "step": 24
    },
    {
      "epoch": 0.9696969696969697,
      "eval_loss": 4.950736999511719,
      "eval_runtime": 4.989,
      "eval_samples_per_second": 33.273,
      "eval_steps_per_second": 0.601,
      "step": 24
    }
  ],
  "logging_steps": 1,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6378880818708480.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}