{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8298755186721992,
  "eval_steps": 25,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002074688796680498,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.9284,
      "step": 1
    },
    {
      "epoch": 0.05186721991701245,
      "grad_norm": 79.10929107666016,
      "learning_rate": 1.4201183431952663e-07,
      "loss": 1.2205,
      "step": 25
    },
    {
      "epoch": 0.05186721991701245,
      "eval_loss": 0.898228645324707,
      "eval_runtime": 41.4826,
      "eval_samples_per_second": 21.841,
      "eval_steps_per_second": 5.472,
      "step": 25
    },
    {
      "epoch": 0.1037344398340249,
      "grad_norm": 64.46797180175781,
      "learning_rate": 2.8994082840236686e-07,
      "loss": 0.8806,
      "step": 50
    },
    {
      "epoch": 0.1037344398340249,
      "eval_loss": 0.783169686794281,
      "eval_runtime": 41.8537,
      "eval_samples_per_second": 21.647,
      "eval_steps_per_second": 5.424,
      "step": 50
    },
    {
      "epoch": 0.15560165975103735,
      "grad_norm": 61.91770553588867,
      "learning_rate": 4.378698224852071e-07,
      "loss": 0.8311,
      "step": 75
    },
    {
      "epoch": 0.15560165975103735,
      "eval_loss": 0.7539569139480591,
      "eval_runtime": 41.7737,
      "eval_samples_per_second": 21.688,
      "eval_steps_per_second": 5.434,
      "step": 75
    },
    {
      "epoch": 0.2074688796680498,
      "grad_norm": 71.48536682128906,
      "learning_rate": 5.857988165680473e-07,
      "loss": 0.7368,
      "step": 100
    },
    {
      "epoch": 0.2074688796680498,
      "eval_loss": 0.7413491606712341,
      "eval_runtime": 41.7951,
      "eval_samples_per_second": 21.677,
      "eval_steps_per_second": 5.431,
      "step": 100
    },
    {
      "epoch": 0.25933609958506226,
      "grad_norm": 109.77881622314453,
      "learning_rate": 7.337278106508875e-07,
      "loss": 0.6719,
      "step": 125
    },
    {
      "epoch": 0.25933609958506226,
      "eval_loss": 0.7641308307647705,
      "eval_runtime": 41.7732,
      "eval_samples_per_second": 21.689,
      "eval_steps_per_second": 5.434,
      "step": 125
    },
    {
      "epoch": 0.3112033195020747,
      "grad_norm": 70.72398376464844,
      "learning_rate": 8.816568047337278e-07,
      "loss": 0.6884,
      "step": 150
    },
    {
      "epoch": 0.3112033195020747,
      "eval_loss": 0.7019675970077515,
      "eval_runtime": 41.805,
      "eval_samples_per_second": 21.672,
      "eval_steps_per_second": 5.43,
      "step": 150
    },
    {
      "epoch": 0.3630705394190871,
      "grad_norm": 116.62774658203125,
      "learning_rate": 9.999024041442455e-07,
      "loss": 0.7906,
      "step": 175
    },
    {
      "epoch": 0.3630705394190871,
      "eval_loss": 0.6973831057548523,
      "eval_runtime": 41.8286,
      "eval_samples_per_second": 21.66,
      "eval_steps_per_second": 5.427,
      "step": 175
    },
    {
      "epoch": 0.4149377593360996,
      "grad_norm": 96.68453216552734,
      "learning_rate": 9.964905480067584e-07,
      "loss": 0.6676,
      "step": 200
    },
    {
      "epoch": 0.4149377593360996,
      "eval_loss": 0.7133656144142151,
      "eval_runtime": 41.8429,
      "eval_samples_per_second": 21.652,
      "eval_steps_per_second": 5.425,
      "step": 200
    },
    {
      "epoch": 0.46680497925311204,
      "grad_norm": 55.1112174987793,
      "learning_rate": 9.882369320834068e-07,
      "loss": 0.8055,
      "step": 225
    },
    {
      "epoch": 0.46680497925311204,
      "eval_loss": 0.6769455075263977,
      "eval_runtime": 41.8352,
      "eval_samples_per_second": 21.656,
      "eval_steps_per_second": 5.426,
      "step": 225
    },
    {
      "epoch": 0.5186721991701245,
      "grad_norm": 90.48117065429688,
      "learning_rate": 9.752220453700554e-07,
      "loss": 0.7137,
      "step": 250
    },
    {
      "epoch": 0.5186721991701245,
      "eval_loss": 0.6899203658103943,
      "eval_runtime": 41.8154,
      "eval_samples_per_second": 21.667,
      "eval_steps_per_second": 5.429,
      "step": 250
    },
    {
      "epoch": 0.5705394190871369,
      "grad_norm": 75.77264404296875,
      "learning_rate": 9.575728086215091e-07,
      "loss": 0.7415,
      "step": 275
    },
    {
      "epoch": 0.5705394190871369,
      "eval_loss": 0.663297712802887,
      "eval_runtime": 41.7881,
      "eval_samples_per_second": 21.681,
      "eval_steps_per_second": 5.432,
      "step": 275
    },
    {
      "epoch": 0.6224066390041494,
      "grad_norm": 175.5083465576172,
      "learning_rate": 9.354613366244106e-07,
      "loss": 0.6871,
      "step": 300
    },
    {
      "epoch": 0.6224066390041494,
      "eval_loss": 0.6589707136154175,
      "eval_runtime": 41.8294,
      "eval_samples_per_second": 21.659,
      "eval_steps_per_second": 5.427,
      "step": 300
    },
    {
      "epoch": 0.6742738589211619,
      "grad_norm": 80.65347290039062,
      "learning_rate": 9.091032597394012e-07,
      "loss": 0.6895,
      "step": 325
    },
    {
      "epoch": 0.6742738589211619,
      "eval_loss": 0.6799529194831848,
      "eval_runtime": 41.8081,
      "eval_samples_per_second": 21.67,
      "eval_steps_per_second": 5.43,
      "step": 325
    },
    {
      "epoch": 0.7261410788381742,
      "grad_norm": 67.32386779785156,
      "learning_rate": 8.7875562108081e-07,
      "loss": 0.721,
      "step": 350
    },
    {
      "epoch": 0.7261410788381742,
      "eval_loss": 0.6336647272109985,
      "eval_runtime": 41.7777,
      "eval_samples_per_second": 21.686,
      "eval_steps_per_second": 5.434,
      "step": 350
    },
    {
      "epoch": 0.7780082987551867,
      "grad_norm": 123.56040954589844,
      "learning_rate": 8.447143698405059e-07,
      "loss": 0.6144,
      "step": 375
    },
    {
      "epoch": 0.7780082987551867,
      "eval_loss": 0.6625879406929016,
      "eval_runtime": 41.749,
      "eval_samples_per_second": 21.701,
      "eval_steps_per_second": 5.437,
      "step": 375
    },
    {
      "epoch": 0.8298755186721992,
      "grad_norm": 86.80571746826172,
      "learning_rate": 8.073114752009387e-07,
      "loss": 0.7663,
      "step": 400
    },
    {
      "epoch": 0.8298755186721992,
      "eval_loss": 0.6124003529548645,
      "eval_runtime": 41.7721,
      "eval_samples_per_second": 21.689,
      "eval_steps_per_second": 5.434,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 964,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4329971279462400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}